78 citations · 121 across the 7 of their papers we have counts for
7 papers
Evaluating Self-Supervised Learning for Molecular Graph Embeddings
Hanchen Wang, Jean Kaddour, Shengchao Liu +3
Graph Self-Supervised Learning (GSSL) provides a robust pathway for acquiring embeddings without expert labelling, a capability that carries profound implications for molecular gra…
An Empirical Study of Retrieval-enhanced Graph Neural Networks
Dingmin Wang, Shengchao Liu, Hanchen Wang +5
Graph Neural Networks (GNNs) are effective tools for graph representation learning. Most GNNs rely on a recursive neighborhood aggregation scheme, named message passing, thereby th…
Advancing COVID-19 Diagnosis with Privacy-Preserving Collaboration in Artificial Intelligence
Xiang Bai, Hanchen Wang, Liya Ma +43
Artificial intelligence (AI) provides a promising substitution for streamlining COVID-19 diagnoses. However, concerns surrounding security and trustworthiness impede the collection…
Iterative Teaching by Label Synthesis
Weiyang Liu, Zhen Liu, Hanchen Wang +3
In this paper, we consider the problem of iterative machine teaching, where a teacher provides examples sequentially based on the current iterative learner. In contrast to previous…
Matching Point Sets with Quantum Circuit Learning
Mohammadreza Noormandipour, Hanchen Wang
In this work, we propose a parameterised quantum circuit learning approach to point set matching problem. In contrast to previous annealing-based methods, we propose a quantum circ…
Unsupervised Point Cloud Pre-Training via Occlusion Completion
Hanchen Wang, Qi Liu, Xiangyu Yue +2
We describe a simple pre-training approach for point clouds. It works in three steps: 1. Mask all points occluded in a camera view; 2. Learn an encoder-decoder model to reconstruct…
An Empirical Study on Learning Fairness Metrics for COMPAS Data with Human Supervision
Hanchen Wang, Nina Grgic-Hlaca, Preethi Lahoti +2
The notion of individual fairness requires that similar people receive similar treatment. However, this is hard to achieve in practice since it is difficult to specify the appropri…