2 papers
cs.LG2024
NoiseHGNN: Synthesized Similarity Graph-Based Neural Network For Noised Heterogeneous Graph Representation Learning
Xiong Zhang, Cheng Xie, Haoran Duan +1
Real-world graph data environments intrinsically exist noise (e.g., link and structure errors) that inevitably disturb the effectiveness of graph representation and downstream lear…
cs.CV2021
Cross Knowledge-based Generative Zero-Shot Learning Approach with Taxonomy Regularization
Cheng Xie, Hongxin Xiang, Ting Zeng +3
Although zero-shot learning (ZSL) has an inferential capability of recognizing new classes that have never been seen before, it always faces two fundamental challenges of the cross…