SIGN: Scalable Inception Graph Neural Networks

By Emanuele Rossi, Fabrizio Frasca, Benjamin Paul Chamberlain, Davide Eynard, Michael M. Bronstein, Federico Monti. arXiv.org, 2020

475 citations recorded by the source corpus.

Graph representation learning has recently been applied to a broad spectrum of problems ranging from computer graphics and chemistry to high energy physics and social media. The popularity of graph neural networks has sparked interest, both in academia and in industry, in developing methods that scale to very large graphs such as Facebook or Twitter social networks. In most of these approaches, the computational cost is alleviated by a sampling strategy retaining a subset of node neighbors or subgraphs at training time. In this paper we propose a new, efficient and scalable graph deep learning architecture which sidesteps the need for graph sampling by using graph convolutional filters of different size that are amenable to efficient precomputation, allowing extremely fast training and inference. Our architecture allows using different local graph operators (e.g. motif-induced adjacency matrices or Personalized Page Rank diffusion matrix) to best suit the task at hand. We conduct extensive experimental evaluation on various open benchmarks and show that our approach is competitive with other state-of-the-art architectures, while requiring a fraction of the training and inference time.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/de7ac74b8388d7b5893478b479633af4ed4f97f8

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs (2021, methodology): “29 SGC 0.7M 65.82 65.29 SIGN 3.8M 66.64 66.09 MLP+C&S 0.5M 66.98 66.18 GRAPHSAGE (NS) 4.9M 66.79 66.28 GAT (NS) 4.9M 67.15 66.80 R-GRAPHSAGE (NS) 12.2M 69.86 68.94 R-GAT (NS) 12.3M 70.02 69.42 KDD 1ST: BD-PGL 75.49 KDD 2ND: ACADEMIC 75.19 KDD 3RD: SYNERISE AI 74.60 Table 3: Analysis of graph homophi”
HittER: Hierarchical Transformers for Knowledge Graph Embeddings (2020, methodology): “ The dashed box indicates a simple context-independent baseline where M e src is directly used for link prediction. tions (Zhao and Akoglu,2020;Zhou et al.,2020) and efﬁciency issues when scaling up (Rossi et al., 2020), so they are usually restricted in expressiveness and cannot easily scale to lar”
ETA Prediction with Graph Neural Networks in Google Maps (2021, unknown): “As graph neural network methodologies became more widely available and scalable [4, 9, 21], this also enabled a wider range of web-scale applications of graph representation learning.”
Benchmarking Graph Neural Networks (2023, background): “very large graph datasets also present a computational challenge and require extensive GPU resources to be studied (Chiang et al., 2019; Rossi et al., 2020; Hu et al., 2021).”
Combining Label Propagation and Simple Models Out-performs Graph Neural Networks (2020, methodology): “Our framework also complements the Simpliﬁed Graph Convolution (Wu et al., 2019), as well as algorithms designed to increase scalability (Bojchevski et al., 2020; Zeng et al., 2019; Rossi et al., 2020).”
Training Graph Neural Networks with 1000 Layers (2021, methodology): “, 2019) and SIGN (Frasca et al., 2020) on ogbn-products.”
Graph Neural Networks in Recommender Systems: A Survey (2020, background): “Another mainstream to solve this problem is to decouple the operations of nonlinearities and collapsing weight matrices between consecutive layers [38, 54, 167].”