349 citations · 1.6k across the 67 of their papers we have counts for
11 papers · 1 filter
Reachability-Aware Laplacian Representation in Reinforcement Learning
Kaixin Wang, Kuangqi Zhou, Jiashi Feng +2
In Reinforcement Learning (RL), Laplacian Representation (LapRep) is a task-agnostic state representation that encodes the geometry of the environment. A desirable property of LapR…
Divide to Adapt: Mitigating Confirmation Bias for Domain Adaptation of Black-Box Predictors
Jianfei Yang, Xiangyu Peng, Kai Wang +4
Domain Adaptation of Black-box Predictors (DABP) aims to learn a model on an unlabeled target domain supervised by a black-box predictor trained on a source domain. It does not req…
Tyger: Task-Type-Generic Active Learning for Molecular Property Prediction
Kuangqi Zhou, Kaixin Wang, Jiashi Feng +3
How to accurately predict the properties of molecules is an essential problem in AI-driven drug discovery, which generally requires a large amount of annotation for training deep l…
Sharpness-Aware Training for Free
Jiawei Du, Daquan Zhou, Jiashi Feng +2
Modern deep neural networks (DNNs) have achieved state-of-the-art performances but are typically over-parameterized. The over-parameterization may result in undesirably large gener…
The Geometry of Robust Value Functions
Kaixin Wang, Navdeep Kumar, Kuangqi Zhou +3
The space of value functions is a fundamental concept in reinforcement learning. Characterizing its geometric properties may provide insights for optimization and representation. E…
DHA: End-to-End Joint Optimization of Data Augmentation Policy, Hyper-parameter and Architecture
Kaichen Zhou, Lanqing Hong, Shoukang Hu +4
Automated machine learning (AutoML) usually involves several crucial components, such as Data Augmentation (DA) policy, Hyper-Parameter Optimization (HPO), and Neural Architecture…
Towards Better Laplacian Representation in Reinforcement Learning with Generalized Graph Drawing
Kaixin Wang, Kuangqi Zhou, Qixin Zhang +3
The Laplacian representation recently gains increasing attention for reinforcement learning as it provides succinct and informative representation for states, by taking the eigenve…
No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data
Mi Luo, Fei Chen, Dapeng Hu +3
A central challenge in training classification models in the real-world federated system is learning with non-IID data. To cope with this, most of the existing works involve enforc…
Continual Learning via Bit-Level Information Preserving
Yujun Shi, Li Yuan, Yunpeng Chen +1
Continual learning tackles the setting of learning different tasks sequentially. Despite the lots of previous solutions, most of them still suffer significant forgetting or expensi…
How Well Does Self-Supervised Pre-Training Perform with Streaming Data?
Dapeng Hu, Shipeng Yan, Qizhengqiu Lu +6
Prior works on self-supervised pre-training focus on the joint training scenario, where massive unlabeled data are assumed to be given as input all at once, and only then is a lear…
Understanding and Resolving Performance Degradation in Graph Convolutional Networks
Kuangqi Zhou, Yanfei Dong, Kaixin Wang +4
A Graph Convolutional Network (GCN) stacks several layers and in each layer performs a PROPagation operation (PROP) and a TRANsformation operation (TRAN) for learning node represen…