📝 Publications

• Can Large Language Models Act as Ensembler for Multi-GNNs?,
  Hanqi Duan, Yao Cheng, Jianxiang Yu, Yao Liu*, Xiang Li*.
  In EMNLP, 2025, Suzhou, China.
  
• Text Detoxification: Data Efficiency, Semantic Preservation and Model Generalization,
  Jing Yu, Yibo Zhao, Jiapeng Zhu, Wenming Shao, Bo Pang, Zhao Zhang, Xiang Li*.
  In EMNLP, 2025, Suzhou, China.
  
• Permitted Knowledge Boundary: Evaluating the Knowledge-Constrained Responsiveness of Large Language Models,
  Wenrui Bao, Kai Wang, Siqiang Luo, Xiang Li.
  In EMNLP Findings, 2025, Suzhou, China.
  
• Boosting Cross-Domain and Cross-Task Generalization for Text-Attributed Graphs from Structural Perspective,
  Yao Cheng, Jiapeng Zhu, Yige Zhao, Jianxiang Yu, Jiaqi Tan, Xiang Li*.
  In Frontiers of Computer Science, 2025.
  
• Towards Instance-wise Personalized Federated Learning via Semi-Implicit Bayesian Prompt Tuning,
  Tiandi Ye, Wenyan Liu, Kai Yao, Lichun Li, Shangchao Su, Cen Chen, Xiang Li, Shan Yin, Ming Gao.
  In CIKM 2025, Seoul, Korea.
  
• Enhancing LLM-based Hatred and Toxicity Detection with Meta-Toxic Knowledge Graph,
  Yibo Zhao, Jiapeng Zhu, Can Xu, Yao Liu*, Xiang Li*.
  In ACL Findings, 2025, Vienna, Austria.
  
• Initializing and Retrofitting Key-Value Adaptors for Traceable Model Editing,
  Hanlun Zhu, Yunshi Lan, Xiang Li, Weining Qian.
  In ACL Findings, 2025, Vienna, Austria.
  
• Let's Be Self-generated via Step by Step: A Curriculum Learning Approach to Automated Reasoning with Large Language Models,
  Kangyang Luo, Zichen Ding, Zhenmin Weng, Lingfeng Qiao, Meng Zhao, Xiang Li*, Di Yin, Jinlong Shu.
  In ACL Findings, 2025, Vienna, Austria.
  
• A Survey on Learning from Graphs with Heterophily: Recent Advances and Future Directions,
  Chenghua Gong, Yao Cheng, Jianxiang Yu, Can Xu, Caihua Shan, Siqiang Luo, Xiang Li*.
  In Frontiers of Computer Science, 2025.
  
• PA-RAG: RAG Alignment via Multi-Perspective Preference Optimization,
  Jiayi Wu, Hengyi Cai, Lingyong Yan, Hao Sun, Xiang Li*, Shuaiqiang Wang, Dawei Yin, Ming Gao.
  In NAACL 2025, Albuquerque, New Mexico, USA.
  
• Hierarchical Vector Quantized Graph Autoencoder with Annealing-Based Code Selection,
  Long Zeng, Jianxiang Yu, Jiapeng Zhu, Qingsong Zhong, Xiang Li*.
  In WWW 2025, Sydney, Australia.
  
• Leveraging Large Language Models for Node Generation in Few-Shot Learning on Text-Attributed Graphs,
  Jianxiang Yu, Yuxiang Ren*, Chenghua Gong, Jiaqi Tan, Xiang Li*, Xuecang Zhang.
  In AAAI 2025, Philadelphia, USA.
  
• RELIEF: Reinforcement Learning Empowered Graph Feature Prompt Tuning,
  Jiapeng Zhu, Zichen Ding, Jianxiang Yu, Jiaqi Tan, Xiang Li*.
  In KDD 2025, Toronto, Canada.
  
• Variational Graph Autoencoder for Heterogeneous Information Networks with Missing and Inaccurate Attributes,
  Yige Zhao, Jianxiang Yu, Yao Cheng, Chengcheng Yu, Yiding Liu, Xiang Li*, Shuaiqiang Wang.
  In KDD 2025, Toronto, Canada.
  
• Cross-model Control: Improving Multiple Large Language Models in One-time Training,
  Jiayi Wu, Hao Sun, Hengyi Cai, Lixin Su, Shuaiqiang Wang, Dawei Yin, Xiang Li*, Ming Gao.
  In NeurIPS 2024, Vancouver, Canada.
  
• Automated Peer Reviewing in Paper SEA: Standardization, Evaluation, and Analysis,
  Jianxiang Yu, Zichen Ding, Jiaqi Tan, Kangyang Luo, Zhenmin Weng, Chenghua Gong, Long Zeng, RenJing Cui, Chengcheng Han, Qiushi Sun, Zhiyong Wu, Yunshi Lan, Xiang Li*.
  In EMNLP Findings 2024, Miami, USA.
  
• DFDG: Data-Free Dual-Generator Adversarial Distillation for One-Shot Federated Learning,
  Kangyang Luo, Shuai Wang, Yexuan Fu, Renrong Shao, Xiang Li*, Yunshi Lan, Ming Gao, Jinlong Shu.
  In ICDM 2024, Dubai, UAE. (Regular paper, Top 66/604)
  
• GraphCBAL: Class-Balanced Active Learning for Graph Neural Networks via Reinforcement Learning,
  Chengcheng Yu, Jiapeng Zhu, Xiang Li*.
  In CIKM 2024, Boise, Idaho, USA.
  
• Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaboration,
  Qiushi Sun, Zhangyue Yin, Xiang Li, Zhiyong Wu, Xipeng Qiu, Lingpeng Kong.
  In COLM 2024, Philadelphia, USA.
  
• Self-Pro: Self-Prompt and Tuning Framework for Graph Neural Networks,
  Chenghua Gong, Xiang Li*, Jianxiang Yu, Yao Cheng, Jiaqi Tan, Chengcheng Yu.
  In ECML-PKDD 2024, Vilnius, Lithuania.
  
• PSP: Pre-Training and Structure Prompt Tuning for Graph Neural Networks,
  Qingqing Ge, Zeyuan Zhao, Yiding Liu, Anfeng Cheng, Xiang Li*, Shuaiqiang Wang, Dawei Yin.
  In ECML-PKDD 2024, Vilnius, Lithuania.
  
• HetCAN: A Heterogeneous Graph Cascade Attention Network with Dual-Level Awareness,
  Zeyuan Zhao, Qingqing Ge, Anfeng Cheng, Yiding Liu, Xiang Li*, Shuaiqiang Wang.
  In ECML-PKDD 2024, Vilnius, Lithuania.
  
• Resurrecting Label Propagation for Graphs with Heterophily and Label Noise,
  Yao Cheng, Caihua Shan, Yifei Shen, Xiang Li*, Siqiang Luo, Dongsheng Li.
  In KDD 2024, Barcelona, Spain.
  
• Boosting Language Models Reasoning with Chain-of-Knowledge Prompting,
  Jianing Wang, Qiushi Sun, Xiang Li*, Ming Gao.
  In ACL 2024, Bangkok, Thailand.
  
• Learning Prioritized Node-wise Message Propagation in Graph Neural Networks,
  Yao Cheng, Xiang Li*, Minjie Chen, Caihua Shan.
  In TKDE 2024.
  
• Heterogeneous Graph Contrastive Learning with Meta-path Contexts and Adaptively Weighted Negative Samples,
  Jianxiang Yu, Qingqing Ge, Xiang Li*, Aoying Zhou.
  In TKDE 2024.
  
• Conjoin After Decompose: Improving Few-Shot Performance of Named Entity Recognition,
  Chengcheng Han, Renyu Zhu, Jun Kuang, Fengjiao Chen, Xiang Li*, Ming Gao, Xuezhi Cao, Yunsen Xian.
  In LREC-COLING 2024, Torino, Italia.
  
• Structure-aware Fine-tuning for Code Pre-trained Models,
  Jiayi Wu, Renyu Zhu, Nuo Chen, Qiushi Sun, Xiang Li, Ming Gao.
  In LREC-COLING 2024, Torino, Italia.
  
• Make Prompt-based Black-Box Tuning Colorful: Boosting Model Generalization from Three Orthogonal Perspectives,
  Qiushi Sun, Chengcheng Han, Nuo Chen, Renyu Zhu, Jingyang Gong, Xiang Li*, Ming Gao.
  In LREC-COLING 2024, Torino, Italia.
  
• TransCoder: Towards Unified Transferable Code Representation Learning Inspired by Human Skills,
  Qiushi Sun, Nuo Chen, Jianing Wang, Xiang Li*, Ming Gao.
  In LREC-COLING 2024, Torino, Italia.
  
• BapFL: You can Backdoor Personalized Federated Learning,
  Tiandi Ye, Cen Chen, Yinggui Wang, Xiang Li, Ming Gao.
  In TKDD 2024.
  
• Training-free Multi-objective Diffusion Model for 3D Molecule Generation,
  Xu Han, Caihua Shan, Yifei Shen, Can Xu, Han Yang, Xiang Li, Dongsheng Li.
  In ICLR 2024, Vienna, Austria.
  
• UPFL: Unsupervised Personalized Federated Learning towards New Clients,
  Tiandi Ye, Cen Chen, Yinggui Wang, Xiang Li, Ming Gao.
  In SDM 2024, Houston, USA
  
• Federated Learning via Consensus Mechanism on Heterogeneous Data: A New Perspective on Convergence,
  Shu Zheng, Tiandi Ye, Xiang Li*, Ming Gao.
  In ICASSP 2024, Seoul, Korea.
  
• Scalable Decoupling Graph Neural Network with Feature-Oriented Optimization,
  Ningyi Liao, Dingheng Mo, Siqiang Luo, Xiang Li, Pengcheng Yin.
  In VLDBJ 2023.
  
• DialCoT Meets PPO: Decomposing and Exploring Reasoning Paths in Smaller Language Models,
  Chengcheng Han, Xiaowei Du, Che Zhang, Yixin Lian, Xiang Li, Ming Gao, Baoyuan Wang.
  In EMNLP 2023, Singapore.
  
• Pass-Tuning: Towards Structure-Aware Parameter-Efficient Tuning for Code Representation Learning,
  Nuo Chen, Qiushi Sun, Jianing Wang, Xiang Li, Ming Gao.
  In EMNLP Findings 2023, Singapore.
  
• Uncertainty-aware Parameter-Efficient Self-training for Semi-supervised Language Understanding,
  Jianing Wang, Qiushi Sun, Nuo Chen, Chengyu Wang, Xiang Li, Ming Gao, Jun Huang.
  In EMNLP Findings 2023, Singapore.
  
• Evaluating and Enhancing the Robustness of Code Pre-trained Models through Structure-Aware Adversarial Samples Generation,
  Nuo Chen, Qiushi Sun, Jianing Wang, Xiaoli Li, Xiang Li, Ming Gao.
  In EMNLP Findings 2023, Singapore.
  
• DFRD: Data-Free Robustness Distillation for Heterogeneous Federated Learning,
  Kangyang Luo, Shuai Wang, Yexuan Fu, Xiang Li*, Yunshi Lan and Ming Gao.
  In NeurIPS 2023, New Orleans, USA.
  
• LD2: Scalable Heterophilous Graph Neural Network with Decoupled Embedding,
  Ningyi Liao, Siqiang Luo, Xiang Li, and Jieming Shi.
  In NeurIPS 2023, New Orleans, USA.
  
• Graph Self-Contrast Representation Learning,
  Minjie Chen, Yao Cheng, Ye Wang, Xiang Li*, and Ming Gao.
  In ICDM 2023, Shanghai, China. (Regular paper, Top 9.37%)
  
• DropMix: Better Graph Contrastive Learning with Harder Negative Samples,
  Yueqi Ma, Minjie Chen and Xiang Li*.
  In ICDM Workshop 2023, Shanghai, China.
  
• MUSE: Multi-view contrastive learning for heterophilic graphs via information reconstruction,
  Mengyi Yuan, Minjie Chen and Xiang Li*.
  In CIKM 2023, Birmingham, UK
  
• Decentralized Local Updates with Dual-Slow Estimation and Momentum-based Variance-Reduction for Non-Convex Optimization,
  Kangyang Luo, Kunkun Zhang, Shengbo Zhang, Xiang Li* and Ming Gao.
  In ECAI 2023, Kraków, Poland
  
• When Gradient Descent Meets Derivative-Free Optimization: A Match Made in Black-Box Scenario,
  Chengcheng Han, Liqing Cui, Renyu Zhu, Jianing Wang, Nuo Chen, Qiushi Sun, Xiang Li and Ming Gao.
  In ACL Findings 2023, Toronto, Canada.
  
• GradMA: A Gradient-Memory-based Accelerated Federated Learning with Alleviated Catastrophic Forgetting,
  Kangyang Luo, Xiang Li*, Yunshi Lan and Ming Gao.
  In CVPR 2023, Vancouver, Canada. (Highlight, Top 2.5%)
  
• SeeGera: Self-supervised Semi-implicit Graph Variational Auto-encoders with Masking,
  Xiang Li, Tiandi Ye, Caihua Shan, Dongsheng Li and Ming Gao.
  In WebConf 2023, Austin, Texas, USA.
  
• Explaining Temporal Graph Models through an Explorer-Navigator Framework,
  Wenwen Xia, Mincai Lai, Caihua Shan, Yao Zhang, Xinnan Dai, Xiang Li, Dongsheng Li.
  In ICLR 2023, Kigali Rwanda.
  
• Meta-Learning Siamese Network for Few-Shot Text Classification,
  Chengcheng Han, Yuhe Wang, Yingnan Fu, Xiang Li*, Minghui Qiu, Ming Gao and Aoying Zhou.
  In DASFAA 2023, Tianjin, China.
  
• Heterogeneous Graph Contrastive Learning with Meta-path Contexts and Weighted Negative Samples,
  Jianxiang Yu and Xiang Li*.
  In SDM 2023, Minneapolis, Minnesota, USA.
  
• Knowledge Prompting in Pre-trained Language Model for Natural Language Understanding,
  Jianing Wang, Wenkang Huang, Minghui Qiu, Qiuhui Shi, Hongbin Wang, Xiang Li* and Ming Gao.
  In EMNLP 2022, Abu Dhabi, UAE.
  
• CAT-probing: A Metric-based Approach to Interpret How Pre-trained Models for Programming Language Attend Code Structure,
  Nuo Chen, Qiushi Sun, Renyu Zhu, Xiang Li*, Xuesong Lu and Ming Gao.
  In Findings of EMNLP 2022, Abu Dhabi, UAE.
  
• Finding Global Homophily in Graph Neural Networks When Meeting Heterophily,
  Xiang Li, Renyu Zhu, Yao Cheng, Caihua Shan, Siqiang Luo, Dongsheng Li, Weining Qian.
  In ICML 2022, Baltimore, USA. (Spotlight) [Slices]
  
• SCARA: Scalable Graph Neural Networks with Feature-Oriented Optimization,
  Ningyi Liao, Dingheng Mo, Siqiang Luo, Xiang Li, Pengcheng Yin.
  In PVLDB 2022, Sydney, Australia.
  
• Lexical Knowledge Internalization for Neural Dialog Generation,
  Zhiyong Wu, Wei Bi, Xiang Li, Lingpeng Kong, Ben Kao.
  In ACL 2022, Virtual Conference.
  
• A Neural Network Architecture for Program Understanding Inspired by Human Behaviors,
  Renyu Zhu, Lei Yuan, Xiang Li*, Ming Gao, Wenyuan Cai.
  In ACL 2022, Virtual Conference.
  
• Reinforcement Learning Enhanced Explainer for Graph Neural Networks,
  Caihua Shan, Yifei Shen, Yao Zhang, Xiang Li, Dongsheng Li.
  In NeurIPS 2021, Virtual Conference.
  
• Good for Misconceived Reasons: An Empirical Revisiting on the Need for Visual Context in Multimodal Machine Translation,
  Zhiyong Wu, Lingpeng Kong, Wei Bi, Xiang Li, Ben Kao.
  In ACL 2021, Virtual Conference.
  
• Leveraging meta-path contexts for classification in heterogeneous information networks,
  Xiang Li, Danhao Ding, Ben Kao, Yizhou Sun, Nikos Mamoulis.
  In ICDE 2021, Virtual Conference. [Project Codes]
  
• Disentangling user interest and popularity bias for recommendation with causal embedding,
  Yu Zheng, Chen Gao, Xiang Li, Xiangnan He, Yong Li, Depeng Jin.
  In WWW 2021, Virtual Conference.
  
• SceneRec: Scene-Based Graph Neural Networks for Recommender Systems,
  Gang Wang, Ziyi Guo, Xiang Li, Dawei Yin, Shuai Ma.
  In EDBT 2021, Virtual Conference.
  
• CAST: A Correlation-based Adaptive Spectral Clustering Algorithm on Multi-scale Data,
  Xiang Li, Ben Kao, Caihua Shan, Dawei Yin, Martin Ester.
  In KDD 2020, Virtual Conference. [Project Codes]
  
• SCHAIN-IRAM: An Efficient and Effective Semi-supervised Clustering Algorithm for Attributed Heterogeneous Information Networks,
  Xiang Li, Yao Wu, Martin Ester, Ben Kao, Xin Wang, and Yudian Zheng.
  In TKDE 2020.
  
• An End-to-End Deep RL Framework for Task Arrangement in Crowdsourcing Platforms,
  Caihua Shan, Nikos Mamoulis, Reynold Cheng, Guoliang Li, Xiang Li and Yuqiu Qian.
  In ICDE 2020, Virtual Conference.
  
• A General Early-Stopping Module for Crowdsourced Ranking,
  Caihua Shan, Leong Hou U, Nikos Mamoulis, Reynold Cheng and Xiang Li.
  In DASFAA 2020, Virtual Conference.
  
• Spectral clustering in heterogeneous information networks,
  Xiang Li, Ben Kao, Zhaochun Ren, Dawei Yin.
  In AAAI 2019, Honolulu, USA. [Project Codes]
  
• ROSC: robust spectral clustering on multi-scale data,
  Xiang Li, Ben Kao, Siqiang Luo, Martin Ester.
  In WWW 2018, Lyon, France. [Project Codes]
  
• Semi-supervised clustering in attributed heterogeneous information networks,
  Xiang Li, Yao Wu, Martin Ester, Ben Kao, Xin Wang, and Yudian Zheng.
  In WWW 2017, Perth, Australia. [Project Codes]
  
• On transductive classification in heterogeneous information networks,
  Xiang Li, Ben Kao, Yudian Zheng, and Zhipeng Huang.
  In CIKM 2016, Indianapolis, USA.
  
• Computing relevance in large heterogeneous information networks,
  Zhipeng Huang, Yudian Zheng, Reynold Cheng, Yizhou Sun, Nikos Mamoulis, and Xiang Li.
  In KDD 2016, San Francisco, USA.
  
• Classification with active learning and meta-paths in heterogeneous information networks,
  Chang Wan, Xiang Li, Ben Kao, Xiao Yu, Quanquan Gu, David Cheung, and Jiawei Han.
  In CIKM 2015, Melbourne, Australia.
  
• Novel user influence measurement based on user interaction in microblog,
  Xiang Li, Shaoyin Cheng, Wenlong Chen, and Fan Jiang.
  In ASONAM 2013, Niagara Falls, Canada.