Search

In noisy and reverberant environments, the performance of deep learning-based speech separation methods drops dramatically because previous methods are not designed and optimized for such situations. To address this issue, we propose a multi-stage end-to-end learning method that decouples the difficult speech separation problem in noisy and reverberant environments into three sub-problems: speech denoising, separation, and de-reverberation. The probability and speed of searching for the optimal solution of the speech separation model are improved by reducing the solution space. Moreover, since the channel information of the audio sequence in the time domain is crucial for speech separation, we propose a triple-path structure capable of modeling the channel dimension of audio sequences. Experimental results show that the proposed multi-stage triple-path method can improve the performance of speech separation models at the cost of little model parameter increment., Accepted by ICASSP 2023

In Causal Discovery with latent variables, We define two data paradigms: definite data: a single-skeleton structure with observed nodes single-value, and indefinite data: a set of multi-skeleton structures with observed nodes multi-value. Multi,skeletons induce low sample utilization and multi values induce incapability of the distribution assumption, both leading that recovering causal relations from indefinite data is, as of yet, largely unexplored. We design the causal strength variational model to settle down these two problems. Specifically, we leverage the causal strength instead of independent noise as latent variable to mediate evidence lower bound. By this design ethos, The causal strength of different skeletons is regarded as a distribution and can be expressed as a single-valued causal graph matrix. Moreover, considering the latent confounders, we disentangle the causal graph G into two relatisubgraphs O and C. O contains pure relations between observed nodes, while C represents the relations from latent variables to observed nodes. We summarize the above designs as Confounding Disentanglement Causal Discovery (biCD), which is tailored to learn causal representation from indefinite data under the latent confounding. Finally, we conduct comprehensive experiments on synthetic and real-world data to demonstrate the effectiveness of our method.

The affective reasoning task is a set of emerging affect-based tasks in conversation, including Emotion Recognition in Conversation (ERC),Emotion-Cause Pair Extraction (ECPE), and Emotion-Cause Span Recognition (ECSR). Existing methods make various assumptions on the apparent relationship while neglecting the essential causal model due to the nonuniqueness of skeletons and unobservability of implicit causes. This paper settled down the above two problems and further proposed Conversational Affective Causal Discovery (CACD). It is a novel causal discovery method showing how to discover causal relationships in a conversation via designing a common skeleton and generating a substitute for implicit causes. CACD contains two steps: (i) building a common centering one graph node causal skeleton for all utterances in variable-length conversations; (ii) Causal Auto-Encoder (CAE) correcting the skeleton to yield causal representation through generated implicit causes and known explicit causes. Comprehensive experiments demonstrate that our novel method significantly outperforms the SOTA baselines in six affect-related datasets on the three tasks.

With the development of adversarial attacks, adversairal examples have been widely used to enhance the robustness of the training models on deep neural networks. Although considerable efforts of adversarial attacks on improving the transferability of adversarial examples have been developed, the attack success rate of the transfer-based attacks on the surrogate model is much higher than that on victim model under the low attack strength (e.g., the attack strength $\epsilon=8/255$). In this paper, we first systematically investigated this issue and found that the enormous difference of attack success rates between the surrogate model and victim model is caused by the existence of a special area (known as fuzzy domain in our paper), in which the adversarial examples in the area are classified wrongly by the surrogate model while correctly by the victim model. Then, to eliminate such enormous difference of attack success rates for improving the transferability of generated adversarial examples, a fuzziness-tuned method consisting of confidence scaling mechanism and temperature scaling mechanism is proposed to ensure the generated adversarial examples can effectively skip out of the fuzzy domain. The confidence scaling mechanism and the temperature scaling mechanism can collaboratively tune the fuzziness of the generated adversarial examples through adjusting the gradient descent weight of fuzziness and stabilizing the update direction, respectively. Specifically, the proposed fuzziness-tuned method can be effectively integrated with existing adversarial attacks to further improve the transferability of adverarial examples without changing the time complexity. Extensive experiments demonstrated that fuzziness-tuned method can effectively enhance the transferability of adversarial examples in the latest transfer-based attacks.

Distribution shift is a major challenge in machine learning, as models often perform poorly during the test stage if the test distribution differs from the training distribution. In this paper, we focus on domain shifts, which occur when the model is applied to new domains that are different from the ones it was trained on, and propose a new approach called D^3G. Unlike previous approaches that aim to learn a single model that is domain invariant, D^3G learns domain-specific models by leveraging the relations among different domains. Concretely, D^3G learns a set of training-domain-specific functions during the training stage and reweights them based on domain relations during the test stage. These domain relations can be directly derived or learned from fixed domain meta-data. Under mild assumptions, we theoretically proved that using domain relations to reweight training-domain-specific functions achieves stronger generalization compared to averaging them. Empirically, we evaluated the effectiveness of D^3G using both toy and real-world datasets for tasks such as temperature regression, land use classification, and molecule-protein interaction prediction. Our results showed that D^3G consistently outperformed state-of-the-art methods, with an average improvement of 10.6% in performance.

Transformer, as an alternative to CNN, has been proven effective in many modalities (e.g., texts and images). For 3D point cloud transformers, existing efforts focus primarily on pushing their accuracy to the state-of-the-art level. However, their latency lags behind sparse convolution-based models (3x slower), hindering their usage in resource-constrained, latency-sensitive applications (such as autonomous driving). This inefficiency comes from point clouds' sparse and irregular nature, whereas transformers are designed for dense, regular workloads. This paper presents FlatFormer to close this latency gap by trading spatial proximity for better computational regularity. We first flatten the point cloud with window-based sorting and partition points into groups of equal sizes rather than windows of equal shapes. This effectively avoids expensive structuring and padding overheads. We then apply self-attention within groups to extract local features, alternate sorting axis to gather features from different directions, and shift windows to exchange features across groups. FlatFormer delivers state-of-the-art accuracy on Waymo Open Dataset with 4.6x speedup over (transformer-based) SST and 1.4x speedup over (sparse convolutional) CenterPoint. This is the first point cloud transformer that achieves real-time performance on edge GPUs and is faster than sparse convolutional methods while achieving on-par or even superior accuracy on large-scale benchmarks., CVPR 2023. The first two authors contributed equally to this work. Project page: https://flatformer.mit.edu

Reasoning, a crucial aspect of NLP research, has not been adequately addressed by prevailing models including Large Language Model. Conversation reasoning, as a critical component of it, remains largely unexplored due to the absence of a well-designed cognitive model. In this paper, inspired by intuition theory on conversation cognition, we develop a conversation cognitive model (CCM) that explains how each utterance receives and activates channels of information recursively. Besides, we algebraically transformed CCM into a structural causal model (SCM) under some mild assumptions, rendering it compatible with various causal discovery methods. We further propose a probabilistic implementation of the SCM for utterance-level relation reasoning. By leveraging variational inference, it explores substitutes for implicit causes, addresses the issue of their unobservability, and reconstructs the causal representations of utterances through the evidence lower bounds. Moreover, we constructed synthetic and simulated datasets incorporating implicit causes and complete cause labels, alleviating the current situation where all available datasets are implicit-causes-agnostic. Extensive experiments demonstrate that our proposed method significantly outperforms existing methods on synthetic, simulated, and real-world datasets. Finally, we analyze the performance of CCM under latent confounders and propose theoretical ideas for addressing this currently unresolved issue.

This paper presents a deep learning framework for medical video segmentation. Convolution neural network (CNN) and transformer-based methods have achieved great milestones in medical image segmentation tasks due to their incredible semantic feature encoding and global information comprehension abilities. However, most existing approaches ignore a salient aspect of medical video data - the temporal dimension. Our proposed framework explicitly extracts features from neighbouring frames across the temporal dimension and incorporates them with a temporal feature blender, which then tokenises the high-level spatio-temporal feature to form a strong global feature encoded via a Swin Transformer. The final segmentation results are produced via a UNet-like encoder-decoder architecture. Our model outperforms other approaches by a significant margin and improves the segmentation benchmarks on the VFSS2022 dataset, achieving a dice coefficient of 0.8986 and 0.8186 for the two datasets tested. Our studies also show the efficacy of the temporal feature blending scheme and cross-dataset transferability of learned capabilities. Code and models are fully available at https://github.com/SimonZeng7108/Video-SwinUNet.

Existing melody harmonization models have made great progress in improving the quality of generated harmonies, but most of them ignored the emotions beneath the music. Meanwhile, the variability of harmonies generated by previous methods is insufficient. To solve these problems, we propose a novel LSTM-based Hierarchical Variational Auto-Encoder (LHVAE) to investigate the influence of emotional conditions on melody harmonization, while improving the quality of generated harmonies and capturing the abundant variability of chord progressions. Specifically, LHVAE incorporates latent variables and emotional conditions at different levels (piece- and bar-level) to model the global and local music properties. Additionally, we introduce an attention-based melody context vector at each step to better learn the correspondence between melodies and harmonies. Objective experimental results show that our proposed model outperforms other LSTM-based models. Through subjective evaluation, we conclude that only altering the types of chords hardly changes the overall emotion of the music. The qualitative analysis demonstrates the ability of our model to generate variable harmonies., Comment: Accepted by IEEE SMC 2023

Understanding the performance of machine learning (ML) models across diverse data distributions is critically important for reliable applications. Despite recent empirical studies positing a near-perfect linear correlation between in-distribution (ID) and out-of-distribution (OOD) accuracies, we empirically demonstrate that this correlation is more nuanced under subpopulation shifts. Through rigorous experimentation and analysis across a variety of datasets, models, and training epochs, we demonstrate that OOD performance often has a nonlinear correlation with ID performance in subpopulation shifts. Our findings, which contrast previous studies that have posited a linear correlation in model performance during distribution shifts, reveal a "moon shape" correlation (parabolic uptrend curve) between the test performance on the majority subpopulation and the minority subpopulation. This non-trivial nonlinear correlation holds across model architectures, hyperparameters, training durations, and the imbalance between subpopulations. Furthermore, we found that the nonlinearity of this "moon shape" is causally influenced by the degree of spurious correlations in the training data. Our controlled experiments show that stronger spurious correlation in the training data creates more nonlinear performance correlation. We provide complementary experimental and theoretical analyses for this phenomenon, and discuss its implications for ML reliability and fairness. Our work highlights the importance of understanding the nonlinear effects of model improvement on performance in different subpopulations, and has the potential to inform the development of more equitable and responsible machine learning models., Comment: Accepted to the main conference of ICML 2023

In the transfer-based adversarial attacks, adversarial examples are only generated by the surrogate models and achieve effective perturbation in the victim models. Although considerable efforts have been developed on improving the transferability of adversarial examples generated by transfer-based adversarial attacks, our investigation found that, the big deviation between the actual and steepest update directions of the current transfer-based adversarial attacks is caused by the large update step length, resulting in the generated adversarial examples can not converge well. However, directly reducing the update step length will lead to serious update oscillation so that the generated adversarial examples also can not achieve great transferability to the victim models. To address these issues, a novel transfer-based attack, namely direction tuning attack, is proposed to not only decrease the update deviation in the large step length, but also mitigate the update oscillation in the small sampling step length, thereby making the generated adversarial examples converge well to achieve great transferability on victim models. In addition, a network pruning method is proposed to smooth the decision boundary, thereby further decreasing the update oscillation and enhancing the transferability of the generated adversarial examples. The experiment results on ImageNet demonstrate that the average attack success rate (ASR) of the adversarial examples generated by our method can be improved from 87.9\% to 94.5\% on five victim models without defenses, and from 69.1\% to 76.2\% on eight advanced defense methods, in comparison with that of latest gradient-based attacks.

System auditing has emerged as a key approach for monitoring system call events and investigating sophisticated attacks. Based on the collected audit logs, research has proposed to search for attack patterns or track the causal dependencies of system events to reveal the attack sequence. However, existing approaches either cannot reveal long-range attack sequences or suffer from the dependency explosion problem due to a lack of focus on attack-relevant parts, and thus are insufficient for investigating complex attacks. To bridge the gap, we propose Zebra, a system that synergistically integrates attack pattern search and causal dependency tracking for efficient attack investigation. With Zebra, security analysts can alternate between search and tracking to reveal the entire attack sequence in a progressive, user-guided manner, while mitigating the dependency explosion problem by prioritizing the attack-relevant parts. To enable this, Zebra provides (1) an expressive and concise domain-specific language, Tstl, for performing various types of search and tracking analyses, and (2) an optimized language execution engine for efficient execution over a big amount of auditing data. Evaluations on a broad set of attack cases demonstrate the effectiveness of Zebra in facilitating a timely attack investigation.

Emotion-cause pair extraction (ECPE) is an emerging task aiming to extract potential pairs of emotions and corresponding causes from documents. Previous approaches have focused on modeling the pair-to-pair relationship and achieved promising results. However, the clause-to-clause relationship, which fundamentally symbolizes the underlying structure of a document, has still been in its research infancy. In this paper, we define a novel clause-to-clause relationship. To learn it applicably, we propose a general clause-level encoding model named EA-GAT comprising E-GAT and Activation Sort. E-GAT is designed to aggregate information from different types of clauses; Activation Sort leverages the individual emotion/cause prediction and the sort-based mapping to propel the clause to a more favorable representation. Since EA-GAT is a clause-level encoding model, it can be broadly integrated with any previous approach. Experimental results show that our approach has a significant advantage over all current approaches on the Chinese and English benchmark corpus, with an average of $2.1\%$ and $1.03\%$.

We propose Video-TransUNet, a deep architecture for instance segmentation in medical CT videos constructed by integrating temporal feature blending into the TransUNet deep learning framework. In particular, our approach amalgamates strong frame representation via a ResNet CNN backbone, multi-frame feature blending via a Temporal Context Module (TCM), non-local attention via a Vision Transformer, and reconstructive capabilities for multiple targets via a UNet-based convolutional-deconvolutional architecture with multiple heads. We show that this new network design can significantly outperform other state-of-the-art systems when tested on the segmentation of bolus and pharynx/larynx in Videofluoroscopic Swallowing Study (VFSS) CT sequences. On our VFSS2022 dataset it achieves a dice coefficient of 0.8796 and an average surface distance of 1.0379 pixels. Note that tracking the pharyngeal bolus accurately is a particularly important application in clinical practice since it constitutes the primary method for diagnostics of swallowing impairment. Our findings suggest that the proposed model can indeed enhance the TransUNet architecture via exploiting temporal information and improving segmentation performance by a significant margin. We publish key source code, network weights, and ground truth annotations for simplified performance reproduction., Accepted by International Conference on Machine Vision 2022

Automated social behaviour analysis of mice has become an increasingly popular research area in behavioural neuroscience. Recently, pose information (i.e., locations of keypoints or skeleton) has been used to interpret social behaviours of mice. Nevertheless, effective encoding and decoding of social interaction information underlying the keypoints of mice has been rarely investigated in the existing methods. In particular, it is challenging to model complex social interactions between mice due to highly deformable body shapes and ambiguous movement patterns. To deal with the interaction modelling problem, we here propose a Cross-Skeleton Interaction Graph Aggregation Network (CS-IGANet) to learn abundant dynamics of freely interacting mice, where a Cross-Skeleton Node-level Interaction module (CS-NLI) is used to model multi-level interactions (i.e., intra-, inter- and cross-skeleton interactions). Furthermore, we design a novel Interaction-Aware Transformer (IAT) to dynamically learn the graph-level representation of social behaviours and update the node-level representation, guided by our proposed interaction-aware self-attention mechanism. Finally, to enhance the representation ability of our model, an auxiliary self-supervised learning task is proposed for measuring the similarity between cross-skeleton nodes. Experimental results on the standard CRMI13-Skeleton and our PDMB-Skeleton datasets show that our proposed model outperforms several other state-of-the-art approaches.

In strong adversarial attacks against deep neural networks (DNN), the generated adversarial example will mislead the DNN-implemented classifier by destroying the output features of the last layer. To enhance the robustness of the classifier, in our paper, a \textbf{F}eature \textbf{A}nalysis and \textbf{C}onditional \textbf{M}atching prediction distribution (FACM) model is proposed to utilize the features of intermediate layers to correct the classification. Specifically, we first prove that the intermediate layers of the classifier can still retain effective features for the original category, which is defined as the correction property in our paper. According to this, we propose the FACM model consisting of \textbf{F}eature \textbf{A}nalysis (FA) correction module, \textbf{C}onditional \textbf{M}atching \textbf{P}rediction \textbf{D}istribution (CMPD) correction module and decision module. The FA correction module is the fully connected layers constructed with the output of the intermediate layers as the input to correct the classification of the classifier. The CMPD correction module is a conditional auto-encoder, which can not only use the output of intermediate layers as the condition to accelerate convergence but also mitigate the negative effect of adversarial example training with the Kullback-Leibler loss to match prediction distribution. Through the empirically verified diversity property, the correction modules can be implemented synergistically to reduce the adversarial subspace. Hence, the decision module is proposed to integrate the correction modules to enhance the DNN classifier's robustness. Specially, our model can be achieved by fine-tuning and can be combined with other model-specific defenses.

Black-box query attacks, which rely only on the output of the victim model, have proven to be effective in attacking deep learning models. However, existing black-box query attacks show low performance in a novel scenario where only a few queries are allowed. To address this issue, we propose gradient aligned attacks (GAA), which use the gradient aligned losses (GAL) we designed on the surrogate model to estimate the accurate gradient to improve the attack performance on the victim model. Specifically, we propose a gradient aligned mechanism to ensure that the derivatives of the loss function with respect to the logit vector have the same weight coefficients between the surrogate and victim models. Using this mechanism, we transform the cross-entropy (CE) loss and margin loss into gradient aligned forms, i.e. the gradient aligned CE or margin losses. These losses not only improve the attack performance of our gradient aligned attacks in the novel scenario but also increase the query efficiency of existing black-box query attacks. Through theoretical and empirical analysis on the ImageNet database, we demonstrate that our gradient aligned mechanism is effective, and that our gradient aligned attacks can improve the attack performance in the novel scenario by 16.1\% and 31.3\% on the $l_2$ and $l_{\infty}$ norms of the box constraint, respectively, compared to four latest transferable prior-based query attacks. Additionally, the gradient aligned losses also significantly reduce the number of queries required in these transferable prior-based query attacks by a maximum factor of 2.9 times. Overall, our proposed gradient aligned attacks and losses show significant improvements in the attack performance and query efficiency of black-box query attacks, particularly in scenarios where only a few queries are allowed.

Multi-sensor fusion is essential for an accurate and reliable autonomous driving system. Recent approaches are based on point-level fusion: augmenting the LiDAR point cloud with camera features. However, the camera-to-LiDAR projection throws away the semantic density of camera features, hindering the effectiveness of such methods, especially for semantic-oriented tasks (such as 3D scene segmentation). In this paper, we break this deeply-rooted convention with BEVFusion, an efficient and generic multi-task multi-sensor fusion framework. It unifies multi-modal features in the shared bird's-eye view (BEV) representation space, which nicely preserves both geometric and semantic information. To achieve this, we diagnose and lift key efficiency bottlenecks in the view transformation with optimized BEV pooling, reducing latency by more than 40x. BEVFusion is fundamentally task-agnostic and seamlessly supports different 3D perception tasks with almost no architectural changes. It establishes the new state of the art on nuScenes, achieving 1.3% higher mAP and NDS on 3D object detection and 13.6% higher mIoU on BEV map segmentation, with 1.9x lower computation cost. Code to reproduce our results is available at https://github.com/mit-han-lab/bevfusion., Comment: The first two authors contributed equally to this work. Project page: https://bevfusion.mit.edu

Despite the increased adoption of open-source cyber threat intelligence (OSCTI) for acquiring knowledge about cyber threats, little effort has been made to harvest knowledge from a large number of unstructured OSCTI reports available in the wild (e.g., security articles, threat reports). These reports provide comprehensive threat knowledge in a variety of entities (e.g., IOCs, threat actors, TTPs) and relations, which, however, are hard to gather due to diverse report formats, large report quantities, and complex structures and nuances in the natural language report text. To bridge the gap, we propose ThreatKG, a system for automated open-source cyber threat knowledge gathering and management. ThreatKG automatically collects a large number of OSCTI reports from various sources, extracts high-fidelity threat knowledge, constructs a threat knowledge graph, and updates the knowledge graph by continuously ingesting new knowledge. To address multiple challenges, ThreatKG provides: (1) a hierarchical ontology for modeling a variety of threat knowledge entities and relations; (2) an accurate deep learning-based pipeline for threat knowledge extraction; (3) a scalable and extensible system architecture for threat knowledge graph construction, persistence, updating, and exploration. Evaluations on a large number of reports demonstrate the effectiveness of ThreatKG in threat knowledge gathering and management

There is an inescapable long-tailed class-imbalance issue in many real-world classification problems. Existing long-tailed classification methods focus on the single-domain setting, where all examples are drawn from the same distribution. However, real-world scenarios often involve multiple domains with distinct imbalanced class distributions. We study this multi-domain long-tailed learning problem and aim to produce a model that generalizes well across all classes and domains. Towards that goal, we introduce TALLY, which produces invariant predictors by balanced augmenting hidden representations over domains and classes. Built upon a proposed selective balanced sampling strategy, TALLY achieves this by mixing the semantic representation of one example with the domain-associated nuisances of another, producing a new representation for use as data augmentation. To improve the disentanglement of semantic representations, TALLY further utilizes a domain-invariant class prototype that averages out domain-specific effects. We evaluate TALLY on four long-tailed variants of classical domain generalization benchmarks and two real-world imbalanced multi-domain datasets. The results indicate that TALLY consistently outperforms other state-of-the-art methods in both subpopulation shift and domain shift.

Understanding causality helps to structure interventions to achieve specific goals and enables predictions under interventions. With the growing importance of learning causal relationships, causal discovery tasks have transitioned from using traditional methods to infer potential causal structures from observational data to the field of pattern recognition involved in deep learning. The rapid accumulation of massive data promotes the emergence of causal search methods with brilliant scalability. Existing summaries of causal discovery methods mainly focus on traditional methods based on constraints, scores and FCMs, there is a lack of perfect sorting and elaboration for deep learning-based methods, also lacking some considers and exploration of causal discovery methods from the perspective of variable paradigms. Therefore, we divide the possible causal discovery tasks into three types according to the variable paradigm and give the definitions of the three tasks respectively, define and instantiate the relevant datasets for each task and the final causal model constructed at the same time, then reviews the main existing causal discovery methods for different tasks. Finally, we propose some roadmaps from different perspectives for the current research gaps in the field of causal discovery and point out future research directions., Comment: 26 pages,10 figures. arXiv admin note: text overlap with arXiv:2012.07138, arXiv:1605.08179, arXiv:2203.14237 by other authors

Histopathological images provide the definitive source of cancer diagnosis, containing information used by pathologists to identify and subclassify malignant disease, and to guide therapeutic choices. These images contain vast amounts of information, much of which is currently unavailable to human interpretation. Supervised deep learning approaches have been powerful for classification tasks, but they are inherently limited by the cost and quality of annotations. Therefore, we developed Histomorphological Phenotype Learning, an unsupervised methodology, which requires no annotations and operates via the self-discovery of discriminatory image features in small image tiles. Tiles are grouped into morphologically similar clusters which appear to represent recurrent modes of tumor growth emerging under natural selection. These clusters have distinct features which can be identified using orthogonal methods. Applied to lung cancer tissues, we show that they align closely with patient outcomes, with histopathologically recognised tumor types and growth patterns, and with transcriptomic measures of immunophenotype.

Deep neural networks are easily attacked by imperceptible perturbation. Presently, adversarial training (AT) is the most effective method to enhance the robustness of the model against adversarial examples. However, because adversarial training solved a min-max value problem, in comparison with natural training, the robustness and generalization are contradictory, i.e., the robustness improvement of the model will decrease the generalization of the model. To address this issue, in this paper, a new concept, namely confidence threshold (CT), is introduced and the reducing of the confidence threshold, known as confidence threshold reduction (CTR), is proven to improve both the generalization and robustness of the model. Specifically, to reduce the CT for natural training (i.e., for natural training with CTR), we propose a mask-guided divergence loss function (MDL) consisting of a cross-entropy loss term and an orthogonal term. The empirical and theoretical analysis demonstrates that the MDL loss improves the robustness and generalization of the model simultaneously for natural training. However, the model robustness improvement of natural training with CTR is not comparable to that of adversarial training. Therefore, for adversarial training, we propose a standard deviation loss function (STD), which minimizes the difference in the probabilities of the wrong categories, to reduce the CT by being integrated into the loss function of adversarial training. The empirical and theoretical analysis demonstrates that the STD based loss function can further improve the robustness of the adversarially trained model on basis of guaranteeing the changeless or slight improvement of the natural accuracy., Comment: Under review

As an indispensable part of modern human-computer interaction system, speech synthesis technology helps users get the output of intelligent machine more easily and intuitively, thus has attracted more and more attention. Due to the limitations of high complexity and low efficiency of traditional speech synthesis technology, the current research focus is the deep learning-based end-to-end speech synthesis technology, which has more powerful modeling ability and a simpler pipeline. It mainly consists of three modules: text front-end, acoustic model, and vocoder. This paper reviews the research status of these three parts, and classifies and compares various methods according to their emphasis. Moreover, this paper also summarizes the open-source speech corpus of English, Chinese and other languages that can be used for speech synthesis tasks, and introduces some commonly used subjective and objective speech quality evaluation method. Finally, some attractive future research directions are pointed out.

Access to labeled time series data is often limited in the real world, which constrains the performance of deep learning models in the field of time series analysis. Data augmentation is an effective way to solve the problem of small sample size and imbalance in time series datasets. The two key factors of data augmentation are the distance metric and the choice of interpolation method. SMOTE does not perform well on time series data because it uses a Euclidean distance metric and interpolates directly on the object. Therefore, we propose a DTW-based synthetic minority oversampling technique using siamese encoder for interpolation named DTWSSE. In order to reasonably measure the distance of the time series, DTW, which has been verified to be an effective method forts, is employed as the distance metric. To adapt the DTW metric, we use an autoencoder trained in an unsupervised self-training manner for interpolation. The encoder is a Siamese Neural Network for mapping the time series data from the DTW hidden space to the Euclidean deep feature space, and the decoder is used to map the deep feature space back to the DTW hidden space. We validate the proposed methods on a number of different balanced or unbalanced time series datasets. Experimental results show that the proposed method can lead to better performance of the downstream deep learning model., Comment: Accepted as full research paper in APWEB-WAIM 2021

The utilization of deep learning techniques in generating various contents (such as image, text, etc.) has become a trend. Especially music, the topic of this paper, has attracted widespread attention of countless researchers.The whole process of producing music can be divided into three stages, corresponding to the three levels of music generation: score generation produces scores, performance generation adds performance characteristics to the scores, and audio generation converts scores with performance characteristics into audio by assigning timbre or generates music in audio format directly. Previous surveys have explored the network models employed in the field of automatic music generation. However, the development history, the model evolution, as well as the pros and cons of same music generation task have not been clearly illustrated. This paper attempts to provide an overview of various composition tasks under different music generation levels, covering most of the currently popular music generation tasks using deep learning. In addition, we summarize the datasets suitable for diverse tasks, discuss the music representations, the evaluation methods as well as the challenges under different levels, and finally point out several future directions., 96 pages,this is a draft

In this paper we show that learning video feature spaces in which temporal cycles are maximally predictable benefits action classification. In particular, we propose a novel learning approach termed Cycle Encoding Prediction (CEP) that is able to effectively represent high-level spatio-temporal structure of unlabelled video content. CEP builds a latent space wherein the concept of closed forward-backward as well as backward-forward temporal loops is approximately preserved. As a self-supervision signal, CEP leverages the bi-directional temporal coherence of the video stream and applies loss functions that encourage both temporal cycle closure as well as contrastive feature separation. Architecturally, the underpinning network structure utilises a single feature encoder for all video snippets, adding two predictive modules that learn temporal forward and backward transitions. We apply our framework for pretext training of networks for action recognition tasks. We report significantly improved results for the standard datasets UCF101 and HMDB51. Detailed ablation studies support the effectiveness of the proposed components. We publish source code for the CEP components in full with this paper., accepted at BMVC

In classic network security games, the defender distributes defending resources to the nodes of the network, and the attacker attacks a node, with the objective to maximize the damage caused. Existing models assume that the attack at node u causes damage only at u. However, in many real-world security scenarios, the attack at a node u spreads to the neighbors of u and can cause damage at multiple nodes, e.g., for the outbreak of a virus. In this paper, we consider the network defending problem against contagious attacks. Existing works that study shared resources assume that the resource allocated to a node can be shared or duplicated between neighboring nodes. However, in real world, sharing resource naturally leads to a decrease in defending power of the source node, especially when defending against contagious attacks. To this end, we study the model in which resources allocated to a node can only be transferred to its neighboring nodes, which we refer to as a reallocation process. We show that this more general model is difficult in two aspects: (1) even for a fixed allocation of resources, we show that computing the optimal reallocation is NP-hard; (2) for the case when reallocation is not allowed, we show that computing the optimal allocation (against contagious attack) is also NP-hard. For positive results, we give a mixed integer linear program formulation for the problem and a bi-criteria approximation algorithm. Our experimental results demonstrate that the allocation and reallocation strategies our algorithm computes perform well in terms of minimizing the damage due to contagious attacks., Comment: 9 pages; AAAI 2021

Differential privacy provides a rigorous framework to quantify data privacy, and has received considerable interest recently. A randomized mechanism satisfying $(\epsilon, \delta)$-differential privacy (DP) roughly means that, except with a small probability $\delta$, altering a record in a dataset cannot change the probability that an output is seen by more than a multiplicative factor $e^{\epsilon} $. A well-known solution to $(\epsilon, \delta)$-DP is the Gaussian mechanism initiated by Dwork et al. [1] in 2006 with an improvement by Dwork and Roth [2] in 2014, where a Gaussian noise amount $\sqrt{2\ln \frac{2}{\delta}} \times \frac{\Delta}{\epsilon}$ of [1] or $\sqrt{2\ln \frac{1.25}{\delta}} \times \frac{\Delta}{\epsilon}$ of [2] is added independently to each dimension of the query result, for a query with $\ell_2$-sensitivity $\Delta$. Although both classical Gaussian mechanisms [1,2] assume $0 < \epsilon \leq 1$, our review finds that many studies in the literature have used the classical Gaussian mechanisms under values of $\epsilon$ and $\delta$ where the added noise amounts of [1,2] do not achieve $(\epsilon,\delta)$-DP. We obtain such result by analyzing the optimal noise amount $\sigma_{DP-OPT}$ for $(\epsilon,\delta)$-DP and identifying $\epsilon$ and $\delta$ where the noise amounts of classical mechanisms are even less than $\sigma_{DP-OPT}$. Since $\sigma_{DP-OPT}$ has no closed-form expression and needs to be approximated in an iterative manner, we propose Gaussian mechanisms by deriving closed-form upper bounds for $\sigma_{DP-OPT}$. Our mechanisms achieve $(\epsilon,\delta)$-DP for any $\epsilon$, while the classical mechanisms [1,2] do not achieve $(\epsilon,\delta)$-DP for large $\epsilon$ given $\delta$. Moreover, the utilities of our mechanisms improve those of [1,2] and are close to that of the optimal yet more computationally expensive Gaussian mechanism., Comment: 23 Pages

Regional style in Chinese folk songs is a rich treasure that can be used for ethnic music creation and folk culture research. In this paper, we propose MG-VAE, a music generative model based on VAE (Variational Auto-Encoder) that is capable of capturing specific music style and generating novel tunes for Chinese folk songs (Min Ge) in a manipulatable way. Specifically, we disentangle the latent space of VAE into four parts in an adversarial training way to control the information of pitch and rhythm sequence, as well as of music style and content. In detail, two classifiers are used to separate style and content latent space, and temporal supervision is utilized to disentangle the pitch and rhythm sequence. The experimental results show that the disentanglement is successful and our model is able to create novel folk songs with controllable regional styles. To our best knowledge, this is the first study on applying deep generative model and adversarial training for Chinese music generation., Accepted by the 7th Conference on Sound and Music Technology, 2019, Harbin, China

Local differential privacy (LDP) can provide each user with strong privacy guarantees under untrusted data curators while ensuring accurate statistics derived from privatized data. Due to its powerfulness, LDP has been widely adopted to protect privacy in various tasks (e.g., heavy hitters discovery, probability estimation) and systems (e.g., Google Chrome, Apple iOS). Although ${\epsilon}$-LDP has been proposed for many years, the more general notion of $({\epsilon}, {\delta})$-LDP has only been studied in very few papers, which mainly consider mean estimation for numeric data. Besides, prior solutions achieve $({\epsilon}, {\delta})$-LDP by leveraging Gaussian mechanism, which leads to low accuracy of the aggregated results. In this paper, we propose novel mechanisms that achieve $({\epsilon}, {\delta})$-LDP with high utility in data analytics and machine learning. Specifically, we first design $({\epsilon}, {\delta})$-LDP algorithms for collecting multi-dimensional numeric data, which can ensure higher accuracy than the optimal Gaussian mechanism while guaranteeing strong privacy for each user. Then, we investigate different local protocols for categorical attributes under $({\epsilon}, {\delta})$-LDP. Furthermore, we conduct theoretical analysis on the error bound and variance of the proposed algorithms. Experimental results on real and synthetic datasets demonstrate the high data utility of our proposed algorithms on both simple data statistics and complex machine learning models.

Understanding the morphological changes of primary neuronal cells induced by chemical compounds is essential for drug discovery. Using the data from a single high-throughput imaging assay, a classification model for predicting the biological activity of candidate compounds was introduced. The image recognition model which is based on deep convolutional neural network (CNN) architecture with residual connections achieved accuracy of 99.6$\%$ on a binary classification task of distinguishing untreated and treated rodent primary neuronal cells with Amyloid-$\beta_{(25-35)}$., Comment: 11 pages, 5 figures

High-dimensional crowdsourced data collected from numerous users produces rich knowledge about our society; however, it also brings unprecedented privacy threats to the participants. Local differential privacy (LDP), a variant of differential privacy, is recently proposed as a state-of-the-art privacy notion. Unfortunately, achieving LDP on high-dimensional crowdsourced data publication raises great challenges in terms of both computational efficiency and data utility. To this end, based on the expectation maximization (EM) algorithm and Lasso regression, we first propose efficient multi-dimensional joint distribution estimation algorithms with LDP. Then, we develop a local differentially private high-dimensional data publication algorithm (LoPub) by taking advantage of our distribution estimation techniques. In particular, correlations among multiple attributes are identified to reduce the dimensionality of crowdsourced data, thus speeding up the distribution learning process and achieving high data utility. Extensive experiments on real-world datasets demonstrate that our multivariate distribution estimation scheme significantly outperforms existing estimation schemes in terms of both communication overhead and estimation speed. Moreover, LoPub can keep, on average, 80% and 60% accuracy over the released datasets in terms of support vector machine and random forest classification, respectively.\ud