A Quasi-Wasserstein Loss for Learning Graph Neural Networks

1 code implementation • 18 Oct 2023 • Minjie Cheng, Hongteng Xu

To eliminate such inconsistency, in this study we propose a novel Quasi-Wasserstein (QW) loss with the help of the optimal transport defined on graphs, leading to new learning and prediction paradigms of GNNs.

Regularized Optimal Transport Layers for Generalized Global Pooling Operations

1 code implementation • 13 Dec 2022 • Hongteng Xu, Minjie Cheng

Making the parameters of the ROT problem learnable, we develop a family of regularized optimal transport pooling (ROTP) layers.

Graph Classification Image Classification

Revisiting Global Pooling through the Lens of Optimal Transport

1 code implementation • 23 Jan 2022 • Minjie Cheng, Hongteng Xu

Global pooling is one of the most significant operations in many machine learning models and tasks, whose implementation, however, is often empirical in practice.

Graph Classification Graph Embedding +1