Chaosheng Dong

Preprints

• Why Ghost Outputs Teach: A Kernel-Based Understanding of Subliminal Learning.
  Zhe Li, Bicheng Ying, Chaosheng Dong, and Haibo Yang.
  

• Mathematical Programming in Machine Learning and Artificial Intelligence: A Unified Taxonomy of Models and Applications.
  Chaosheng Dong.
  

• One Model, Many Minds: Unlocking Multi-Agent Synergy in a Single Agent via Mixture of Roles.
  Zhichen Zeng, Huiyuan Chen, Jingru Cheng, Juan Zha, Ming Liu, Ying Chen, Xiyuan Yang, Chaosheng Dong, Haiyang Zhang, and Hanghang Tong.
  

• MatrAIx: Simulating the World with 8.3 Billion Persona Agents.
  Xiaomin Li et al.
  

• P2GNN: Two Prototype Sets to Boost GNN Performance.
  Arihant Jain, Gundeep Arora, Anoop Saladi, and Chaosheng Dong.
  

• DeepMTL2R: A Library for Deep Multi-task Learning to Rank.
  Chaosheng Dong, Peiyao Xiao, Yijia Wang, and Kaiyi Ji.
  

• Towards Generalized Inverse Reinforcement Learning.
  Chaosheng Dong and Yijia Wang.
  

• Bandit Learning to Rank with Position-Based Click Models: Personalized and Equal Treatments.
  Tianchen Zhou, Jia Liu, Yang Jiao, Chaosheng Dong, Yetian Chen, Yan Gao, and Yi Sun.
  

• Inferring Parameters Through Inverse Multiobjective Optimization.
  Chaosheng Dong and Bo Zeng.
  [bibtex]

Journal Papers

• Learning Risk Preferences from Investment Portfolios Using Inverse Optimization.
  Shi Yu, Haoran Wang, and Chaosheng Dong.
  Published in Research in International Business and Finance, 2023.
  

Conference Papers

• Behavioral Feature Boosting via Substitute Relationships for E-commerce Search.
  Chaosheng Dong, Michinari Momma, Yijia Wang, Yan Gao, and Yi Sun.
  Accepted at the ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2026).
  

• Converge Faster, Talk Less: Hessian-Informed Federated Zeroth-Order Optimization.
  Zhe Li, Bicheng Ying, Zidong Liu, Chaosheng Dong, and Haibo Yang.
  Accepted at the International Conference on Learning Representations (ICLR 2026).
  

• LDC-MTL: Balancing Multi-task Learning Through Scalable Loss Discrepancy Control.
  Peiyao Xiao, Chaosheng Dong, Shaofeng Zou, and Kaiyi Ji.
  Accepted at the European Conference on Computer Vision (ECCV 2026).
  

• Enabling Pareto-Stationarity Exploration in Multi-Objective Reinforcement Learning: A Multi-Objective Weighted-Chebyshev Actor-Critic Approach.
  Fnu Hairi, Jiao Yang, Tianchen Zhou, Haibo Yang, Chaosheng Dong, Fan Yang, Michinari Momma, Yan Gao, and Jia Liu.
  Accepted at the IEEE Conference on Decision and Control (CDC 2025).
  

• Achieving Dimension-Free Communication in Federated Learning via Zeroth-Order Optimization.
  Zhe Li, Bicheng Ying, Zidong Liu, Chaosheng Dong, and Haibo Yang.
  Accepted at the International Conference on Learning Representations (ICLR 2025).
  

• MO-LightGBM: A Library for Multi-objective Learning to Rank with LightGBM.
  Chaosheng Dong and Michinari Momma.
  Accepted at the ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2025).
  

• AutoEval-ToD: Automated Evaluation of Task-oriented Dialog Systems.
  Arihant Jain, Purav Aggarwal, Rishav Sahay, Chaosheng Dong, and Anoop Saladi.
  Accepted at the Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL 2025).
  

• Generative Prompting for Complex Product Retrieval.
  Nan Xi, Jingjing Meng, Yitian Chen, Chaosheng Dong, Yan Gao, Yi Sun, and Junsong Yuan.
  Accepted at The Web Conference (TheWebConf 2025).
  

• STIMULUS: Achieving Fast Convergence and Low Sample Complexity in Stochastic Multi-Objective Learning.
  Zidong Liu, Chaosheng Dong, Michinari Momma, Shuo Shao, Shaoyuan Xu, Haibo Yang, and Jia Liu.
  Accepted at the Conference on Uncertainty in Artificial Intelligence (UAI 2025).
  

• DeComFL: Federated Learning with Dimension-Free Communication.
  Zhe Li, Bicheng Ying, Zidong Liu, Chaosheng Dong, and Haibo Yang.
  Accepted at the International Workshop on Federated Foundation Models, 2024.
  

• AdaSelection: Accelerating Deep Learning Training through Adaptive Data Subsampling.
  Minghe Zhang, Chaosheng Dong, Jinmiao Fu, Tianchen Zhou, Jia Liang, Jia Liu, Bo Liu, Michinari Momma, Bryan Wang, Yan Gao, and Yi Sun.
  Accepted at the ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2024).
  

• Scalable and Effective Implicit Graph Neural Networks on Large Graphs.
  Juncheng Liu, Bryan Hooi, Kenji Kawaguchi, Yijia Wang, Chaosheng Dong, and Xiao Xiao.
  Accepted at the International Conference on Learning Representations (ICLR 2024).
  

• Q-Tuning: Queue-based Prompt Tuning for Lifelong Few-shot Language Learning.
  Yanhui Guo, Shaoyuan Xu, Jinmiao Fu, Jia Liu, Chaosheng Dong, and Bryan Wang.
  Accepted at the Findings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2024).
  

• Federated Multi-Objective Learning.
  Haibo Yang, Zhuqing Liu, Jia Liu, Chaosheng Dong, and Michinari Momma.
  Accepted at the Conference on Neural Information Processing Systems (NeurIPS 2023).
  

• G-STO: Sequential Main Shopping Intention Detection via Graph-Regularized Stochastic Transformer.
  Yuchen Zhuang, Xin Shen, Yan Zhao, Chaosheng Dong, Ming Wang, Jin Li, and Chao Zhang.
  Accepted at the ACM International Conference on Information and Knowledge Management (CIKM 2023).
  

• Multi-Task Learning on Heterogeneous Graph Neural Network for Substitute Recommendation.
  Tianchen Zhou, Michinari Momma, Chaosheng Dong, Fan Yang, Chenghuan Guo, Jin Shang, and Jia Liu.
  Accepted at the KDD Workshop on Mining and Learning with Graphs (MLG-KDD 2023).
  

• AdaSelection: Accelerating Deep Learning Training through Data Subsampling.
  Minghe Zhang, Chaosheng Dong, Jinmiao Fu, Tianchen Zhou, Jia Liang, Jia Liu, Bo Liu, Michinari Momma, Bryan Wang, Yan Gao, and Yi Sun.
  Accepted at the KDD Workshop on Resource-Efficient Learning for Knowledge Discovery, 2023.
  

• Querywise Fair Learning to Rank through Multi-Objective Optimization.
  Debabrata Mahapatra, Chaosheng Dong, and Michinari Momma.
  Accepted at the ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2023).
  

• Learning Multiobjective Program Through Online Learning.
  Chaosheng Dong, Yijia Wang, and Bo Zeng.
  Accepted at the OPT Workshop on Optimization for Machine Learning, 2023.
  

• Multi-Label Learning to Rank through Multi-Objective Optimization.
  Debabrata Mahapatra, Chaosheng Dong, Yetian Chen, Deqiang Meng, and Michinari Momma.
  Accepted at the ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2023).
  

• Multi-task GNN for Substitute Identification.
  Tong Jian, Fan Yang, Zhen Zuo, Wenbo Wang, Michinari Momma, Tong Zhao, Chaosheng Dong, Yan Gao, and Yi Sun.
  Accepted at The Web Conference (TheWebConf 2022).
  

• A Multi-objective/Multi-task Learning Framework Induced by Pareto Stationarity.
  Michinari Momma, Chaosheng Dong, and Jia Liu.
  Accepted at the International Conference on Machine Learning (ICML 2022).
  

• Multi-objective Ranking with Directions of Preferences.
  Michinari Momma, Chaosheng Dong, and Yetian Chen.
  Accepted at the SIGIR Workshop on eCommerce, 2022.
  

• Personalized Complementary Product Recommendation.
  An Yan, Chaosheng Dong, Yan Gao, Jinmiao Fu, Tong Zhao, Yi Sun, and Julian McAuley.
  Accepted at the Web Conference (WWW 2022).
  

• Bandit Learning with Joint Effect of Incentivized Sampling, Delayed Sampling Feedback, and Self-Reinforcing User Preferences.
  Tianchen Zhou, Jia Liu, Chaosheng Dong, and Yi Sun.
  Accepted at the International Conference on Learning Representations (ICLR 2022).
  

• Incentivized Bandit Learning with Self-Reinforcing User Preferences.
  Tianchen Zhou, Jia Liu, Chaosheng Dong, and Jingyuan Deng.
  Accepted at the International Conference on Machine Learning (ICML 2021).
  

• One Backward from Ten Forward, Subsampling for Large-Scale Deep Learning.
  Chaosheng Dong, Xiaojie Jin, Weihao Gao, Yijia Wang, Hongyi Zhang, Xiang Wu, Jianchao Yang, and Xiaobing Liu.
  Accepted at the DeMaL Workshop at The Web Conference 2021.
  

• Heterogeneous Graph Neural Networks with Neighbor-SIM Attention Mechanism for Substitute Product Recommendation.
  Liyuan Zheng, Zhen Zuo, Wenbo Wang, Chaosheng Dong, Michinari Momma, and Yi Sun.
  Accepted at the Workshop on Deep Learning on Graphs: Methods and Applications at AAAI 2021.
  

• Wasserstein Distributionally Robust Inverse Multiobjective Optimization.
  Chaosheng Dong and Bo Zeng.
  Preliminary version has been accepted by the OTML Workshop at NeurIPS 2019.
  Accepted at the Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI 2021).
  

• Expert Learning through Generalized Inverse Multiobjective Optimization: Models, Insights and Algorithms.
  Chaosheng Dong and Bo Zeng.
  Accepted at the International Conference on Machine Learning (ICML 2020).
  -- Runner-up in the best theoretical paper competition at the 15th INFORMS Workshop on Data Mining & Decision Analytics.
  

• Generalized Inverse Optimization through Online Learning.
  Chaosheng Dong, Yiran Chen, and Bo Zeng.
  Accepted at the Neural Information Processing Systems Conference (NeurIPS 2018).
  -- Finalist in the best theoretical paper competition at the 14th INFORMS Workshop on Data Mining & Decision Analytics.
  [bibtex][poster] [code]