Xiang Li

Xiang Li

Auto-generated profile, based on publicly available information

Xiang Li

School of Data Science and Engineering East China Normal University

Research Focus & Metrics

Academic Career Length

25Years (2002-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2024
Verified
Conference Paper
Open access
PDF file
JWJianing Wang
Jianing Wang
QSQiushi Sun
Qiushi Sun
XLXiang Li
Xiang Li
MGMing Gao
Ming Gao
Jianing Wang, Qiushi Sun, Xiang Li, Ming Gao. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

1 April 2024 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
JYJianxiang Yu
Jianxiang Yu
QGQingqing Ge
Qingqing Ge
XLXiang Li
Xiang Li
AZAoying Zhou
Aoying Zhou
Heterogeneous graph contrastive learning has received wide attention recently. Some existing methods use meta-paths, which are sequences of object types that capture semantic relationships between objects, to construct contrastive views. However, most of them ignore the rich meta-path context information that describes how two objects are connected by meta-paths. Further, they fail to distinguish negative samples, which could adversely affect the model performance. To address the problems, we propose MEOW, which considers both meta-path contexts and weighted negative samples. Specifically, MEOW constructs a coarse view and a fine-grained view for contrast. The former reflects which objects are connected by meta-paths, while the latter uses meta-path contexts and characterizes details on how the objects are connected. Then, we theoretically analyze the InfoNCE loss and recognize its limitations for computing gradients of negative samples. To better distinguish negative samples, we learn hard-valued weights for them based on node clustering and use prototypical contrastive learning to pull close embeddings of nodes in the same cluster. In addition, we propose a variant model AdaMEOW that adaptively learns soft-valued weights of negative samples to further improve node representation. Finally, we conduct extensive experiments to show the superiority of MEOW and AdaMEOW against other state-of-the-art methods.

1 January 2022
Verified
Conference Paper
Open access
PDF file
JWJianing Wang
Jianing Wang
WHWenkang Huang
Wenkang Huang
MQMinghui Qiu
Minghui Qiu
QSQiuhui Shi
Qiuhui Shi
HWHongbin Wang
Hongbin Wang
MGMing Gao
Ming Gao
Jianing Wang, Wenkang Huang, Minghui Qiu, Qiuhui Shi, Hongbin Wang, Xiang Li, Ming Gao. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. 2022.

30 April 2023
Verified
Conference Paper
Open access
XLXiang Li
Xiang Li
TYTiandi Ye
Tiandi Ye
CSCaihua Shan
Caihua Shan
DLDongsheng Li
Dongsheng Li
MGMing Gao
Ming Gao
Generative graph self-supervised learning (SSL) aims to learn node representations by reconstructing the input graph data. However, most existing methods focus on unsupervised learning tasks only and very few work has shown its superiority over the state-of-the-art graph contrastive learning (GCL) models, especially on the classification task. While a very recent model has been proposed to bridge the gap, its performance on unsupervised learning tasks is still unknown. In this paper, to comprehensively enhance the performance of generative graph SSL against other GCL models on both unsupervised and supervised learning tasks, we propose the SeeGera model, which is based on the family of self-supervised variational graph auto-encoder (VGAE). Specifically, SeeGera adopts the semi-implicit variational inference framework, a hierarchical variational framework, and mainly focuses on feature reconstruction and structure/feature masking. On the one hand, SeeGera co-embeds both nodes and features in the encoder and reconstructs both links and features in the decoder. Since feature embeddings contain rich semantic information on features, they can be combined with node embeddings to provide fine-grained knowledge for feature reconstruction. On the other hand, SeeGera adds an additional layer for structure/feature masking to the hierarchical variational framework, which boosts the model generalizability. We conduct extensive experiments comparing SeeGera with 9 other state-of-the-art competitors. Our results show that SeeGera can compare favorably against other state-of-the-art GCL methods in a variety of unsupervised and supervised learning tasks.

19 June 2024 in ACM Transactions on Knowledge Discovery From Data
Verified
Journal Article
Open access
TYTiandi Ye
Tiandi Ye
CCCen Chen
Cen Chen
YWYinggui Wang
Yinggui Wang
XLXiang Li
Xiang Li
MGMing Gao
Ming Gao
In federated learning (FL), malicious clients could manipulate the predictions of the trained model through backdoor attacks, posing a significant threat to the security of FL systems. Existing research primarily focuses on backdoor attacks and defenses within the generic federated learning scenario, where all clients collaborate to train a single global model. A recent study conducted by Qin et al. [ 24 ] marks the initial exploration of backdoor attacks within the personalized federated learning (pFL) scenario, where each client constructs a personalized model based on its local data. Notably, the study demonstrates that pFL methods with parameter decoupling can significantly enhance robustness against backdoor attacks. However, in this article, we whistleblow that pFL methods with parameter decoupling are still vulnerable to backdoor attacks. The resistance of pFL methods with parameter decoupling is attributed to the heterogeneous classifiers between malicious clients and benign counterparts. We analyze two direct causes of the heterogeneous classifiers: (1) data heterogeneity inherently exists among clients and (2) poisoning by malicious clients further exacerbates the data heterogeneity. To address these issues, we propose a two-pronged attack method, BapFL, which comprises two simple yet effective strategies: (1) poisoning only the feature encoder while keeping the classifier fixed and (2) diversifying the classifier through noise introduction to simulate that of the benign clients. Extensive experiments on three benchmark datasets under varying conditions demonstrate the effectiveness of our proposed attack. Additionally, we evaluate the effectiveness of six widely used defense methods and find that BapFL still poses a significant threat even in the presence of the best defense, Multi-Krum. We hope to inspire further research on attack and defense strategies in pFL scenarios. The code is available at: https://github.com/BapFL/code

20 August 2023
Verified
Conference Paper
Open access
RPRohit Paturi
Rohit Paturi
SSSundararajan Srinivasan
Sundararajan Srinivasan
XLXiang Li
Xiang Li