activity
20192023
most citedDeep Subdomain Adaptation Network for Image Classification

1.2k citations · 2k across the 23 of their papers we have counts for

collaborators
Showing 2021Show all

9 papers · 1 filter

cs.LG2021

Exploiting Bi-directional Global Transition Patterns and Personal Preferences for Missing POI Category Identification

Dongbo Xi, Fuzhen Zhuang, Yanchi Liu +4

Recent years have witnessed the increasing popularity of Location-based Social Network (LBSN) services, which provides unparalleled opportunities to build personalized Point-of-Int…

cs.LG2021★ 2 cited

Neural Hierarchical Factorization Machines for User's Event Sequence Analysis

Dongbo Xi, Fuzhen Zhuang, Bowen Song +6

Many prediction tasks of real-world applications need to model multi-order feature interactions in user's event sequence for better detection performance. However, existing popular…

cs.IR2021

Mind the Gap: Cross-Lingual Information Retrieval with Hierarchical Knowledge Enhancement

Fuwei Zhang, Zhao Zhang, Xiang Ao +4

Cross-Lingual Information Retrieval (CLIR) aims to rank the documents written in a language different from the user's query. The intrinsic gap between different languages is an ess…

cs.CL2021

Towards Robust Knowledge Graph Embedding via Multi-task Reinforcement Learning

Zhao Zhang, Fuzhen Zhuang, Hengshu Zhu +4

Nowadays, Knowledge graphs (KGs) have been playing a pivotal role in AI-related applications. Despite the large sizes, existing KGs are far from complete and comprehensive. In orde…

cs.IR2021★ 14 cited

Personalized Transfer of User Preferences for Cross-domain Recommendation

Yongchun Zhu, Zhenwei Tang, Yudan Liu +5

Cold-start problem is still a very challenging problem in recommender systems. Fortunately, the interactions of the cold-start users in the auxiliary source domain can help cold-st…

cs.CV2021★ 1.2k cited

Deep Subdomain Adaptation Network for Image Classification

Yongchun Zhu, Fuzhen Zhuang, Jindong Wang +5

For a target task where labeled data is unavailable, domain adaptation can transfer a learner from a different source domain. Previous deep domain adaptation methods mainly learn a…