Search Results for author: Asiri Wijesinghe

Found 5 papers, 3 papers with code

N-WL: A New Hierarchy of Expressivity for Graph Neural Networks

no code implementations The Eleventh International Conference on Learning Representations 2023 Qing Wang, Dillon Chen, Asiri Wijesinghe, Shouheng Li, Muhammad Farhan

The expressive power of Graph Neural Networks (GNNs) is fundamental for understanding their capabilities and limitations, i. e., what graph properties can or cannot be learnt by a GNN.

A Regularized Wasserstein Framework for Graph Kernels

1 code implementation6 Oct 2021 Asiri Wijesinghe, Qing Wang, Stephen Gould

This framework provides a novel optimal transport distance metric, namely Regularized Wasserstein (RW) discrepancy, which can preserve both features and structure of graphs via Wasserstein distances on features and their local variations, local barycenters and global connectivity.

A New Perspective on "How Graph Neural Networks Go Beyond Weisfeiler-Lehman?"

1 code implementation ICLR 2022 Asiri Wijesinghe, Qing Wang

To elaborate this framework, we propose a novel neural model, called GraphSNN, and prove that this model is strictly more expressive than the Weisfeiler Lehman test in distinguishing graph structures.

Graph Learning

ErGAN: Generative Adversarial Networks for Entity Resolution

no code implementations18 Dec 2020 Jingyu Shao, Qing Wang, Asiri Wijesinghe, Erhard Rahm

Entity resolution targets at identifying records that represent the same real-world entity from one or more datasets.

Entity Resolution Generative Adversarial Network

DFNets: Spectral CNNs for Graphs with Feedback-Looped Filters

1 code implementation NeurIPS 2019 Asiri Wijesinghe, Qing Wang

We propose a novel spectral convolutional neural network (CNN) model on graph structured data, namely Distributed Feedback-Looped Networks (DFNets).

Document Classification General Classification +1

Cannot find the paper you are looking for? You can Submit a new open access paper.