Lu Liu
Address: 1600 Amphitheatre Parkway, Mountain View, CA

About Me ([GitHub] [Google Scholar] [Twitter] [Resume])

Hi! I am a research scientist at Google Research! I did my Ph.D. at University of Technology Sydney, Australia.

Research Interests

My research mainly solves the problem of how to learn better representations with fewer labels. I have developed algorithms for this problem via weakly-supervised data, knowledge graphs, semantic description, cross-domain representation transfer, feature or data generation, and memory networks.


FedProto: Federated Prototype Learning across Heterogeneous Clients
Yue Tan, Guodong Long, Lu Liu, Tianyi Zhou, Qinghua Lu, Jing Jiang, Chengqi Zhang
in AAAI 2022
[ arXiv ] [ BibTex ]
Recognizing Vector Graphics without Rasterization
Xinyang Jiang, Lu Liu, Caihua Shan, Yifei Shen, Xuanyi Dong, Dongsheng Li
in NeurIPS 2021
[ NeurIPS-PDF ] [ BibTex ]
A Universal Representation Transformer Layer for Few-Shot Image Classification
Lu Liu, William Hamilton, Guodong Long, Jing Jiang, Hugo Larochelle
in ICLR 2021
[ arXiv ] [ ICLR-PDF ] [ Code ] [ BibTex ]
Isometric Propagation Network for Generalized Zero-shot Learning
Lu Liu, Tianyi Zhou, Guodong Long, Jing Jiang, Xuanyi Dong, Chengqi Zhang
in ICLR 2021
[ ICLR-PDF ] [ BibTex ]
Free Lunch for Few-shot Learning: Distribution Calibration
Shuo Yang, Lu Liu, Min Xu
in ICLR 2021 (Oral)
[ BibTex ]
NATS-Bench: Benchmarking NAS Algorithms for Architecture Topology and Size
Xuanyi Dong, Lu Liu, Katarzyna Musial, Bogdan Gabrys
in IEEE TPAMI 2021
[ arXiv ] [ Code ] [ API/Dataset ] [ Package ] [ Project ] [ BibTex ]
Episodic memory governs choices: An RNN-based reinforcement learning model for decision-making task
Xiaohan Zhang, Lu Liu, Guodong Long, Jing Jiang, Shenquan Liu
in Neural Networks
[ PDF ] [ BibTex ]
Attribute Propagation Network for Graph Zero-shot Learning
Lu Liu, Tianyi Zhou, Guodong Long, Jing Jiang, Chengqi Zhang
in AAAI 2020 (Spotlight)
[ arXiv ] [ AAAI-PDF ] [ Poster ] [ BibTex ]
Many-Class Few-Shot Learning onMulti-Granularity Class Hierarchy
Lu Liu, Tianyi Zhou, Guodong Long, Jing Jiang, Chengqi Zhang
in IEEE Transactions on Knowledge and Data Engineering (TKDE) 2020
[ arXiv ] [ IEEE-PDF ] [ BibTex ]
Learning to Propagate for Graph Meta-Learning
Lu Liu, Tianyi Zhou, Guodong Long, Jing Jiang, Chengqi Zhang
in NeurIPS 2019
[ arXiv ] [ NeurIPS-PDF ] [ Poster ] [ Slides ] [ Code ] [ BibTex ]
Prototype Propagation Networks (PPN) for Weakly-supervised Few-shot Learning on Category Graph
Lu Liu, Tianyi Zhou, Guodong Long, Jing Jiang, Lina Yao, Chengqi Zhang
in IJCAI 2019 (Oral) & ICML 2019 Workshop
[ arXiv ] [ IJCAI-PDF ] [ Code ] [ BibTex ]
Few-shot Time-series Classification with Dual Interpretability
Wensi Tang, Lu Liu, Guodong Long
in ICML 2019 Time Series Workshop
[ ICML-W-PDF ] [ BibTex ]

Review Services

IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
Neural Information Processing Systems (NeurIPS)
International Conference on Machine Learning (ICML)
International Conference on Learning Representations (ICLR)
Computer Vision and Pattern Recognition (CVPR)
AAAI Conference on Artificial Intelligence (AAAI)
International Joint Conference on Artificial Intelligence (IJCAI)