Publications

Publications by categories in reversed chronological order. * indicates co-first author.

2024

  1. NeurIPS
    Provably Faster Algorithms for Bilevel Optimization via Without-Replacement Sampling
    Junyi Li, and Heng Huang
    In Advances in Neural Information Processing Systems , 2024
  2. TMLR
    Hessian Free Efficient Single Loop Iterative Differentiation Methods for Bi-Level Optimization Problems
    Peiran Yu , Junyi Li, and Heng Huang
    Transactions on Machine Learning Research, 2024
  3. NAACL
    The steerability of large language models toward data-driven personas
    Junyi Li, Charith Peris , Ninareh Mehrabi , Palash Goyal , Kai-Wei Chang , Aram Galstyan , and 2 more authors
    In Proceedings of Conference of the North American Chapter of the Association for Computational Linguistics (Long Paper) , 2024
  4. ICLR
    FedDA: Faster Framework of Local Adaptive Gradient Methods via Restarted Dual Averaging
    Junyi Li, Feihu Huang , and Heng Huang
    The Twelfth International Conference on Learning Representations, 2024
  5. ICLR
    Dropout Enhanced Bilevel Training
    Peiran Yu , Junyi Li, and Huang Heng
    The Twelfth International Conference on Learning Representations, 2024
  6. AISTATS
    Adaptive federated minimax optimization with lower complexities
    Feihu Huang , Xinrui Wang , Junyi Li, and Songcan Chen
    In International Conference on Artificial Intelligence and Statistics , 2024
  7. CVPR
    Device-Wise Federated Network Pruning
    Junyi Li\textsuperscript* , Shangqian Gao\textsuperscript* , Zeyu Zhang\textsuperscript* , Yanfu Zhang , Weidong Cai , and Heng Huang
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , 2024

2023

  1. NeurIPS
    Communication-Efficient Federated Bilevel Optimization with Local and Global Lower Level Problems
    Junyi Li, Feihu Huang , and Heng Huang
    Advances in Neural Information Processing Systems, 2023
  2. NeurIPS
    FedSep: Separating Communication and Learning in Federated Learning
    Junyi Li, and Heng Huang
    Advances in Neural Information Processing Systems, 2023
  3. NeurIPS
    Federated Conditional Stochastic Optimization
    Xidong Wu , Jianhui Sun , Zhengmian Hu , Junyi Li, Aidong Zhang , and Heng Huang
    Advances in Neural Information Processing Systems, 2023

2022

  1. AAAI
    A fully single loop algorithm for bilevel optimization without hessian inverse
    Junyi Li, Bin Gu , and Heng Huang
    In Proceedings of the AAAI Conference on Artificial Intelligence , 2022
  2. ICML
    On the convergence of local stochastic compositional gradient descent with momentum
    Hongchang Gao , Junyi Li, and Heng Huang
    In International Conference on Machine Learning , 2022
  3. KDD
    Communication-efficient robust federated learning with noisy labels
    Junyi Li, Jian Pei , and Heng Huang
    In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining , 2022
  4. NeurIPS
    Enhanced bilevel optimization via bregman distance
    Feihu Huang , Junyi Li, Shangqian Gao , and Heng Huang
    Advances in Neural Information Processing Systems, 2022
  5. FedGRec: Federated Graph Recommender System with Lazy Update of Latent Embeddings
    Junyi Li, and Heng Huang
    FL: Recent Advances and New Challenges (FL-NeurIPS’22), 2022

2021

  1. NeurIPS
    Super-adam: faster and universal framework of adaptive gradients
    Feihu Huang , Junyi Li, and Heng Huang
    Advances in Neural Information Processing Systems, 2021
  2. Compositional federated learning: Applications in distributionally robust averaging and meta learning
    Feihu Huang , Junyi Li, and Heng Huang
    arXiv preprint arXiv:2106.11264, 2021
  3. Biadam: Fast adaptive bilevel optimization methods
    Feihu Huang , Junyi Li, and Shangqian Gao
    arXiv preprint arXiv:2106.11396, 2021

2020

  1. AAAI
    Generating realistic stock market order streams
    Junyi Li, Xintong Wang , Yaoyang Lin , Arunesh Sinha , and Michael Wellman
    In Proceedings of the AAAI Conference on Artificial Intelligence , 2020
  2. KDD
    Faster secure data mining via distributed homomorphic encryption
    Junyi Li, and Heng Huang
    In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining , 2020
  3. Improved bilevel model: Fast and optimal algorithm with theoretical guarantee
    Junyi Li, Bin Gu , and Heng Huang
    arXiv preprint arXiv:2009.00690, 2020