检索结果-内蒙古大学图书馆

A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protection

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wu, Bingzhe Li, Jintang Yu, Junchi Bian, Yatao Zhang, Hengtong Chen, Chaochao Hou, Chengbin Fu, Guoji Chen, Liang Xu, Tingyang Rong, Yu Zheng, Xiaolin Huang, Junzhou He, Ran Wu, Baoyuan Sun, Guangyu Cui, Peng Zheng, Zibing Liu, Zhe Zhao, Peilin Tencent AI Lab United States Sun Yat-Sen University China Institute of Automation Chinese Academy of Sciences China Zhejiang University China University of Texas Arlington United States School of Data Science Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen China Peking University China Tsinghua University China Zhejiang Lab China

Deep graph learning has achieved remarkable progresses in both business and scientific areas ranging from finance and e-commerce, to drug and advanced material discovery. Despite these progresses, how to ensure various deep graph learning algorithms behave in a socially responsible manner and meet regulatory compliance requirements becomes an emerging problem, especially in risk-sensitive domains. Trustworthy graph learning (TwGL) aims to solve the above problems from a technical viewpoint. In contrast to conventional graph learning research which mainly cares about model performance, TwGL considers various reliability and safety aspects of the graph learning framework including but not limited to robustness, explainability, and privacy. In this survey, we provide a comprehensive review of recent leading approaches in the TwGL field from three dimensions, namely, reliability, explainability, and privacy protection. We give a general categorization for existing work and review typical work for each category. To give further insights for TwGL research, we provide a unified view to inspect previous works and build the connection between them. We also point out some important open problems remaining to be solved in the future developments of TwGL. Copyright © 2022, The Authors. All rights reserved.

关键词： Regulatory compliance

PointCA: Evaluating the Robustness of 3D Point Cloud Completion Models Against Adversarial Examples

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Hu, Shengshan Zhang, Junwei Liu, Wei Hou, Junhui Li, Minghui Zhang, Leo Yu Jin, Hai Sun, Lichao School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China Cluster and Grid Computing Lab China National Engineering Research Center for Big Data Technology and System Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China Services Computing Technology and System Lab China City University of Hong Kong Hong Kong Deakin University Australia Lehigh University United States

Point cloud completion, as the upstream procedure of 3D recognition and segmentation, has become an essential part of many tasks such as navigation and scene understanding. While various point cloud completion models have demonstrated their powerful capabilities, their robustness against adversarial attacks, which have been proven to be fatally malicious towards deep neural networks, remains unknown. In addition, existing attack approaches towards point cloud classifiers cannot be applied to the completion models due to different output forms and attack purposes. In order to evaluate the robustness of the completion models, we propose PointCA, the first adversarial attack against 3D point cloud completion models. PointCA can generate adversarial point clouds that maintain high similarity with the original ones, while being completed as another object with totally different semantic information. Specifically, we minimize the representation discrepancy between the adversarial example and the target point set to jointly explore the adversarial point clouds in the geometry space and the feature space. Furthermore, to launch a stealthier attack, we innovatively employ the neighbourhood density information to tailor the perturbation constraint, leading to geometry-aware and distribution-adaptive modification for each point. Extensive experiments against different premier point cloud completion networks show that PointCA can cause a performance degradation from 77.9% to 16.7%, with the structure chamfer distance kept below 0.01. We conclude that existing completion models are severely vulnerable to adversarial examples, and state-of-the-art defenses for point cloud classification will be partially invalid when applied to incomplete and uneven point cloud data. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep neural networks

Challenges and Approaches for Mitigating Byzantine Attacks in Federated Learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Shi, Junyu Wan, Wei Hu, Shengshan Lu, Jianrong Zhang, Leo Yu School of Cyber Science and Engineering Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security China School of Information Technology Deakin University Australia

Recently emerged federated learning (FL) is an attractive distributed learning framework in which numerous wireless end-user devices can train a global model with the data remained autochthonous. Compared with the traditional machine learning framework that collects user data for centralized storage, which brings huge communication burden and concerns about data privacy, this approach can not only save the network bandwidth but also protect the data privacy. Despite the promising prospect, Byzantine attack, an intractable threat in conventional distributed network, is discovered to be rather efficacious against FL as well. In this paper, we conduct a comprehensive investigation of the state-of-the-art strategies for defending against Byzantine attacks in FL. We first provide a taxonomy for the existing defense solutions according to the techniques they used, followed by an across-the-board comparison and discussion. Then we propose a new Byzantine attack method called weight attack to defeat those defense schemes, and conduct experiments to demonstrate its threat. The results show that existing defense solutions, although abundant, are still far from fully protecting FL. Finally, we indicate possible countermeasures for weight attack, and highlight several challenges and future research directions for mitigating Byzantine attacks in FL. © 2021, CC BY.

关键词： data privacy

Self-Supervised Teaching and Learning of Representations on Graphs 23

学校读者我要写书评

暂无评论

Self-Supervised Teaching and Learning of Representations on ...

2023 World Wide Web Conference, WWW 2023

作者： Wan, Liangtian Fu, Zhenqiang Sun, Lu Wang, Xianpeng Xu, Gang Yan, Xiaoran Xia, Feng Key Laboratory for Ubiquitous Network Service Software of Liaoning Province School of Software Dalian University of Technology Dalian China Department of Communication Engineering Institute of Information Science Technology Dalian Maritime University Dalian China State Key Laboratory of Marine Resource Utilization in South China Sea School of Information and Communication Engineering Hainan University Haikou China State Key Laboratory of Millimeter Waves School of Information Science and Engineering Southeast University Nanjing China Research Center of Big Data Intelligence Research Institute of Artificial Intelligence Zhejiang Lab Hangzhou China School of Computing Technologies Rmit University Melbourne Australia

ISBN: (纸本)9781450394161

Recent years have witnessed significant advances in graph contrastive learning (GCL), while most GCL models use graph neural networks as encoders based on supervised learning. In this work, we propose a novel graph learning model called GraphTL, which explores self-supervised teaching and learning of representations on graphs. One critical objective of GCL is to retain original graph information. For this purpose, we design an encoder based on the idea of unsupervised dimensionality reduction of locally linear embedding (LLE). Specifically, we map one iteration of the LLE to one layer of the network. To guide the encoder to better retain the original graph information, we propose an unbalanced contrastive model consisting of two views, which are the learning view and the teaching view, respectively. Furthermore, we consider the nodes that are identical in muti-views as positive node pairs, and design the node similarity scorer so that the model can select positive samples of a target node. Extensive experiments have been conducted over multiple datasets to evaluate the performance of GraphTL in comparison with baseline models. Results demonstrate that GraphTL can reduce distances between similar nodes while preserving network topological and feature information, yielding better performance in node classification. © 2023 ACM.

关键词： Classification (of information)

Electricity Consumption Forecasting with Outliers Handling Based On Clustering and Deep Learning with Application to the Algerian Market

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Hadjout, Dalil Sebaa, Abderrazak Torres, José F. Martínez-Álvarez, Francisco Data Science and Big Data Lab Pablo de Olavide University SevilleES-41013 Spain LIMED Laboratory Faculty of Exact Sciences University of Bejaia Bejaia06000 Algeria Laboratoire LITAN Ecole Supérieure en Sciences et Technologies de l’Informatique et du Numérique Amizour Bejaia 06000 Algeria

The reduction of electricity loss and the e ective management of electricity demand are vital operations for production and distribution electricity enterprises. To achieve these goals, accurate forecasts of aggregate and individual electricity consumers are necessary. A novel multistep forecasting method is developed to forecast medium-term electricity consumption of the Algerian economic sector. The proposed method goes through the following three steps : cleaning steps, clustering steps and forecasting step of each cluster. The aim of the rst step is to detect and then replace outliers. To complete the rst phase, Robust Exponential and Holt-Winters Smoothing algorithms are adapted. Then, to carry out accurate forecasting at a lowest level, K-Shape and K-Means clustering methods are utilized to extract similarities and identify customer consumption patterns as a second step. The third step entails developing a deep learning model based on Gated Recurrent Units to forecast the electricity consumption in each cluster. To validate the proposed method, wecompared our results to the most known methods in literature like Autoregressive Integrated Moving Average, Seasonal Grey Model, LSTM networks, Temporal Convolutional Networks and two ensemble models. The results of several experiments conducted with 2000 electricity consumers during 14 years from an Algeria province (Bejaia) demonstrate that the proposed method provides remarkable prediction performances. Thus, prediction performances of the K-Shape-based clustering method reaches much higher prediction accuracy. According to the MAPE metric, the results of the best predictions are equal to 2.04%. It is also notable that 87% of the clients have a considerably low prediction error. © 2022, The Authors. All rights reserved.

关键词： Forecasting

label-Semantic-Enhanced Online Hashing for Efficient Cross-modal Retrieval

学校读者我要写书评

暂无评论

Label-Semantic-Enhanced Online Hashing for Efficient Cross-m...

IEEE International Conference on Multimedia and Expo (ICME)

作者： Xueting Jiang Xin Liu Yiu-Ming Cheung Xing Xu Shukai Zheng Taihao Li College of Computer Science and Technology Huaqiao University Xiamen China Zhejiang Lab Hangzhou China Xiamen Key Lab. of Comput. Vis. Pattern Recognit. & Fujian Key Lab. of Big Data Intell. and Security Xiamen China Department of Computer Science Hong Kong Baptist University Hong Kong SAR China Dept. of Computer Sci. and Eng. University of Electronic Science and Technology of China Chengdu China

Existing online cross-modal hashing methods often treat the semantic label categories independently to correlate the semantically similar data instances, which intrinsically ignore the potential dependency between the label categories and thus fail to capture the discriminative information in the hash code learning process. To alleviate this concern, we explore the inter-dependency between the label categories through their co-occurrence correlation from the label set, and present an efficient label-Semantic-Enhanced Online Hashing (LSE-OH) method for various cross-modal retrieval task. To be specific, the proposed framework integrates the instance-wise similarity and label-category affinity to incrementally learn the discriminative hash codes for the current arriving data, while updating the hash functions at a streaming manner. Further, an iterative discrete optimization algorithm is derived to mine the inter-dependency between the label categories and discriminatively learn the hash codes without relaxation. Accordingly, the hash codes are adaptively learned online with the high discriminative capability and inter-dependency, while avoiding high computation complexity to process the streaming data. Experimental results show its outstanding performance in comparison with the-state-of-arts.

关键词：

Attention Mechanism Balances Semantic Representation and Syntactic Representation 2020

学校读者我要写书评

暂无评论

Attention Mechanism Balances Semantic Representation and Syn...

Proceedings of the 2020 9th International Conference on Computing and Pattern Recognition

作者： Ci Liu Xuetong Zhao Xiang Li Yawei Zhao Big Data Analysis Technology Lab University of Chinese Academy of Science Beijing China School of Management Capital Normal University Beijing China

ISBN: (纸本)9781450387835

Semantic information and syntactic information are two essential dimensions of language. In recent years, most researches focus on extracting semantic information or how to extract useful information from syntactic dependency tree. As the semantic representations are closely related to syntactic ones, how to effectively integrate semantic and syntactic information is still a subject worth studying. We propose attention mechanism based on graph convolutional networks. The model integrates syntactic dependence information into semantic features and automatically achieve a balance between semantic information and syntactic information. We conducted experiments on the task of sentence-level relation extraction, and the results show that our model performs better than some previous methods.

关键词： attention syntax feature Relation extraction GCN

Optimal margin distribution machine for multi-instance learning 29

学校读者我要写书评

暂无评论

Optimal margin distribution machine for multi-instance learn...

29th International Joint Conference on Artificial Intelligence, IJCAI 2020

作者： Zhang, Teng Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China

ISBN: (纸本)9780999241165

Multi-instance learning (MIL) is a celebrated learning framework where each example is represented as a bag of instances. An example is negative if it has no positive instances, and vice versa if at least one positive instance is contained. During the past decades, various MIL algorithms have been proposed, among which the large margin based methods is a very popular class. Recently, the studies on margin theory disclose that the margin distribution is of more importance to generalization ability than the minimal margin. Inspired by this observation, we propose the multi-instance optimal margin distribution machine, which can identify the key instances via explicitly optimizing the margin distribution. We also extend a stochastic accelerated mirror prox method to solve the formulated minimax problem. Extensive experiments show the superiority of the proposed method. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.

关键词： Optimization

Equivariant Graph Hierarchy-Based Neural Networks

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Han, Jiaqi Huang, Wenbing Xu, Tingyang Rong, Yu Department of Computer Science and Technology Tsinghua University China Gaoling School of Artificial Intelligence Renmin University of China China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China Tencent AI Lab China

Equivariant Graph neural Networks (EGNs) are powerful in characterizing the dynamics of multi-body physical systems. Existing EGNs conduct flat message passing, which, yet, is unable to capture the spatial/dynamical hierarchy for complex systems particularly, limiting substructure discovery and global information fusion. In this paper, we propose Equivariant Hierarchy-based Graph Networks (EGHNs) which consist of the three key components: generalized Equivariant Matrix Message Passing (EMMP), E-Pool and E-UnPool. In particular, EMMP is able to improve the expressivity of conventional equivariant message passing, E-Pool assigns the quantities of the low-level nodes into high-level clusters, while E-UnPool leverages the high-level information to update the dynamics of the low-level nodes. As their names imply, both E-Pool and E-UnPool are guaranteed to be E(n)-equivariant to meet the physical symmetry. Considerable experimental evaluations verify the effectiveness of our EGHN on several applications including multi-object dynamics simulation, motion capture, and protein dynamics modeling. © 2022, CC BY.

关键词： Message passing