Search

The context information such as product category plays a critical role in sequential recommendation. Recent years have witnessed a growing interest in context-aware sequential recommender systems. Existing studies often treat the contexts as auxiliary feature vectors without considering the sequential dependency in contexts. However, such a dependency provides valuable clues to predict the user's future behavior. For example, a user might buy electronic accessories after he/she buy an electronic product. In this paper, we propose a novel seq2seq translation architecture to highlight the importance of sequential dependency in contexts for sequential recommendation. Specifically, we first construct a collateral context sequence in addition to the main interaction sequence. We then generalize recent advancements in translation model from sequences of words in two languages to sequences of items and contexts in recommender systems. Taking the category information as an item's context, we develop a basic coupled and an extended tripled seq2seq translation models to encode the category-item and item-category-item relations between the item and context sequences. We conduct extensive experiments on three real world datasets. The results demonstrate the superior performance of the proposed model compared with the state-of-the-art baselines.

This letter introduces an abstract learning problem called the "set embedding": The objective is to map sets into probability distributions so as to lose less information. We relate set union and intersection operations with corresponding interpolations of probability distributions. We also demonstrate a preliminary solution with experimental results on toy set embedding examples., Comment: To be presented at Sets & Partitions (NeurIPS 2019 workshop)

Regularization plays a crucial role in machine learning models, especially for deep neural networks. The existing regularization techniques mainly rely on the i.i.d. assumption and only consider the knowledge from the current sample, without the leverage of the neighboring relationship between samples. In this work, we propose a general regularizer called \textbf{Patch-level Neighborhood Interpolation~(Pani)} that conducts a non-local representation in the computation of networks. Our proposal explicitly constructs patch-level graphs in different layers and then linearly interpolates neighborhood patch features, serving as a general and effective regularization strategy. Further, we customize our approach into two kinds of popular regularization methods, namely Virtual Adversarial Training (VAT) and MixUp as well as its variants. The first derived \textbf{Pani VAT} presents a novel way to construct non-local adversarial smoothness by employing patch-level interpolated perturbations. The second derived \textbf{Pani MixUp} method extends the MixUp, and achieves superiority over MixUp and competitive performance over state-of-the-art variants of MixUp method with a significant advantage in computational efficiency. Extensive experiments have verified the effectiveness of our Pani approach in both supervised and semi-supervised settings., Comment: Accepted in ACML 2023 conference track

iDASH is a competition soliciting implementations of cryptographic schemes of interest in the context of biology. In 2019, one track asked for multi-party computation implementations of training of a machine learning model suitable for two datasets from cancer research. In this note, we describe our solution submitted to the competition. We found that the training can be run on three AWS c5.9xlarge instances in less then one minute using MPC tolerating one semi-honest corruption, and less than ten seconds at a slightly lower accuracy., Comment: 4 pages

Single-photon sources are a fundamental resource in quantum optics. The indistinguishability and purity of photons emitted from different sources are crucial (necessary, essential) properties for many quantum applications to ensure high-visibility interference between different sources. The state of a single-photon source is described by the modes occupied by the single light quanta. Thus the ability to determine the mode structure of a single-photon source provides a means to assess its quality, compare different sources, and provide feedback for source engineering. Here, we propose and demonstrate an experimental scheme that allows for complete characterization of the spectral-temporal state of a pulsed single-photon source. The density matrix elements of the single-photon source are determined by spectral interferometry with a known single-photon reference. Frequency-resolved coincidence measurements are performed after the unknown single-photon source is interfered with a single-photon reference pulse. Fourier analysis of the frequency-resolved two-photon interference pattern reveals the spectral-temporal density matrix of the broadband single-photon source. We present an experimental realization of this method for pure and mixed state pulsed, single-photon sources.

High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection. Existing state-of-the-art frameworks first encode the input image as a low-resolution representation through a subnetwork that is formed by connecting high-to-low resolution convolutions \emph{in series} (e.g., ResNet, VGGNet), and then recover the high-resolution representation from the encoded low-resolution representation. Instead, our proposed network, named as High-Resolution Network (HRNet), maintains high-resolution representations through the whole process. There are two key characteristics: (i) Connect the high-to-low resolution convolution streams \emph{in parallel}; (ii) Repeatedly exchange the information across resolutions. The benefit is that the resulting representation is semantically richer and spatially more precise. We show the superiority of the proposed HRNet in a wide range of applications, including human pose estimation, semantic segmentation, and object detection, suggesting that the HRNet is a stronger backbone for computer vision problems. All the codes are available at~{\url{https://github.com/HRNet}}., Comment: To appear in TPAMI. State-of-the-art performance on human pose estimation, semantic segmentation, object detection, instance segmentation, and face alignment. Full version of arXiv:1904.04514. (arXiv admin note: text overlap with arXiv:1904.04514)

The design of deep graph models still remains to be investigated and the crucial part is how to explore and exploit the knowledge from different hops of neighbors in an efficient way. In this paper, we propose a novel RNN-like deep graph neural network architecture by incorporating AdaBoost into the computation of network; and the proposed graph convolutional network called AdaGCN~(Adaboosting Graph Convolutional Network) has the ability to efficiently extract knowledge from high-order neighbors of current nodes and then integrates knowledge from different hops of neighbors into the network in an Adaboost way. Different from other graph neural networks that directly stack many graph convolution layers, AdaGCN shares the same base neural network architecture among all ``layers'' and is recursively optimized, which is similar to an RNN. Besides, We also theoretically established the connection between AdaGCN and existing graph convolutional methods, presenting the benefits of our proposal. Finally, extensive experiments demonstrate the consistent state-of-the-art prediction performance on graphs across different label rates and the computational advantage of our approach AdaGCN~\footnote{Code is available at \url{https://github.com/datake/AdaGCN}.}, Comment: Published on International Conference on Learning Representations (ICLR) 2021

Lepton flavor violation decays are channels which may lead to fundamental discoveries in the forthcoming years and this make it an exciting research field for beyond the Standard Model searches. In this work, we present an analysis of the lepton flavor violation decays $l_{\alpha}\rightarrow 3l_{\beta}$ in Minimal R-symmetric Supersymmetric Standard Model. The prediction for BR($l_{\alpha}\rightarrow 3l_{\beta}$) depend on the off-diagonal entries of the slepton mass matrix. The contributions to Wilson coefficients can be classified into Higgs penguins, photon penguins, Z penguins, and box diagrams. It shows the contribution from Z penguins dominates the predictions for BR($l_{\alpha}\rightarrow 3l_{\beta}$), and the contributions from Higgs penguins and box diagrams play different roles in different decay channels. The theoretical predictions for BR($l_{\alpha}\rightarrow 3l_{\beta}$) can reach the future experimental limits, and there channels are very promising to be observed in near future experiment., Comment: 16 pages,6 figures

Image denoising is the process of removing noise from noisy images, which is an image domain transferring task, i.e., from a single or several noise level domains to a photo-realistic domain. In this paper, we propose an effective image denoising method by learning two image priors from the perspective of domain alignment. We tackle the domain alignment on two levels. 1) the feature-level prior is to learn domain-invariant features for corrupted images with different level noise; 2) the pixel-level prior is used to push the denoised images to the natural image manifold. The two image priors are based on $\mathcal{H}$-divergence theory and implemented by learning classifiers in adversarial training manners. We evaluate our approach on multiple datasets. The results demonstrate the effectiveness of our approach for robust image denoising on both synthetic and real-world noisy images. Furthermore, we show that the feature-level prior is capable of alleviating the discrepancy between different level noise. It can be used to improve the blind denoising performance in terms of distortion measures (PSNR and SSIM), while pixel-level prior can effectively improve the perceptual quality to ensure the realistic outputs, which is further validated by subjective evaluation.

We present a new method for improving the performances of variational autoencoder (VAE). In addition to enforcing the deep feature consistent principle thus ensuring the VAE output and its corresponding input images to have similar deep features, we also implement a generative adversarial training mechanism to force the VAE to output realistic and natural images. We present experimental results to show that the VAE trained with our new method outperforms state of the art in generating face images with much clearer and more natural noses, eyes, teeth, hair textures as well as reasonable backgrounds. We also show that our method can learn powerful embeddings of input face images, which can be used to achieve facial attribute manipulation. Moreover we propose a multi-view feature extraction strategy to extract effective image representations, which can be used to achieve state of the art performance in facial attribute prediction., Comment: Accepted in Neurocomputing, 2019. arXiv admin note: text overlap with arXiv:1610.00291

Why do deep neural networks (DNNs) benefit from very high dimensional parameter spaces? Their huge parameter complexities vs. stunning performances in practice is all the more intriguing and not explainable using the standard theory of model selection for regular models. In this work, we propose a geometrically flavored information-theoretic approach to study this phenomenon. Namely, we introduce the locally varying dimensionality of the parameter space of neural network models by considering the number of significant dimensions of the Fisher information matrix, and model the parameter space as a manifold using the framework of singular semi-Riemannian geometry. We derive model complexity measures which yield short description lengths for deep neural network models based on their singularity analysis thus explaining the good performance of DNNs despite their large number of parameters., Comment: This work first appeared under the former title "Lightlike Neuromanifolds, Occam's Razor and Deep Learning"

The Internet of Things (IoT), as a cutting-edge integrated cross-technology, promises to informationize people's daily lives, while being threatened by continuous challenges of eavesdropping and tampering. The emerging quantum cryptography, harnessing the random nature of quantum mechanics, may also enable unconditionally secure control network, beyond the applications in secure communications. Here, we present a quantum-enhanced cryptographic remote control scheme that combines quantum randomness and one-time pad algorithm for delivering commands remotely. We experimentally demonstrate this on an unmanned aircraft vehicle (UAV) control system. We precharge quantum random number (QRN) into controller and controlee before launching UAV, instead of distributing QRN like standard quantum communication during flight. We statistically verify the randomness of both quantum keys and the converted ciphertexts to check the security capability. All commands in the air are found to be completely chaotic after encryption, and only matched keys on UAV can decipher those commands precisely. In addition, the controlee does not response to the commands that are not or incorrectly encrypted, showing the immunity against interference and decoy. Our work adds true randomness and quantum enhancement into the realm of secure control algorithm in a straightforward and practical fashion, providing a promoted solution for the security of artificial intelligence and IoT., Comment: 7 pages, 5 figures, 2 tables

High-resolution representation learning plays an essential role in many vision problems, e.g., pose estimation and semantic segmentation. The high-resolution network (HRNet)~\cite{SunXLW19}, recently developed for human pose estimation, maintains high-resolution representations through the whole process by connecting high-to-low resolution convolutions in \emph{parallel} and produces strong high-resolution representations by repeatedly conducting fusions across parallel convolutions. In this paper, we conduct a further study on high-resolution representations by introducing a simple yet effective modification and apply it to a wide range of vision tasks. We augment the high-resolution representation by aggregating the (upsampled) representations from all the parallel convolutions rather than only the representation from the high-resolution convolution as done in~\cite{SunXLW19}. This simple modification leads to stronger representations, evidenced by superior results. We show top results in semantic segmentation on Cityscapes, LIP, and PASCAL Context, and facial landmark detection on AFLW, COFW, $300$W, and WFLW. In addition, we build a multi-level representation from the high-resolution representation and apply it to the Faster R-CNN object detection framework and the extended frameworks. The proposed approach achieves superior results to existing single-model networks on COCO object detection. The code and models have been publicly available at \url{https://github.com/HRNet}.

In a graph convolutional network, we assume that the graph $G$ is generated wrt some observation noise. During learning, we make small random perturbations $\Delta{}G$ of the graph and try to improve generalization. Based on quantum information geometry, $\Delta{}G$ can be characterized by the eigendecomposition of the graph Laplacian matrix. We try to minimize the loss wrt the perturbed $G+\Delta{G}$ while making $\Delta{G}$ to be effective in terms of the Fisher information of the neural network. Our proposed model can consistently improve graph convolutional networks on semi-supervised node classification tasks with reasonable computational overhead. We present three different geometries on the manifold of graphs: the intrinsic geometry measures the information theoretic dynamics of a graph; the extrinsic geometry characterizes how such dynamics can affect externally a graph neural network; the embedding geometry is for measuring node embeddings. These new analytical tools are useful in developing a good understanding of graph neural networks and fostering new techniques., Comment: Published in UAI 2019

Deep neural networks have been widely deployed in various machine learning tasks. However, recent works have demonstrated that they are vulnerable to adversarial examples: carefully crafted small perturbations to cause misclassification by the network. In this work, we propose a novel defense mechanism called Boundary Conditional GAN to enhance the robustness of deep neural networks against adversarial examples. Boundary Conditional GAN, a modified version of Conditional GAN, can generate boundary samples with true labels near the decision boundary of a pre-trained classifier. These boundary samples are fed to the pre-trained classifier as data augmentation to make the decision boundary more robust. We empirically show that the model improved by our approach consistently defenses against various types of adversarial attacks successfully. Further quantitative investigations about the improvement of robustness and visualization of decision boundaries are also provided to justify the effectiveness of our strategy. This new defense mechanism that uses boundary samples to enhance the robustness of networks opens up a new way to defense adversarial attacks consistently.

Most previous works usually explained adversarial examples from several specific perspectives, lacking relatively integral comprehension about this problem. In this paper, we present a systematic study on adversarial examples from three aspects: the amount of training data, task-dependent and model-specific factors. Particularly, we show that adversarial generalization (i.e. test accuracy on adversarial examples) for standard training requires more data than standard generalization (i.e. test accuracy on clean examples); and uncover the global relationship between generalization and robustness with respect to the data size especially when data is augmented by generative models. This reveals the trade-off correlation between standard generalization and robustness in limited training data regime and their consistency when data size is large enough. Furthermore, we explore how different task-dependent and model-specific factors influence the vulnerability of deep neural networks by extensive empirical analysis. Relevant recommendations on defense against adversarial attacks are provided as well. Our results outline a potential path towards the luminous and systematic understanding of adversarial examples.

Graph Convolutional Networks(GCNs) play a crucial role in graph learning tasks, however, learning graph embedding with few supervised signals is still a difficult problem. In this paper, we propose a novel training algorithm for Graph Convolutional Network, called Multi-Stage Self-Supervised(M3S) Training Algorithm, combined with self-supervised learning approach, focusing on improving the generalization performance of GCNs on graphs with few labeled nodes. Firstly, a Multi-Stage Training Framework is provided as the basis of M3S training method. Then we leverage DeepCluster technique, a popular form of self-supervised learning, and design corresponding aligning mechanism on the embedding space to refine the Multi-Stage Training Framework, resulting in M3S Training Algorithm. Finally, extensive experimental results verify the superior performance of our algorithm on graphs with few labeled nodes under different label rates compared with other state-of-the-art approaches., Comment: AAAI Conference on Artificial Intelligence (AAAI 2020)

The effectiveness of Graph Convolutional Networks (GCNs) has been demonstrated in a wide range of graph-based machine learning tasks. However, the update of parameters in GCNs is only from labeled nodes, lacking the utilization of unlabeled data. In this paper, we apply Virtual Adversarial Training (VAT), an adversarial regularization method based on both labeled and unlabeled data, on the supervised loss of GCN to enhance its generalization performance. By imposing virtually adversarial smoothness on the posterior distribution in semi-supervised learning, VAT yields improvement on the Symmetrical Laplacian Smoothness of GCNs. In addition, due to the difference of property in features, we perturb virtual adversarial perturbations on sparse and dense features, resulting in GCN Sparse VAT (GCNSVAT) and GCN Dense VAT (GCNDVAT) algorithms, respectively. Extensive experiments verify the effectiveness of our two methods across different training sizes. Our work paves the way towards better understanding the direction of improvement on GCNs in the future., Comment: Chinese Conference on Pattern Recognition and Computer Vision(PRCV) 2019 Oral paper

This is an official pytorch implementation of Deep High-Resolution Representation Learning for Human Pose Estimation. In this work, we are interested in the human pose estimation problem with a focus on learning reliable high-resolution representations. Most existing methods recover high-resolution representations from low-resolution representations produced by a high-to-low resolution network. Instead, our proposed network maintains high-resolution representations through the whole process. We start from a high-resolution subnetwork as the first stage, gradually add high-to-low resolution subnetworks one by one to form more stages, and connect the mutli-resolution subnetworks in parallel. We conduct repeated multi-scale fusions such that each of the high-to-low resolution representations receives information from other parallel representations over and over, leading to rich high-resolution representations. As a result, the predicted keypoint heatmap is potentially more accurate and spatially more precise. We empirically demonstrate the effectiveness of our network through the superior pose estimation results over two benchmark datasets: the COCO keypoint detection dataset and the MPII Human Pose dataset. The code and models have been publicly available at \url{https://github.com/leoxiaobin/deep-high-resolution-net.pytorch}., Comment: accepted by CVPR2019

The learning data requirements are analyzed for the construction of stealth attacks in state estimation. In particular, the training data set is used to compute a sample covariance matrix that results in a random matrix with a Wishart distribution. The ergodic attack performance is defined as the average attack performance obtained by taking the expectation with respect to the distribution of the training data set. The impact of the training data size on the ergodic attack performance is characterized by proposing an upper bound for the performance. Simulations on the IEEE 30-Bus test system show that the proposed bound is tight in practical settings., Comment: International Conference on Acoustics, Speech, and Signal Processing 2019