Welcome to the website of the Learning and INference Systems (LINs) Lab at Westlake University!

Our research interests lie in the intersection of optimization and generalization for deep learning:

  • leveraging theoretical/empirical understanding (e.g., loss landscape, and training dynamics)
  • to design efficient & robust methods (both learning and inference)
  • for deep learning (centralized) and collaborative deep learning (distributed and/or decentralized),
  • under imperfect environments (e.g., noisy, heterogeneous, and hardware-constrained).

Lab activities:


News

Sep 27, 2024 Two papers of our group were accepted at this year’s NeurIPS 2024 conference. Congratulations to Peng on the acceptance of his paper on Ideal Data, and congratulations to Jiamin for his attempts on Cooperative Hardware-Prompt Learning.
Jul 2, 2024 Congratulations to Yuxuan on the oral acceptance of his paper on multimodal benchmark in pathology at ECCV 2024. This paper was selected as the one of best paper candidates at ECCV.
May 2, 2024 Our paper on distribution-shift-robust Federated Learning was accepted at this year’s ICML 2024 conference. Congratulations to Yongxin.
Feb 27, 2024 Our paper on efficient dataset distillation was accepted at this year’s CVPR 2024 conference. Congratulations to Peng (he also received a CVPR 2024 travel grant).
Feb 4, 2024 We are looking for self-motivated research internship students! Please email us with your CV.

Selected publications

  1. NeurIPS 2024
    Efficiency for Free: Ideal Data Are Transportable Representations
    Sun, Peng, Jiang, Yi, and Lin, Tao
    In Advances in Neural Information Processing Systems (NeurIPS) 2024
  2. ICLR 2023
    Test-Time Robust Personalization for Federated Learning
    In International Conference on Learning Representations (ICLR) 2023
  3. ICML 2021
    Quasi-global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data
    In International Conference on Machine Learning (ICML) 2021
  4. ICLR 2020
    Decentralized Deep Learning with Arbitrary Communication Compression
    In International Conference on Learning Representations (ICLR) 2020
  5. ICLR 2020
    Don’t Use Large Mini-batches, Use Local SGD
    In International Conference on Learning Representations (ICLR) 2020