论文检索

Juan Hu, Xin Liao, Difei Gao, Satoshi Tsutsui, Qian Wang, Zheng Qin, Mike Zheng Shou

Deepfake videos are becoming increasingly realistic, showing few tampering traces on facial areas that vary between frames. Consequently, existing Deepfake detection methods struggle to detect unknown domain Deepfake videos while accurately locating the tampered region. To address this limitation, we propose Delocate, a novel Deepfake detection model that can both recognize and localize unknown domain Deepfake videos. Our method consists of two stages named recovering and localization. In the recovering stage, the model randomly masks regions of interest (ROIs) and reconstructs real faces without tampering traces, leading to a relatively good recovery effect for real faces and a poor recovery effect for fake faces. In the localization stage, the output of the recovery phase and the forgery ground truth mask serve as supervision to guide the forgery localization process. This process strategically emphasizes the recovery phase of fake faces with poor recovery, facilitating the localization of tampered regions. Our extensive experiments on four widely used benchmark datasets demonstrate that Delocate not only excels in localizing tampered areas but also enhances cross-domain detection performance.

Nima Hosseini Dashtbayaz, Ghazal Farhani, Boyu Wang, Charles X. Ling

The residual loss in Physics-Informed Neural Networks (PINNs) alters the simple recursive relation of layers in a feed-forward neural network by applying a differential operator, resulting in a loss landscape that is inherently different from those of common supervised problems. Therefore, relying on the existing theory leads to unjustified design choices and suboptimal performance. In this work, we analyze the residual loss by studying its characteristics at critical points to find the conditions that result in effective training of PINNs. Specifically, we first show that under certain conditions, the residual loss of PINNs can be globally minimized by a wide neural network. Furthermore, our analysis also reveals that an activation function with well-behaved high-order derivatives plays a crucial role in minimizing the residual loss. In particular, to solve a k-th order PDE, the k-th derivative of the activation function should be bijective. The established theory paves the way for designing and choosing effective activation functions for PINNs and explains why periodic activations have shown promising performance in certain cases. Finally, we verify our findings by conducting a set of experiments on several PDEs. Our code is publicly available at https://github.com/nimahsn/pinns_tf2.

Buyun He, Yingguang Yang, Qi Wu, Hao Liu, Renyu Yang, Hao Peng, Xiang Wang, Yong Liao, Pengyuan Zhou

Detecting social bots has evolved into a pivotal yet intricate task, aimed at combating the dissemination of misinformation and preserving the authenticity of online interactions. While earlier graph-based approaches, which leverage topological structure of social networks, yielded notable outcomes, they overlooked the inherent dynamicity of social networks -- In reality, they largely depicted the social network as a static graph and solely relied on its most recent state. Due to the absence of dynamicity modeling, such approaches are vulnerable to evasion, particularly when advanced social bots interact with other users to camouflage identities and escape detection. To tackle these challenges, we propose BotDGT, a novel framework that not only considers the topological structure, but also effectively incorporates dynamic nature of social network. Specifically, we characterize a social network as a dynamic graph. A structural module is employed to acquire topological information from each historical snapshot. Additionally, a temporal module is proposed to integrate historical context and model the evolving behavior patterns exhibited by social bots and legitimate users. Experimental results demonstrate the superiority of BotDGT against the leading methods that neglected the dynamic nature of social networks in terms of accuracy, recall, and F1-score.

Bing Han, Junyu Dai, Weituo Hao, Xinyan He, Dong Guo, Jitong Chen, Yuxuan Wang, Yanmin Qian, Xuchen Song

Music editing primarily entails the modification of instrument tracks or remixing in the whole, which offers a novel reinterpretation of the original piece through a series of operations. These music processing methods hold immense potential across various applications but demand substantial expertise. Prior methodologies, although effective for image and audio modifications, falter when directly applied to music. This is attributed to music's distinctive data nature, where such methods can inadvertently compromise the intrinsic harmony and coherence of music. In this paper, we develop InstructME, an Instruction guided Music Editing and remixing framework based on latent diffusion models. Our framework fortifies the U-Net with multi-scale aggregation in order to maintain consistency before and after editing. In addition, we introduce chord progression matrix as condition information and incorporate it in the semantic space to improve melodic harmony while editing. For accommodating extended musical pieces, InstructME employs a chunk transformer, enabling it to discern long-term temporal dependencies within music sequences. We tested InstructME in instrument-editing, remixing, and multi-round editing. Both subjective and objective evaluations indicate that our proposed method significantly surpasses preceding systems in music quality, text relevance and harmony. Demo samples are available at https://musicedit.github.io

Qiang Gao, Xiaolong Song, Li Huang, Goce Trajcevski, Fan Zhou, Xueqin Chen

Fine-grained urban flow inference (FUFI), which involves inferring fine-grained flow maps from their coarse-grained counterparts, is of tremendous interest in the realm of sustainable urban traffic services. To address the FUFI, existing solutions mainly concentrate on investigating spatial dependencies, introducing external factors, reducing excessive memory costs, etc., -- while rarely considering the catastrophic forgetting (CF) problem. Motivated by recent operator learning, we present an Urban Neural Operator solution with Incremental learning (UNOI), primarily seeking to learn grained-invariant solutions for FUFI in addition to addressing CF. Specifically, we devise an urban neural operator (UNO) in UNOI that learns mappings between approximation spaces by treating the different-grained flows as continuous functions, allowing a more flexible capture of spatial correlations. Furthermore, the phenomenon of CF behind time-related flows could hinder the capture of flow dynamics. Thus, UNOI mitigates CF concerns as well as privacy issues by placing UNO blocks in two incremental settings, i.e., flow-related and task-related. Experimental results on large-scale real-world datasets demonstrate the superiority of our proposed solution against the baselines.

Zhenkan Fu, Shikai Guo, Hui Li, Rong Chen, Xiaochen Li, He Jiang

As software development projects increasingly rely on open-source software, users face the risk of security vulnerabilities from third-party libraries. To address label and character noise in code changes, we present VF-Detector to automatically identifying bug-fix commits in actual noise development environment. VF-Detector consists of three componments: Data Pre-processing (DP), Vulnerability Confidence Computation (VCC) and Confidence Learning Denoising (CLD). The DP component is responsible for preprocessing code change data. The VCC component calculates code change confidence value for each bug-fix by extracting features at various granularity levels. The CLD component removes noise and enhances model robustness by pruning noisy data with confidence values and performing effort-aware adjustments. Experimental results demonstrate VF-Detector's superiority over state-of-the-art methods in EffortCost@L and Popt@L metrics on Java and Python datasets. The improvements were 6.5% and 5% for Java, and 23.4% and 17.8% for Python.

Wenjie Du, Shuai Zhang, Di Wu, Jun Xia, Ziyuan Zhao, Junfeng Fang, Yang Wang

In this paper, we address the challenge of accurately modeling and predicting Gibbs free energy in solute-solvent interactions, a pivotal yet complex aspect in the field of chemical modeling. Traditional approaches, primarily relying on deep learning models, face limitations in capturing the intricate dynamics of these interactions. To overcome these constraints, we introduce a novel framework, molecular modeling graph neural network (MMGNN), which more closely mirrors real-world chemical processes.Specifically, MMGNN explicitly models atomic interactions such as hydrogen bonds by initially forming indiscriminate connections between intermolecular atoms, which are then refined using an attention-based aggregation method, tailoring to specific solute-solvent pairs. To address the challenges of non-interactive or repulsive atomic interactions, MMGNN incorporates interpreters for nodes and edges in the merged graph, enhancing explainability and reducing redundancy. MMGNN stands as the first framework to explicitly align with real chemical processes, providing a more accurate and scientifically sound approach to modeling solute-solvent interactions. The infusion of explainability allows for the extraction of key subgraphs, which are pivotal for further research in solute-solvent dynamics. Extensive experimental validation confirms the efficacy and enhanced explainability of MMGNN.

Hastyn Doshi, Ayush Tripathi, Keshav Agarwal, Harshad Khadilkar, Shivaram Kalyanakrishnan

The railway scheduling problem requires the computation of an operable timetable that satisfies constraints involving railway infrastructure and resource occupancy times, while minimising average delay over a set of events. Since this problem is computationally hard, practical solutions typically roll out feasible (but suboptimal) schedules one step at a time, by choosing which train to move next in every step. The choices made by such algorithms are necessarily myopic, and incur the risk of driving the system to a deadlock. To escape deadlocks, the predominant approach is to stay away from states flagged as potentially unsafe by some fast-to-compute rule R. While many choices of R guarantee deadlock avoidance, they are suboptimal in the sense of also flagging some safe states as unsafe. In this paper, we revisit the literature on process scheduling and describe a rule R0 that is (i) necessary and sufficient for deadlock detection when the network has at least two tracks in each resource (station / track section), (ii) computable in linear time, and (iii) yields lower delays when combined with existing scheduling algorithms on both synthetic and real data sets from Indian Railways.

Jingyang Deng, Xingjian Li, Haoyi Xiong, Xiaoguang Hu, Jinwen Ma

Deep learning surrogate models aim to accelerate the solving of partial differential equations (PDEs) and have achieved certain promising results. Although several main-stream models through neural operator learning have been applied to delve into PDEs on varying geometries, they were designed to map the complex geometry to a latent uniform grid, which is still challenging to learn by the networks with general architectures. In this work, we rethink the critical factors of PDE solutions and propose a novel model-agnostic framework, called 3D Geometry-Guided Conditional adaptation (3D-GeoCA), for solving PDEs on arbitrary 3D geometries. Starting with a 3D point cloud geometry encoder, 3D-GeoCA can extract the essential and robust representations of any kind of geometric shapes, which conditionally guides the adaptation of hidden features in the surrogate model. We conduct experiments on two public computational fluid dynamics datasets, the Shape-Net Car and Ahmed-Body dataset, using several surrogate models as the backbones with various point cloud geometry encoders to simulate corresponding large-scale Reynolds Average Navier-Stokes equations. Equipped with 3D-GeoCA, these backbone models can reduce the L-2 error by a large margin. Moreover, this 3D-GeoCA is model-agnostic so that it can be applied to any surrogate model.

Xiaoxiao Chi, Xuyun Zhang, Yan Wang, Lianyong Qi, Amin Beheshti, Xiaolong Xu, Kim-Kwang Raymond Choo, Shuo Wang, Hongsheng Hu

Recommender systems have been successfully applied in many applications. Nonetheless, recent studies demonstrate that recommender systems are vulnerable to membership inference attacks (MIAs), leading to the leakage of users’ membership privacy. However, existing MIAs relying on shadow training suffer a large performance drop when the attacker lacks knowledge of the training data distribution and the model architecture of the target recommender system. To better understand the privacy risks of recommender systems, we propose shadow-free MIAs that directly leverage a user’s recommendations for membership inference. Without shadow training, the proposed attack can conduct MIAs efficiently and effectively under a practice scenario where the attacker is given only black-box access to the target recommender system. The proposed attack leverages an intuition that the recommender system personalizes a user’s recommendations if his historical interactions are used by it. Thus, an attacker can infer membership privacy by determining whether the recommendations are more similar to the interactions or the general popular items. We conduct extensive experiments on benchmark datasets across various recommender systems. Remarkably, our attack achieves far better attack accuracy with low false positive rates than baselines while with a much lower computational cost.

Shengchao Chen, Guodong Long, Tao Shen, Jing Jiang, Chengqi Zhang

On-device intelligence for weather forecasting uses local deep learning models to analyze weather patterns without centralized cloud computing, holds significance for supporting human activates. Federated Learning is a promising solution for such forecasting by enabling collaborative model training without sharing raw data. However, it faces three main challenges that hinder its reliability: (1) data heterogeneity among devices due to geographic differences; (2) data homogeneity within individual devices and (3) communication overload from sending large model parameters for collaboration. To address these challenges, this paper propose Federated Prompt learning for Weather Foundation Models on Devices (FedPoD), which enables devices to obtain highly customized models while maintaining communication efficiency. Concretely, our Adaptive Prompt Tuning leverages lightweight prompts guide frozen foundation model to generate more precise predictions, also conducts prompt-based multi-level communication to encourage multi-source knowledge fusion and regulate optimization. Additionally, Dynamic Graph Modeling constructs graphs from prompts, prioritizing collaborative training among devices with similar data distributions to against heterogeneity. Extensive experiments demonstrates FedPoD leads the performance among state-of-the-art baselines across various setting in real-world on-device weather forecasting datasets.

Jiayuan Chen, Changchang Yin, Yuanlong Wang, Ping Zhang

Deep learning-based predictive models, leveraging Electronic Health Records (EHR), are receiving increasing attention in healthcare. An effective representation of a patient's EHR should hierarchically encompass both the temporal relationships between historical visits and medical events, and the inherent structural information within these elements. Existing patient representation methods can be roughly categorized into sequential representation and graphical representation. The sequential representation methods focus only on the temporal relationships among longitudinal visits. On the other hand, the graphical representation approaches, while adept at extracting the graph-structured relationships between various medical events, fall short in effectively integrate temporal information. To capture both types of information, we model a patient's EHR as a novel temporal heterogeneous graph. This graph includes historical visits nodes and medical events nodes. It propagates structured information from medical event nodes to visit nodes and utilizes time-aware visit nodes to capture changes in the patient's health status. Furthermore, we introduce a novel temporal graph transformer (TRANS) that integrates temporal edge features, global positional encoding, and local structural encoding into heterogeneous graph convolution, capturing both temporal and structural information. We validate the effectiveness of TRANS through extensive experiments on three real-world datasets. The results show that our proposed approach achieves state-of-the-art performance.

Daoming Zong, Chaoyue Ding, Baoxiang Li, Jiakui Li, Ken Zheng

Multimodal learning is provably superior to unimodal learning. However, in practice, the best-performing unimodal networks often outperform jointly trained multimodal networks. This phenomenon can be attributed to the varying convergence and generalization rates across different modalities, leading to the dominance of one modality and causing underfitting of other modalities in simple multimodal joint training. To mitigate this issue, we propose two key ingredients: i) disentangling the learning of unimodal features and multimodal interaction through an intermediate representation fusion block; ii) modulating the logits of different modalities via dynamic coefficients during training to align their magnitudes with the target values, referred to as online logit modulation (OLM). Remarkably, OLM is model-agnostic and can be seamlessly integrated with most existing multimodal training frameworks. Empirical evidence shows that our approach brings significant enhancements over baselines on a wide range of multimodal tasks, covering video, audio, text, image, and depth modalities.

Zehan Zhu, Yan Huang, Xin Wang, Jinming Xu

In this paper, we propose a differentially private decentralized learning method (termed PrivSGP-VR) which employs stochastic gradient push with variance reduction and guarantees (epsilon, delta)-differential privacy (DP) for each node. Our theoretical analysis shows that, under DP Gaussian noise with constant variance, PrivSGP-VR achieves a sub-linear convergence rate of O(1/sqrt(nK)), where n and K are the number of nodes and iterations, respectively, which is independent of stochastic gradient variance, and achieves a linear speedup with respect to n. Leveraging the moments accountant method, we further derive an optimal K to maximize the model utility under certain privacy budget in decentralized settings. With this optimized K, PrivSGP-VR achieves a tight utility bound of O(sqrt(d*log(1/delta))/(sqrt(n)*J*epsilon)), where J and d are the number of local samples and the dimension of decision variable, respectively, which matches that of the server-client distributed counterparts, and exhibits an extra factor of 1/sqrt(n) improvement compared to that of the existing decentralized counterparts, such as A(DP)2SGD. Extensive experiments corroborate our theoretical findings, especially in terms of the maximized utility with optimized K, in fully decentralized settings.

Yun Zhu, Yaoke Wang, Haizhou Shi, Siliang Tang

Rich textual and topological information of textual graphs need to be modeled in real-world applications such as webpages, e-commerce, and academic articles. Practitioners have been long following the path of adopting a shallow text encoder and a subsequent graph neural network (GNN) to solve this problem. In light of recent advancements in large language models (LLMs), it is apparent that integrating LLMs for enhanced textual encoding can substantially improve the performance of textual graphs. Nevertheless, the efficiency of these methods poses a significant challenge. In this paper, we propose ENGINE, a parameter- and memory-efficient fine-tuning method for textual graphs with an LLM encoder. The key insight is to combine the LLMs and GNNs through a tunable side structure, which significantly reduces the training complexity without impairing the joint model's capacity. Extensive experiments on textual graphs demonstrate our method's effectiveness by achieving the best model performance, meanwhile having the lowest training cost compared to previous methods. Moreover, we introduce two variants with caching and dynamic early exit to further enhance training and inference speed. Specifically, caching accelerates ENGINE's training by 12x, and dynamic early exit achieves up to 5x faster inference with a negligible performance drop (at maximum 1.17% relevant drop across 7 datasets). Our codes are available at: https://github.com/ZhuYun97/ENGINE.

Yiwen Zhu, Jinyi Liu, Wenya Wei, Qianyi Fu, Yujing Hu, Zhou Fang, Bo An, Jianye Hao, Tangjie Lv, Changjie Fan

Reinforcement Learning (RL) is a widely employed technique in decision-making problems, encompassing two fundamental operations -- policy evaluation and policy improvement. Enhancing learning efficiency remains a key challenge in RL, with many efforts focused on using ensemble critics to boost policy evaluation efficiency. However, when using multiple critics, the actor in the policy improvement process can obtain different gradients. Previous studies have combined these gradients without considering their disagreements. Therefore, optimizing the policy improvement process is crucial to enhance learning efficiency. This study focuses on investigating the impact of gradient disagreements caused by ensemble critics on policy improvement. We introduce the concept of uncertainty of gradient directions as a means to measure the disagreement among gradients utilized in the policy improvement process. Through measuring the disagreement among gradients, we find that transitions with lower uncertainty of gradient directions are more reliable in the policy improvement process. Building on this analysis, we propose a method called von Mises-Fisher Experience Resampling (vMFER), which optimizes the policy improvement process by resampling transitions and assigning higher confidence to transitions with lower uncertainty of gradient directions. Our experiments demonstrate that vMFER significantly outperforms the benchmark and is particularly well-suited for ensemble structures in RL.

Yinlin Zhu, Xunkai Li, Zhengyu Wu, Di Wu, Miao Hu, Rong-Hua Li

Subgraph federated learning (subgraph-FL) is a new distributed paradigm that facilitates the collaborative training of graph neural networks (GNNs) by multi-client subgraphs. Unfortunately, a significant challenge of subgraph-FL arises from subgraph heterogeneity, which stems from node and topology variation, causing the impaired performance of the global GNN. Despite various studies, they have not yet thoroughly investigated the impact mechanism of subgraph heterogeneity. To this end, we decouple node and topology variation, revealing that they correspond to differences in label distribution and structure homophily. Remarkably, these variations lead to significant differences in the class-wise knowledge reliability of multiple local GNNs, misguiding the model aggregation with varying degrees. Building on this insight, we propose topology-aware data-free knowledge distillation technology (FedTAD), enhancing reliable knowledge transfer from the local model to the global model. Extensive experiments on six public datasets consistently demonstrate the superiority of FedTAD over state-of-the-art baselines.

Wenhao Zhu, Guojie Song, Liang Wang, Shaoguo Liu

Graph Transformers (GTs) have significantly advanced the field of graph representation learning by overcoming the limitations of message-passing graph neural networks (GNNs) and demonstrating promising performance and expressive power. However, the quadratic complexity of self-attention mechanism in GTs has limited their scalability, and previous approaches to address this issue often suffer from expressiveness degradation or lack of versatility. To address this issue, we propose AnchorGT, a novel attention architecture for GTs with global receptive field and almost linear complexity, which serves as a flexible building block to improve the scalability of a wide range of GT models. Inspired by anchor-based GNNs, we employ structurally important k-dominating node set as anchors and design an attention mechanism that focuses on the relationship between individual nodes and anchors, while retaining the global receptive field for all nodes. With its intuitive design, AnchorGT can easily replace the attention module in various GT models with different network architectures and structural encodings, resulting in reduced computational overhead without sacrificing performance. In addition, we theoretically prove that AnchorGT attention can be strictly more expressive than Weisfeiler-Lehman test, showing its superiority in representing graph structures. Our experiments on three state-of-the-art GT models demonstrate that their AnchorGT variants can achieve similar results while being faster and significantly more memory efficient.

Bowei Zhu, Shaojie Li, Yong Liu

Minimax problems have achieved success in machine learning such as adversarial training, robust optimization, reinforcement learning. For theoretical analysis, current optimal excess risk bounds, which are composed by generalization error and optimization error, present 1/n-rates in strongly-convex-strongly-concave (SC-SC) settings. Existing studies mainly focus on minimax problems with specific algorithms for optimization error, with only a few studies on generalization performance, which limit better excess risk bounds. In this paper, we study the generalization bounds measured by the gradients of primal functions using uniform localized convergence. We obtain a sharper high probability generalization error bound for nonconvex-strongly-concave (NC-SC) stochastic minimax problems. Furthermore, we provide dimension-independent results under Polyak-Lojasiewicz condition for the outer layer. Based on our generalization error bound, we analyze some popular algorithms such as empirical saddle point (ESP), gradient descent ascent (GDA) and stochastic gradient descent ascent (SGDA). We derive better excess primal risk bounds with further reasonable assumptions, which, to the best of our knowledge, are n times faster than exist results in minimax problems.

Ziyu Zhou, Gengyu Lyu, Yiming Huang, Zihao Wang, Ziyu Jia, Zhen Yang

Transformer has gained widespread adoption in modeling time series due to the exceptional ability of its self-attention mechanism in capturing long-range dependencies. However, when processing time series data with numerous variates, the vanilla self-attention mechanism tends to distribute attention weights evenly and smoothly, causing row-homogenization in attention maps and further hampering time series forecasting. To tackle this issue, we propose an advanced Transformer architecture entitled SDformer, which designs two novel modules, Spectral-Filter-Transform (SFT) and Dynamic-Directional-Attention (DDA), and integrates them into the encoder of Transformer to achieve more intensive attention allocation. Specifically, the SFT module utilizes the Fast Fourier Transform to select the most prominent frequencies, along with a Hamming Window to smooth and denoise the filtered series data; The DDA module applies a specialized kernel function to the query and key vectors projected from the denoised data, concentrating this innovative attention mechanism more effectively on the most informative variates to obtain a sharper attention distribution. These two modules jointly enable attention weights to be more salient among numerous variates, which in turn enhances the attention's ability to capture multivariate correlations, improving the performance in forecasting. Extensive experiments on public datasets demonstrate its superior performance over other state-of-the-art models. Code is available at https://github.com/zhouziyu02/SDformer.