LGFeb 4, 2021

Lookup subnet based Spatial Graph Convolutional neural Network

arXiv:2102.02588v13 citations
Originality Incremental advance
AI Analysis

This work provides a new approach to applying CNN-like operations to graph-structured data, potentially benefiting researchers working on graph analysis tasks by offering a competitive alternative to existing GNNs.

This paper proposes a cross-correlation based graph convolution method that generalizes CNNs to non-Euclidean data, inheriting CNN features like local filters and parameter sharing. The method achieves or matches state-of-the-art results on the Cora, Citeseer, and Pubmed citation network datasets.

Convolutional Neural Networks(CNNs) has achieved remarkable performance breakthrough in Euclidean structure data. Recently, aggregation-transformation based Graph Neural networks(GNNs) gradually produce a powerful performance on non-Euclidean data. In this paper, we propose a cross-correlation based graph convolution method allowing to naturally generalize CNNs to non-Euclidean domains and inherit the excellent natures of CNNs, such as local filters, parameter sharing, flexible receptive field, etc. Meanwhile, it leverages dynamically generated convolution kernel and cross-correlation operators to address the shortcomings of prior methods based on aggregation-transformation or their approximations. Our method has achieved or matched popular state-of-the-art results across three established graph benchmarks: the Cora, Citeseer, and Pubmed citation network datasets.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes