activity
20192021
most citedLearning Disentangled Semantic Representation for Domain Adaptation

124 citations · 131 across the 6 of their papers we have counts for

collaborators

10 papers

cs.LG2021

Graph Domain Adaptation: A Generative View

Ruichu Cai, Fengzhu Wu, Zijian Li +3

Recent years have witnessed tremendous interest in deep learning on graph-structured data. Due to the high cost of collecting labeled graph-structured data, domain adaptation is im…

cs.LG2021

Adaptive Multi-Source Causal Inference

Thanh Vinh Vo, Pengfei Wei, Trong Nghia Hoang +1

Data scarcity is a tremendous challenge in causal effect estimation. In this paper, we propose to exploit additional data sources to facilitate estimating causal effects in the tar…

cs.CL2021

Joint Intent Detection and Slot Filling with Wheel-Graph Attention Networks

Pengfei Wei, Bi Zeng, Wenxiong Liao

Intent detection and slot filling are two fundamental tasks for building a spoken language understanding (SLU) system. Multiple deep learning-based joint models have demonstrated e…

cs.CV2020124 cited

Learning Disentangled Semantic Representation for Domain Adaptation

Ruichu Cai, Zijian Li, Pengfei Wei +3

Domain adaptation is an important but challenging task. Most of the existing domain adaptation methods struggle to extract the domain-invariant representation on the feature space…

cs.LG20203 cited

Cooperative Heterogeneous Deep Reinforcement Learning

Han Zheng, Pengfei Wei, Jing Jiang +3

Numerous deep reinforcement learning agents have been proposed, and each of them has its strengths and flaws. In this work, we present a Cooperative Heterogeneous Deep Reinforcemen…

cs.LG2020

MESA: Boost Ensemble Imbalanced Learning with MEta-SAmpler

Zhining Liu, Pengfei Wei, Jing Jiang +3

Imbalanced learning (IL), i.e., learning unbiased models from class-imbalanced data, is a challenging problem. Typical IL methods including resampling and reweighting were designed…