GNNs Meet Sequence Models Along the Shortest-Path: an Expressive Method for Link Prediction

TL;DR

SP4LP introduces a novel framework combining GNNs with sequence models over shortest paths, significantly improving link prediction by capturing multi-hop structural patterns efficiently.

Contribution

It proposes a new method that integrates GNN node encodings with sequence modeling on shortest paths, enhancing expressiveness and efficiency for link prediction.

Findings

Achieves state-of-the-art results on link prediction benchmarks.

Proves SP4LP is more expressive than standard GNNs and structural heuristics.

Demonstrates computational efficiency in capturing multi-hop patterns.

Abstract

Graph Neural Networks (GNNs) often struggle to capture the link-specific structural patterns crucial for accurate link prediction, as their node-centric message-passing schemes overlook the subgraph structures connecting a pair of nodes. Existing methods to inject such structural context either incur high computational cost or rely on simplistic heuristics (e.g., common neighbor counts) that fail to model multi-hop dependencies. We introduce SP4LP (Shortest Path for Link Prediction), a novel framework that combines GNN-based node encodings with sequence modeling over shortest paths. Specifically, SP4LP first applies a GNN to compute representations for all nodes, then extracts the shortest path between each candidate node pair and processes the resulting sequence of node embeddings using a sequence model. This design enables SP4LP to capture expressive multi-hop relational patterns with computational efficiency. Empirically, SP4LP achieves state-of-the-art performance across link prediction benchmarks. Theoretically, we prove that SP4LP is strictly more expressive than standard message-passing GNNs and several state-of-the-art structural features methods, establishing it as a general and principled approach for link prediction in graphs.