Publications

publications by categories in reversed chronological order. * denotes equal contribution; † denotes corresponding authorship.

2023

    2022

    1. preprint
      Test-Time Robust Personalization for Federated Learning
      arXiv preprint arXiv:2205.10920 2022
    2. IMWUT 2022
      Learning Disentangled Behaviour Patterns for Wearable-based Human Activity Recognition
      Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT) 2022
    3. preprint
      DELTA: Diverse Client Sampling for Fasting Federated Learning
      Wang, Lin, Guo, YongXin, Lin, Tao, and Tang, Xiaoying
      arXiv preprint arXiv:2205.13925 2022
    4. preprint
      FedDebias: Reducing the Local Learning Bias Improves Federated Learning on Heterogeneous Data
      Guo, Yongxin, Tang, Xiaoying, and Lin, Tao
      arXiv preprint arXiv:2205.13462 2022
    5. preprint
      Understanding the Training Dynamics in Federated Deep Learning via Aggregation Weight Optimization
      2022
    6. OPT 2022
      Decentralized Stochastic Optimization with Client Sampling
      Optimization and machine learning (OPT) workshop, in NeurIPS 2022
    7. preprint
      Decentralized Gradient Tracking with Local Steps
      2022

    2021

    1. preprint
      Towards Federated Learning on Time-Evolving Heterogeneous Data
      Guo, Yongxin*, Lin, Tao*, and Tang, Xiaoying
      arXiv preprint arXiv:2112.13246, appeared in FL-ICML workshop 2021
    2. NeurIPS 2021
      RelaySum for Decentralized Deep Learning on Heterogeneous Data
      In Advances in Neural Information Processing Systems (NeurIPS) 2021
    3. NeurIPS 2021
      An Improved Analysis of Gradient Tracking for Decentralized Machine Learning
      In Advances in Neural Information Processing Systems (NeurIPS) 2021
    4. ICML 2021
      Quasi-global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data
      In International Conference on Machine Learning (ICML) 2021
    5. ICML 2021
      Consensus Control for Decentralized Deep Learning
      In International Conference on Machine Learning (ICML) 2021
    6. OPT 2021
      Understanding Memorization from the Perspective of Optimization via Efficient Influence Estimation
      Liu, Futong, Lin, Tao†, and Jaggi, Martin
      Optimization and machine learning (OPT) workshop, in NeurIPS 2021

    2020

    1. NeurIPS 2020
      Ensemble Distillation for Robust Model Fusion in Federated Learning
      In Advances in Neural Information Processing Systems (NeurIPS) 2020
    2. NeurIPS 2020
      On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them
      In Advances in Neural Information Processing Systems (NeurIPS) 2020
    3. EMNLP 2020
      Masking as an Efficient Alternative to Finetuning for Pretrained Language Models
      In Empirical Methods in Natural Language Processing (EMNLP) 2020
    4. ICML 2020
      Extrapolation for Large-batch Training in Deep Learning
      In International Conference on Machine Learning (ICML) 2020
    5. ICLR 2020
      Dynamic Model Pruning with Feedback
      In International Conference on Learning Representations (ICLR) 2020
    6. ICLR 2020
      Decentralized Deep Learning with Arbitrary Communication Compression
      In International Conference on Learning Representations (ICLR) 2020
    7. ICLR 2020
      Don’t Use Large Mini-batches, Use Local SGD
      In International Conference on Learning Representations (ICLR) 2020
    8. CLVision 2020
      Generalized Class Incremental Learning
      Mi, Fei*, Kong, Lingjing*Lin, Tao, Yu, Kaicheng, and Faltings, Boi
      In Conference on Computer Vision and Pattern Recognition (CVPR) Workshop on Continual Learning 2020

    2019

    1. ICML 2019
      Exploring Interpretable LSTM Neural Networks over Multi-variable Data
      In International Conference on Machine Learning (ICML) 2019
    2. TPDS 2019
      Ga-par: Dependable Microservice Orchestration Framework for Geo-distributed Clouds
      Wen, ZhenyuLin, TaoYang, RenyuJi, ShoulingRanjan, Rajiv, Romanovsky, Alexander, Lin, Changting, and Xu, Jie
      IEEE Transactions on Parallel and Distributed Systems (TPDS) 2019

    2018

    1. NeurIPS 2019
      Training DNNs with Hybrid Block Floating Point
      In Advances in Neural Information Processing Systems (NeurIPS) 2018

    2017

    1. IJCAI 2017
      Hybrid Neural Networks for Learning the Trend in Time Series
      In Proceedings of the twenty-sixth international joint conference on artificial intelligence (IJCAI) 2017
    2. VLDB 2017
      Heterogeneous Recommendations: What You Might Like to Read after Watching Interstellar
      Proceedings of the Very Large Data Base Endowment (VLDB) 2017
    3. IEEE 2017
      Fog Orchestration for IoT Services: Issues, Challenges and Directions
      Wen, ZhenyuYang, Renyu, Garraghan, Peter, Lin, TaoXu, Jie, and Rovatsos, Michael
      IEEE Internet Computing 2017