Papers › Watch Your Step: Learning Node Embeddings via Graph Attention

Watch Your Step: Learning Node Embeddings via Graph Attention

26 Oct 2017NeurIPS 2018 12arXiv:1710.09599archive 2025-07-28

Sami Abu-El-Haija, Bryan Perozzi, Rami Al-Rfou, Alex Alemi

Graph embedding methods represent nodes in a continuous vector space, preserving information from the graph (e.g. by sampling random walks). There are many hyper-parameters to these methods (such as random walk length) which have to be manually tuned for every graph. In this paper, we replace random walk hyper-parameters with trainable parameters that we automatically learn via backpropagation. In particular, we learn a novel attention model on the power series of the transition matrix, which guides the random walk to optimize an upstream objective. Unlike previous approaches to attention models, the method that we propose utilizes attention parameters exclusively on the data (e.g. on the random walk), and not used by the model for inference. We experiment on link prediction tasks, as we aim to produce embeddings that best-preserve the graph structure, generalizing to unseen information. We improve state-of-the-art on a comprehensive suite of real world datasets including social, collaboration, and biological networks. Adding attention to random walks can reduce the error by 20% to 45% on datasets we attempted. Further, our learned attention parameters are different for every graph, and our automatically-found values agree with the optimal choice of hyper-parameter if we manually tune existing methods.

PaperPDFConference PDFCode

Code

benedekrozemberczki/AttentionWalk mentioned on GitHubpytorch report
karthik63/attention mentioned on GitHubtf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Graph AttentionGraph EmbeddingLink PredictionNode Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Node Classification Citeseer AttentionWalk Accuracy 51.5% #67 of 71 Archive leaderboard report
Node Classification Cora AttentionWalk Accuracy 67.9% #72 of 73 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: WYS

WYS

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections