Papers › metapath2vec: Scalable Representation Learning for Heterogeneous Networks
metapath2vec: Scalable Representation Learning for Heterogeneous Networks
Yuxiao Dong, Nitesh Vijay Chawla, Ananthram Swami
We study the problem of representation learning in heterogeneous networks. Its unique challenges come from the existence of multiple types of nodes and links, which limit the feasibility of the conventional network embedding techniques. We develop two scalable representation learning models, namely metapath2vec and metapath2vec++. The metapath2vec model formalizes meta-path-based random walks to construct the heterogeneous neighborhood of a node and then leverages a heterogeneous skip-gram model to perform node embeddings. The metapath2vec++ model further enables the simultaneous modeling of structural and semantic correlations in heterogeneous networks. Extensive experiments show that metapath2vec and metapath2vec++ are able to not only outperform state-of-the-art embedding models in various heterogeneous network mining tasks, such as node classification, clustering, and similarity search, but also discern the structural and semantic correlations between diverse network objects.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Link Prediction | MovieLens 25M | metapath2vec | Hits@10 | 0.7956 | #5 of 7 | Archive leaderboard | report |
| Link Prediction | MovieLens 25M | metapath2vec | nDCG@10 | 0.5051 | #5 of 7 | Archive leaderboard | report |
| Link Prediction | Yelp | Metapath2Vec | HR@10 | 0.6307 | #7 of 9 | Archive leaderboard | report |
| Link Prediction | Yelp | Metapath2Vec | nDCG@10 | 0.402 | #7 of 9 | Archive leaderboard | report |
| Node Property Prediction | ogbn-mag | MetaPath2vec | Ext. data | No | #36 of 39 | Archive leaderboard | report |
| Node Property Prediction | ogbn-mag | MetaPath2vec | Number of params | 94479069 | #36 of 39 | Archive leaderboard | report |
| Node Property Prediction | ogbn-mag | MetaPath2vec | Test Accuracy | 0.3544 ± 0.0036 | #36 of 39 | Archive leaderboard | report |
| Node Property Prediction | ogbn-mag | MetaPath2vec | Validation Accuracy | 0.3506 ± 0.0017 | #36 of 39 | 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: metapath2vec
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