90 citations · 225 across the 17 of their papers we have counts for
7 papers · 1 filter
Learning Task-relevant Representations for Generalization via Characteristic Functions of Reward Sequence Distributions
Rui Yang, Jie Wang, Zijie Geng +4
Generalization across different environments with the same tasks is critical for successful applications of visual reinforcement learning (RL) in real scenarios. However, visual di…
Self-Adaptive Label Augmentation for Semi-supervised Few-shot Classification
Xueliang Wang, Jianyu Cai, Shuiwang Ji +3
Few-shot classification aims to learn a model that can generalize well to new tasks when only a few labeled samples are available. To make use of unlabeled data that are more abund…
Exploiting Global Semantic Similarities in Knowledge Graphs by Relational Prototype Entities
Xueliang Wang, Jiajun Chen, Feng Wu +1
Knowledge graph (KG) embedding aims at learning the latent representations for entities and relations of a KG in continuous vector spaces. An empirical observation is that the head…
FlowX: Towards Explainable Graph Neural Networks via Message Flows
Shurui Gui, Hao Yuan, Jie Wang +3
We investigate the explainability of graph neural networks (GNNs) as a step toward elucidating their working mechanisms. While most current methods focus on explaining graph nodes,…
Compressing Deep Graph Neural Networks via Adversarial Knowledge Distillation
Huarui He, Jie Wang, Zhanqiu Zhang +1
Deep graph neural networks (GNNs) have been shown to be expressive for modeling graph-structured data. Nevertheless, the over-stacked architecture of deep graph models makes it dif…
Duality-Induced Regularizer for Semantic Matching Knowledge Graph Embeddings
Jie Wang, Zhanqiu Zhang, Zhihao Shi +3
Semantic matching models -- which assume that entities with similar semantics have similar embeddings -- have shown great power in knowledge graph embeddings (KGE). Many existing s…
Rethinking Graph Convolutional Networks in Knowledge Graph Completion
Zhanqiu Zhang, Jie Wang, Jieping Ye +1
Graph convolutional networks (GCNs) -- which are effective in modeling graph structures -- have been increasingly popular in knowledge graph completion (KGC). GCN-based KGC models…