pith. sign in

arxiv: 1902.07153 · v2 · pith:J5XCPH4Rnew · submitted 2019-02-19 · 💻 cs.LG · stat.ML

Simplifying Graph Convolutional Networks

classification 💻 cs.LG stat.ML
keywords graphcomplexityconvolutionalgcnslearninglinearmodelnetworks
0
0 comments X
read the original abstract

Graph Convolutional Networks (GCNs) and their variants have experienced significant attention and have become the de facto methods for learning graph representations. GCNs derive inspiration primarily from recent deep learning approaches, and as a result, may inherit unnecessary complexity and redundant computation. In this paper, we reduce this excess complexity through successively removing nonlinearities and collapsing weight matrices between consecutive layers. We theoretically analyze the resulting linear model and show that it corresponds to a fixed low-pass filter followed by a linear classifier. Notably, our experimental evaluation demonstrates that these simplifications do not negatively impact accuracy in many downstream applications. Moreover, the resulting model scales to larger datasets, is naturally interpretable, and yields up to two orders of magnitude speedup over FastGCN.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Fast Graph Representation Learning with PyTorch Geometric

    cs.LG 2019-03 accept novelty 7.0

    PyTorch Geometric is a PyTorch library that delivers fast graph neural network training through sparse GPU kernels and variable-size mini-batching.

  2. Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks

    cs.LG 2019-09 unverdicted novelty 6.0

    DGL is a graph-centric library that optimizes GNNs via generalized sparse tensor operations, transparent graph-based optimizations, and framework-neutral design, claiming superior speed and memory use over other GNN f...

  3. Graph Star Net for Generalized Multi-Task Learning

    cs.SI 2019-06 unverdicted novelty 6.0

    GraphStar is a new GNN that adds star nodes and relay attention to achieve non-local representations for node, graph, and link tasks, claiming 2-5% gains over prior SOTA on benchmarks.

  4. Quantum Machine Learning in Drug Discovery: Applications in Academia and Pharmaceutical Industries

    quant-ph 2024-09 unverdicted novelty 2.0

    Review of quantum neural networks on gate-based quantum computers for molecular property prediction and generation in drug discovery.