LGAIDSNEMLMar 25, 2022

SpeqNets: Sparsity-aware Permutation-equivariant Graph Networks

arXiv:2203.13913v348 citationsh-index: 24
Originality Incremental advance
AI Analysis

This addresses a key bottleneck in graph machine learning for applications requiring scalable and expressive models, though it is incremental in refining existing higher-order approaches.

The paper tackles the trade-off between expressivity and scalability in graph neural networks by introducing SpeqNets, a class of permutation-equivariant networks that adapt to graph sparsity, resulting in vastly reduced computation times and significant improvements in predictive performance over standard methods.

While (message-passing) graph neural networks have clear limitations in approximating permutation-equivariant functions over graphs or general relational data, more expressive, higher-order graph neural networks do not scale to large graphs. They either operate on $k$-order tensors or consider all $k$-node subgraphs, implying an exponential dependence on $k$ in memory requirements, and do not adapt to the sparsity of the graph. By introducing new heuristics for the graph isomorphism problem, we devise a class of universal, permutation-equivariant graph networks, which, unlike previous architectures, offer a fine-grained control between expressivity and scalability and adapt to the sparsity of the graph. These architectures lead to vastly reduced computation times compared to standard higher-order graph networks in the supervised node- and graph-level classification and regression regime while significantly improving over standard graph neural network and graph kernel architectures in terms of predictive performance.

Code Implementations1 repo
Foundations

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

Your Notes