HYHao Yu

Hao Yu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Hao Yu has a total of 46 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Explainability-Guided Untargeted Attacks on Knowledge Graph Embedding

    by Yawei Lin, Hao Yu, Ke Liang, Mengzhu Wang, Liang Yang, Xinwang Liu

    Knowledge graph embedding (KGE) aims to learn high-dimensional representations of graph structures for various downstream tasks. However, knowledge graphs (KGs) are vulnerable to adversarial attacks. The adversary can delete key triplets or inject malicious triplets, thereby compromising the quality of learned representations. Existing target-oriented attack methods rely on the predefined target set, but the adversary can hardly obtain this information in realistic scenarios. In contrast, existing rule-oriented attacks only consider short logic rules, and their reliance on random walk sampling often yields many low-quality rules, degrading attack effectiveness. Surprisingly, we find that reasoning paths can represent multi-hop relations among entities in KGs and provide intuitive explainability. Therefore, we introduce PathAttack, the first path-based explainable untargeted attack framework for KGs. Concretely, a triplet discovery approach is proposed by combining selection using different types of KGE models to replace the predefined target set, which overcomes the limitation of unrealistic assumptions. In addition, we extract and weight the multi-hop relational paths between entities for adversarial deletion and addition, overcoming the bottlenecks of rule length and quality. Extensive experiments on FB15k-237, WN18RR, and the massive OGBL-WikiKG2 benchmark demonstrate the superior effectiveness of our method. Notably, PathAttack is scalable to large-scale KGs containing millions of entities, and improves adversarial attack effectiveness by 5% on WN18RR.


  • A Wolf in Sheep’s Clothing: Unveiling a Stealthy Backdoor Attack in Subgraph Federated Learning

    by Hao Yu, Wenjing Yang, Chuan Ma, Lingyuan Meng, Liang Du, Tao Xiang, Xinwang Liu, Kunlun He

    Subgraph Federated Learning (FL) has emerged as a promising paradigm for node classification tasks wherein subgraphs derived from a global graph are distributed across multiple devices to mitigate data leakage risks. Similar to other FL systems, subgraph FL faces significant security challenges, particularly from backdoor attacks, an area that remains extensively underexplored. Existing attacks typically follow a two-phase strategy to implant backdoors. However, in subgraph FL, such attacks often lead to Divergence Amplification, a phenomenon characterized by significant parameter discrepancies between normal and backdoored models, thereby compromising attack stealthiness. To tackle this challenge, we propose BEEF, a Backdoor attack with an End-to-End Framework designed for effectiveness, stealth, and durability. Unlike conventional methods, BEEF incorporates a dedicated trigger generator, which is jointly trained with a backdoored model. To increase its stealthiness, BEEF crafts adversarial perturbations as triggers that provoke misclassification while leaving the model’s parameters entirely untouched. Furthermore, by calibrating a subset of low-salience parameters associated with backdoor activation, BEEF ensures stable performance and sustained effectiveness across FL rounds. Comprehensive evaluations across eight datasets, four models, five state-of-the-art attacks, and six aggregation methods demonstrate BEEF’s effectiveness in deceiving GNNs while maintaining minimal impact on normal data performance. Additionally, we adapt BEEF to federated graph classification tasks, broadening its applicability and practicality.


  • Tensor Multi-Rank Constraint Guided Anchor-Wise Adaptive Alignment for Multi-View Clustering

    by Jun Wang, Miaomiao Li, Zhenglai Li, Hao Yu, Suyuan Liu, Dayu Hu, Chang Tang, Xinwang Liu

    Anchor graph learning has become a widely used technique for significantly reducing the computational complexity in existing multi-view clustering methods. However, most existing approaches select anchors independently for each view and then generate the consensus graph by directly fusing all anchor graphs. This process overlooks the correspondence between anchor sets across different views, i.e., the column order correspondence of the anchor graphs. To address this limitation, we propose a novel anchor-based tensor multi-rank constraint multi-view clustering method (TMC). Specifically, TMC captures the high-order structural information of the original data by constructing an anchor graph tensor and enforcing a multi-rank constraint to induce a block-diagonal structure. Additionally, to enhance anchor consistency across all view, we construct the anchor graph of each view into an anchor tensor and impose a low-rank constraint on it. In this way, the block-diagonal structure of each anchor graph maintains an approximate alignment between anchors. Furthermore, we provide theoretical proof that the generated anchor graphs inherently exhibit a block-diagonal structure. Extensive experimental results on six multi-view datasets demonstrate that TMC outperforms existing state-of-the-art methods, highlighting its effectiveness in multi-view clustering task.


  • G 2 uardFL: Safeguarding Federated Learning Against Backdoor Attacks via Attributed Client Graph Clustering

    by Hao Yu, Chuan Ma, Meng Liu, Tianyu Du, Ming Ding, Tao Xiang, Shouling Ji, Xinwang Liu

    Federated Learning (FL) offers collaborative model training across multiple decentralized devices without the need to share data directly, enhancing privacy and data security. However, FL systems are susceptible to backdoor attacks, where malicious clients inject poisoned weights during training. Existing defenses, primarily based on anomaly detection, are prone to erroneous rejections of normal weights while accepting poisoned ones, largely due to shortcomings in quantifying similarities among client models. Furthermore, other defenses demonstrate effectiveness only when dealing with a limited number of malicious clients, typically fewer than 10%. To alleviate these vulnerabilities, we present G2uardFL, a protective framework that translates the detection of malicious clients into an attributed graph clustering problem, thus safeguarding FL systems. Specifically, this framework employs a client graph clustering approach to identify malicious clients and integrates an adaptive mechanism to amplify the discrepancy between the aggregated model and the poisoned ones, effectively eliminating embedded backdoors. Through empirical evaluation, comparing G2uardFL with cutting-edge defenses, such as FLAME (USENIX Security 2022) [37] and DeepSight (NDSS 2022) [43], against various backdoor attacks, including 3DFed (SP 2023) [26], our results demonstrate its significant effectiveness in mitigating backdoor attacks while having a negligible impact on the aggregated model’s performance on benign samples (i.e., the primary task performance). For instance, in an FL system with 25% malicious clients, G2uardFL reduces the attack success rate to 10.61%, while maintaining a primary task performance of 80.98% on the CIFAR-10 dataset. This surpasses the performance of the best-performing baseline, which merely achieves the attack success rate of 19.54%.


  • Multiview Temporal Graph Clustering

    by Meng Liu, Ke Liang, Hao Yu, Lingyuan Meng, Siwei Wang, Sihang Zhou, Xinwang Liu

    As an emerging task, temporal graph clustering (TGC) is committed to clustering nodes on temporal graphs through interaction sequence-based batch-processing patterns. These patterns allow for more flexibility in finding a balance between time and space requirements than adjacency matrix-based static graph clustering. However, as a new task, TGC still has important unresolved challenges, such as insufficient information. This challenge manifests itself in a variety of problems in real-world datasets, including missing features (eigenvalues are missing or even nonexistent), long-tail nodes (most inactive nodes have little interaction), and noisy data (data is subject to anomalies, errors, and sparsity). These problems occur before training, making it difficult for the model to train well with insufficient information. To solve the challenge, we propose a method that introduces multiview clustering (MVC) into TGC, called MVTGC. Our method aims to perform data augmentation on the temporal graph by constructing multiple views to increase the information richness. In particular, we utilize different techniques to model a certain part of the temporal graph to generate enhanced views focusing on different angles. These views are combined into training through early fusion and late fusion and ultimately enhance the model’s receptive field and information richness. Comparative experiments and a case study on real-world datasets demonstrate the significance and effectiveness of MVTGC, which achieves at most 10.48% performance improvement. The code and data are available at https://github.com/MGitHubL/MVTGC


  • Contrastive Continual Multiview Clustering With Filtered Structural Fusion

    by Xinhang Wan, Jiyuan Liu, Hao Yu, Qian Qu, Ao Li, Xinwang Liu, Ke Liang, Zhibin Dong, En Zhu

    Multiview clustering thrives in applications where views are collected in advance by extracting consistent and complementary information among views. However, it overlooks scenarios where data views are collected sequentially, i.e., real-time data. Due to privacy issues or memory burden, previous views are not available with time in these situations. Some methods are proposed to handle it but are trapped in a stability-plasticity dilemma. In specific, these methods undergo a catastrophic forgetting of prior knowledge when a new view is attained. Such a catastrophic forgetting problem (CFP) would cause the consistent and complementary information hard to get and affect the clustering performance. To tackle this, we propose a novel method termed contrastive continual multiview clustering with filtered structural fusion (CCMVC-FSF). Precisely, considering that data correlations play a vital role in clustering and prior knowledge ought to guide the clustering process of a new view, we develop a data buffer to store filtered structural information and utilize it to guide the generation of a robust partition matrix via contrastive learning. Additionally, to address the high complexity involved in acquiring and storing structural information, we propose a sampling strategy called clustering then sample. Furthermore, we theoretically connect CCMVC-FSF with semisupervised learning and knowledge distillation. Extensive experiments exhibit the excellence of the proposed method. Our code is publicly available at https://github.com/wanxinhang/CCMVC-FSF/.


  • GZOO: Black-Box Node Injection Attack on Graph Neural Networks via Zeroth-Order Optimization

    by Hao Yu, Ke Liang, Dayu Hu, Wenxuan Tu, Chuan Ma, Sihang Zhou, Xinwang Liu

    The ubiquity of Graph Neural Networks (GNNs) emphasizes the imperative to assess their resilience against node injection attacks, a type of evasion attacks that impact victim models by injecting nodes with fabricated attributes and structures. However, prevailing attacks face two primary limitations: (1) Sequential construction of attributes and structures results in suboptimal outcomes as structure information is overlooked during attribute construction and vice versa. (2) In black-box scenarios, where attackers lack access to victim model architecture and parameters, reliance on surrogate models degrades performance due to architectural discrepancies. To overcome these limitations, we introduce GZOO, a black-box node injection attack that leverages an adversarial graph generator, compromising both attribute and structure sub-generators. This integration crafts optimal attributes and structures by considering their mutual information, enhancing their influence when aggregating information from injected nodes. Furthermore, GZOO proposes a zeroth-order optimization algorithm leveraging prediction results from victim models to estimate gradients for updating generator parameters, eliminating the necessity to train surrogate models. Across sixteen datasets, GZOO significantly outperforms state-of-the-art attacks, achieving remarkable effectiveness and robustness. Notably, on the Cora dataset with the GCN model, GZOO achieves an impressive 95.69% success rate, surpassing the maximum 66.01% achieved by baselines.


  • FedEAN: Entity-Aware Adversarial Negative Sampling for Federated Knowledge Graph Reasoning

    by Lingyuan Meng, Ke Liang, Hao Yu, Yue Liu, Sihang Zhou, Meng Liu, Xinwang Liu

    Federated knowledge graph reasoning (FedKGR) aims to perform reasoning over different clients while protecting data privacy, drawing increasing attention to its high practical value. Previous works primarily focus on data heterogeneity, ignoring challenges from limited data scale and primitive negative sample strategies, i.e., random entity replacement, which yield low-quality negatives and zero loss issues. Meanwhile, generative adversarial networks (GANs) are widely used in different fields to generate high-quality negative samples, but no work has been developed for FedKGR. To this end, we propose a plug-andplay Entity-aware Adversarial Negative sampling strategy for FedKGR, termed FedEAN. Specifically, we are the first to adopt GANs to generate high-quality negative samples in different clients. It takes the target triplet in each batch as input and outputs high-quality negative samples, which guaranteed by the joint training of the generator and discriminator. Moreover, we design an entity-aware adaptive negative sampling mechanism based on the similarity of entity representations before and after server aggregation, which can persevere the entity global consistency across clients during training. Extensive experiments demonstrate that FedEAN excels with various FedKGR backbones, demonstrating its ability to construct high-quality negative samples and address the zero-loss issue.


  • Spatial–Spectral Graph Contrastive Clustering With Hard Sample Mining for Hyperspectral Images

    by Renxiang Guan, Wenxuan Tu, Zihao Li, Hao Yu, Dayu Hu, Yuzeng Chen, Chang Tang, Qiangqiang Yuan, Xinwang Liu

    Hyperspectral image (HSI) clustering is a fundamental yet challenging task that groups image pixels with similar features into distinct clusters. Among various approaches, contrastive learning methods, which employ the concept of encouraging semantically similar samples to move closer together while pushing semantically inconsistent samples apart, have garnered significant attention due to their promising performance. However, the most prevalent approaches face two major limitations: 1) treating all samples indiscriminately during optimization, where the abundance of well-categorized samples overwhelms the feature learning process; 2) tending to introduce noise when constructing positive sample pairs through view augmentation or searching the nearest neighbors, which would cause semantic drift of sample features. To solve these issues, we propose a graph autoencoder-based deep clustering framework named SSGCC that constructs spatial-spectral dual views without data augmentation and focuses more on hard samples rather than treating all samples equally with the aid of spatial-spectral features. Concretely, we extract the spectral features and the neighborhood spatial features of the samples as dual branches to avoid the noise caused by data augmentation, and develop the cluster-oriented consistency learning to facilitate the exchange of knowledge between the two spectral-spatial perspectives. Additionally, we propose a hard sample mining-based contrastive learning scheme with the aid of spatial-spectral features. To better measure the importance of the samples, we combine spatial features and spectral features to calculate the similarity between sample pairs. The weights of hard sample pairs are dynamically up-weight while the easy ones are down-weighting to improve the discriminative capability. Extensive experiments on four benchmark HSI datasets demonstrate the effectiveness and superiority of the proposed methods against state-of-the-art ones.


  • High-order Topology for Deep Single-Cell Multiview Fuzzy Clustering

    by Dayu Hu, Zhibin Dong, Ke Liang, Hao Yu, Siwei Wang, Xinwang Liu

    Single-cell multi-view clustering is essential for analyzing the different cell subtypes of the same cell from different views. Some attempts have been made, but most of these models still struggle to handle single-cell sequencing data, primarily due to their non-specific design for cellular data. We observe that such data distinctively exhibits: (1) a profusion of high-order topological correlations, (2) a disparate distribution of information across different views, and (3) inherent fuzzy characteristics, indicating a cell's potential to associate with multiple cluster identities. Neglecting these key cellular patterns could significantly impair medical clustering. In response, we propose a specialized application of fuzzy clustering for single-cell sequencing data, namely the deep Single-cell Multi-view Fuzzy Clustering (scMFC) method. Concretely, we employ a random walk technique to capture high-order topological relationships on the cell graph and have developed a cross-view information aggregation mechanism that adaptively assigns weights to different views. Furthermore, to accurately reflect the dynamic insight in cellular development, we propose a deep fuzzy clustering strategy that allows cells to associate with diverse clusters. Extensive experiments conducted on three real-world single-cell multi-view datasets demonstrate our method's superior performance.