Search

Having the difficulty of solving the semantic gap between images and texts for the image captioning task, conventional studies in this area paid some attention to treating semantic concepts as a bridge between the two modalities and improved captioning performance accordingly. Although promising results on concept prediction were obtained, the aforementioned studies normally ignore the relationship among concepts, which relies on not only objects in the image, but also word dependencies in the text, so that offers a considerable potential for improving the process of generating good descriptions. In this paper, we propose a structured concept predictor (SCP) to predict concepts and their structures, then we integrate them into captioning, so as to enhance the contribution of visual signals in this task via concepts and further use their relations to distinguish cross-modal semantics for better description generation. Particularly, we design weighted graph convolutional networks (W-GCN) to depict concept relations driven by word dependencies, and then learns differentiated contributions from these concepts for following decoding process. Therefore, our approach captures potential relations among concepts and discriminatively learns different concepts, so that effectively facilitates image captioning with inherited information across modalities. Extensive experiments and their results demonstrate the effectiveness of our approach as well as each proposed module in this work., Comment: 13 pages, 4 figures. Published at EMNLP 2023 (Main Conference, Oral)

Implementing intelligent control of robots is a difficult task, especially when dealing with complex black-box systems, because of the lack of visibility and understanding of how these robots work internally. This paper proposes an Intelligent Social Learning (ISL) algorithm to enable intelligent control of black-box robotic systems. Inspired by mutual learning among individuals in human social groups, ISL includes learning, imitation, and self-study styles. Individuals in the learning style use the Levy flight search strategy to learn from the best performer and form the closest relationships. In the imitation style, individuals mimic the best performer with a second-level rapport by employing a random perturbation strategy. In the self-study style, individuals learn independently using a normal distribution sampling method while maintaining a distant relationship with the best performer. Individuals in the population are regarded as autonomous intelligent agents in each style. Neural networks perform strategic actions in three styles to interact with the environment and the robot and iteratively optimize the network policy. Overall, ISL builds on the principles of intelligent optimization, incorporating ideas from reinforcement learning, and possesses strong search capabilities, fast computation speed, fewer hyperparameters, and insensitivity to sparse rewards. The proposed ISL algorithm is compared with four state-of-the-art methods on six continuous control benchmark cases in MuJoCo to verify its effectiveness and advantages. Furthermore, ISL is adopted in the simulation and experimental grasping tasks of the UR3 robot for validations, and satisfactory solutions are yielded.

Colloidal particles can spontaneously self-assemble into ordered structures, which not only can manipulate the propagation of light, but also vibration or phonons. Using Monte Carlo simulation, we study the self-assembly of perfectly aligned segment rod particles with lateral flat cutting. Under the help of surface attractions, we find that particles with different cutting degree can self-assemble into different crystal phases characterized by bond coordination z that varies from 3 to 6. Importantly, we identify a transformable super-isostatic structures with pgg symmetry and redundant bonds (z=5). We find that this structure can support either the soft bulk model or soft edge model depending on its Poisson's ratio which can be tuned from positive to negative by a uniform soft deformation. Importantly, the bulk soft modes are associated with states of self-stress along the direction of zero strain during the uniform soft deformation. This self-assembled transformable super-isostatic structure may act as mechanical metamaterials with potential application in micro-mechanical engineering., Comment: 12 pages,6 figures

Diffusion-based image generation models, such as Stable Diffusion or DALL-E 2, are able to learn from given images and generate high-quality samples following the guidance from prompts. For instance, they can be used to create artistic images that mimic the style of an artist based on his/her original artworks or to maliciously edit the original images for fake content. However, such ability also brings serious ethical issues without proper authorization from the owner of the original images. In response, several attempts have been made to protect the original images from such unauthorized data usage by adding imperceptible perturbations, which are designed to mislead the diffusion model and make it unable to properly generate new samples. In this work, we introduce a perturbation purification platform, named IMPRESS, to evaluate the effectiveness of imperceptible perturbations as a protective measure. IMPRESS is based on the key observation that imperceptible perturbations could lead to a perceptible inconsistency between the original image and the diffusion-reconstructed image, which can be used to devise a new optimization strategy for purifying the image, which may weaken the protection of the original image from unauthorized data usage (e.g., style mimicking, malicious editing). The proposed IMPRESS platform offers a comprehensive evaluation of several contemporary protection methods, and can be used as an evaluation platform for future protection methods., Comment: 21 pages, 11 figures, 9 tables. Accepted by NeurIPS 2023

In social network, a person located at the periphery region (marginal node) is likely to be treated unfairly when compared with the persons at the center. While existing fairness works on graphs mainly focus on protecting sensitive attributes (e.g., age and gender), the fairness incurred by the graph structure should also be given attention. On the other hand, the information aggregation mechanism of graph neural networks amplifies such structure unfairness, as marginal nodes are often far away from other nodes. In this paper, we focus on novel fairness incurred by the graph structure on graph neural networks, named \emph{structure fairness}. Specifically, we first analyzed multiple graphs and observed that marginal nodes in graphs have a worse performance of downstream tasks than others in graph neural networks. Motivated by the observation, we propose \textbf{S}tructural \textbf{Fair} \textbf{G}raph \textbf{N}eural \textbf{N}etwork (SFairGNN), which combines neighborhood expansion based structure debiasing with hop-aware attentive information aggregation to achieve structure fairness. Our experiments show \SFairGNN can significantly improve structure fairness while maintaining overall performance in the downstream tasks., Comment: SIGKDD Explorations (To Appear)

We present a novel approach to cooperative aerial transportation through a team of drones, using optimal control theory and a hierarchical control strategy. We assume the drones are connected to the payload through rigid attachments, essentially transforming the whole system into a larger flying object with "thrust modules" at the attachment locations of the drones. We investigate the optimal arrangement of the thrust modules around the payload, so that the resulting system is robust to disturbances. We choose the $\mathcal{H}_2$ norm as a measure of robustness, and propose an iterative optimization routine to compute the optimal layout of the vehicles around the object. We experimentally validate our approach using four drones and comparing the disturbance rejection performances achieved by two different layouts (the optimal one and a sub-optimal one), and observe that the results match our predictions., Comment: 7 pages, 7 figures, conference paper

Vision-Language (VL) pre-trained models have shown their superiority on many multimodal tasks. However, the adversarial robustness of such models has not been fully explored. Existing approaches mainly focus on exploring the adversarial robustness under the white-box setting, which is unrealistic. In this paper, we aim to investigate a new yet practical task to craft image and text perturbations using pre-trained VL models to attack black-box fine-tuned models on different downstream tasks. Towards this end, we propose VLATTACK to generate adversarial samples by fusing perturbations of images and texts from both single-modal and multimodal levels. At the single-modal level, we propose a new block-wise similarity attack (BSA) strategy to learn image perturbations for disrupting universal representations. Besides, we adopt an existing text attack strategy to generate text perturbations independent of the image-modal attack. At the multimodal level, we design a novel iterative cross-search attack (ICSA) method to update adversarial image-text pairs periodically, starting with the outputs from the single-modal level. We conduct extensive experiments to attack five widely-used VL pre-trained models for six tasks. Experimental results show that VLATTACK achieves the highest attack success rates on all tasks compared with state-of-the-art baselines, which reveals a blind spot in the deployment of pre-trained VL models. Source codes can be found at https://github.com/ericyinyzy/VLAttack., Comment: Accepted by NeurIPS 2023, 21 pages

Health risk prediction is one of the fundamental tasks under predictive modeling in the medical domain, which aims to forecast the potential health risks that patients may face in the future using their historical Electronic Health Records (EHR). Researchers have developed several risk prediction models to handle the unique challenges of EHR data, such as its sequential nature, high dimensionality, and inherent noise. These models have yielded impressive results. Nonetheless, a key issue undermining their effectiveness is data insufficiency. A variety of data generation and augmentation methods have been introduced to mitigate this issue by expanding the size of the training data set through the learning of underlying data distributions. However, the performance of these methods is often limited due to their task-unrelated design. To address these shortcomings, this paper introduces a novel, end-to-end diffusion-based risk prediction model, named MedDiffusion. It enhances risk prediction performance by creating synthetic patient data during training to enlarge sample space. Furthermore, MedDiffusion discerns hidden relationships between patient visits using a step-wise attention mechanism, enabling the model to automatically retain the most vital information for generating high-quality data. Experimental evaluation on four real-world medical datasets demonstrates that MedDiffusion outperforms 14 cutting-edge baselines in terms of PR-AUC, F1, and Cohen's Kappa. We also conduct ablation studies and benchmark our model against GAN-based alternatives to further validate the rationality and adaptability of our model design. Additionally, we analyze generated data to offer fresh insights into the model's interpretability.

Based on the recently developed resummation-based quantum Monte Carlo method for the SU($N$) spin and loop-gas models, we develop a new algorithm, dubbed ResumEE, to compute the entanglement entropy (EE) with greatly enhanced efficiency. Our ResumEE exponentially speeds up the computation of the exponentially small value of the $\langle e^{-S^{(2)}}\rangle$, where $S^{(2)}$ is the 2nd order R\'enyi EE, such that the $S^{(2)}$ for a generic 2D quantum SU($N$) spin models can be readily computed with high accuracy. We benchmark our algorithm with the previously proposed estimators of $S^{(2)}$ on 1D and 2D SU($2$) Heisenberg spin systems to reveal its superior performance and then use it to detect the entanglement scaling data of the N\'eel-to-VBS transition on 2D SU($N$) Heisenberg model with continuously varying $N$. Our ResumEE algorithm is efficient for precisely evaluating the entanglement entropy of SU($N$) spin models with continuous $N$ and reliable access to the conformal field theory data for the highly entangled quantum matter., Comment: 11 pages, 9 figures

Parameter-efficient fine-tuning (PEFT) enables efficient adaptation of pre-trained language models (PLMs) to specific tasks. By tuning only a minimal set of (extra) parameters, PEFT achieves performance that is comparable to standard fine-tuning. However, despite its prevalent use, the security implications of PEFT remain largely unexplored. In this paper, we take the initial steps and present PETA, a novel trojan attack that compromises the weights of PLMs by accounting for downstream adaptation through bilevel optimization: the upper-level objective embeds the backdoor into a model while the lower-level objective simulates PEFT to both retain the PLM's task-specific performance and ensure that the backdoor persists after fine-tuning. With extensive evaluation across a variety of downstream tasks and trigger designs, we demonstrate PETA's effectiveness in terms of both attack success rate and clean accuracy, even when the attacker does not have full knowledge of the victim user's training process.

We present ReMasker, a new method of imputing missing values in tabular data by extending the masked autoencoding framework. Compared with prior work, ReMasker is both simple -- besides the missing values (i.e., naturally masked), we randomly ``re-mask'' another set of values, optimize the autoencoder by reconstructing this re-masked set, and apply the trained model to predict the missing values; and effective -- with extensive evaluation on benchmark datasets, we show that ReMasker performs on par with or outperforms state-of-the-art methods in terms of both imputation fidelity and utility under various missingness settings, while its performance advantage often increases with the ratio of missing data. We further explore theoretical justification for its effectiveness, showing that ReMasker tends to learn missingness-invariant representations of tabular data. Our findings indicate that masked modeling represents a promising direction for further research on tabular data imputation. The code is publicly available.

Pre-trained language models (PLMs) have demonstrated remarkable performance as few-shot learners. However, their security risks under such settings are largely unexplored. In this work, we conduct a pilot study showing that PLMs as few-shot learners are highly vulnerable to backdoor attacks while existing defenses are inadequate due to the unique challenges of few-shot scenarios. To address such challenges, we advocate MDP, a novel lightweight, pluggable, and effective defense for PLMs as few-shot learners. Specifically, MDP leverages the gap between the masking-sensitivity of poisoned and clean samples: with reference to the limited few-shot data as distributional anchors, it compares the representations of given samples under varying masking and identifies poisoned samples as ones with significant variations. We show analytically that MDP creates an interesting dilemma for the attacker to choose between attack effectiveness and detection evasiveness. The empirical evaluation using benchmark datasets and representative attacks validates the efficacy of MDP., Comment: Accepted by NeurIPS'23

We propose an approach to estimate the end-to-end GSNR accurately in a short time when a data center interconnect (DCI) network operator receives a service request from users, not by measuring the GSNR at the operational route and wavelength for the End-End optical path but by simply applying a QoT probe channel link by link, at a convenient wavelength/modulation-format for measurement. Assuming connections between coherent transceivers of various frequency ranges, modulators, and modulation formats, we propose a new device software architecture in which the DCI network operator optimizes the transmission mode between user transceivers with high accuracy using only standard parameters such as Bit Error Rate. In this paper, we first experimentally built three different routes of 32 km/72 km/122 km in the C-band to confirm the accuracy of this approach. For the operational end-to-end GSNR measurements, the accuracy estimated from the sum of the measurements for each link was 0.6 dB, and the wavelength-dependent error was about 0.2 dB. Then, using field fibers deployed in the NSF COSMOS testbed (deployed in an urban area), a Linux-based transmission device software architecture, and coherent transceivers with different optical frequency ranges, modulators, and modulation formats, the fast WDM provisioning of an optical path was completed within 6 minutes (with a Q-factor error of about 0.7 dB)., Comment: 10 pages, 11 figures, 3 tables