Reachability-Aware Laplacian Representation in Reinforcement Learning

no code implementations • 24 Oct 2022 • Kaixin Wang, Kuangqi Zhou, Jiashi Feng, Bryan Hooi, Xinchao Wang

In Reinforcement Learning (RL), Laplacian Representation (LapRep) is a task-agnostic state representation that encodes the geometry of the environment.

reinforcement-learning Reinforcement Learning (RL)

Online Learning for Non-monotone Submodular Maximization: From Full Information to Bandit Feedback

no code implementations • 16 Aug 2022 • Qixin Zhang, Zengde Deng, Zaiyi Chen, Kuangqi Zhou, Haoyuan Hu, Yu Yang

In this paper, we revisit the online non-monotone continuous DR-submodular maximization problem over a down-closed convex set, which finds wide real-world applications in the domain of machine learning, economics, and operations research.

Tyger: Task-Type-Generic Active Learning for Molecular Property Prediction

no code implementations • 23 May 2022 • Kuangqi Zhou, Kaixin Wang, Jiashi Feng, Jian Tang, Tingyang Xu, Xinchao Wang

However, existing best deep AL methods are mostly developed for a single type of learning task (e. g., single-label classification), and hence may not perform well in molecular property prediction that involves various task types.

Active Learning Drug Discovery +3

The Geometry of Robust Value Functions

no code implementations • 30 Jan 2022 • Kaixin Wang, Navdeep Kumar, Kuangqi Zhou, Bryan Hooi, Jiashi Feng, Shie Mannor

The key of this perspective is to decompose the value space, in a state-wise manner, into unions of hypersurfaces.

Mimicking the Oracle: An Initial Phase Decorrelation Approach for Class Incremental Learning

1 code implementation • CVPR 2022 • Yujun Shi, Kuangqi Zhou, Jian Liang, Zihang Jiang, Jiashi Feng, Philip Torr, Song Bai, Vincent Y. F. Tan

Specifically, we experimentally show that directly encouraging CIL Learner at the initial phase to output similar representations as the model jointly trained on all classes can greatly boost the CIL performance.

Class Incremental Learning Incremental Learning

Value Penalized Q-Learning for Recommender Systems

no code implementations • 15 Oct 2021 • Chengqian Gao, Ke Xu, Kuangqi Zhou, Lanqing Li, Xueqian Wang, Bo Yuan, Peilin Zhao

To alleviate the action distribution shift problem in extracting RL policy from static trajectories, we propose Value Penalized Q-learning (VPQ), an uncertainty-based offline RL algorithm.

Offline RL Q-Learning +2

Towards Better Laplacian Representation in Reinforcement Learning with Generalized Graph Drawing

1 code implementation • 12 Jul 2021 • Kaixin Wang, Kuangqi Zhou, Qixin Zhang, Jie Shao, Bryan Hooi, Jiashi Feng

It enables learning high-quality Laplacian representations that faithfully approximate the ground truth.

Continuous Control reinforcement-learning +1

Few-shot Classification via Adaptive Attention

1 code implementation • 6 Aug 2020 • Zi-Hang Jiang, Bingyi Kang, Kuangqi Zhou, Jiashi Feng

To be specific, we devise a simple and efficient meta-reweighting strategy to adapt the sample representations and generate soft attention to refine the representation such that the relevant features from the query and support samples can be extracted for a better few-shot classification.

Classification Few-Shot Learning +1

Multi-Miner: Object-Adaptive Region Mining for Weakly-Supervised Semantic Segmentation

no code implementations • 14 Jun 2020 • Kuangqi Zhou, Qibin Hou, Zun Li, Jiashi Feng

In this paper, we propose a novel multi-miner framework to perform a region mining process that adapts to diverse object sizes and is thus able to mine more integral and finer object regions.

Object Segmentation +2

Understanding and Resolving Performance Degradation in Graph Convolutional Networks

2 code implementations • 12 Jun 2020 • Kuangqi Zhou, Yanfei Dong, Kaixin Wang, Wee Sun Lee, Bryan Hooi, Huan Xu, Jiashi Feng

In this work, we study performance degradation of GCNs by experimentally examining how stacking only TRANs or PROPs works.