# Mind the Links: Cross-Layer Attention for Link Prediction in Multiplex Networks

arXiv: https://arxiv.org/abs/2509.23409 · HTML: https://mlsanity.com/paper/2509.23409/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 24 references that are in the map.
- First posted on arXiv 27 Sep 2025.

## Builds on (most cited first, 6 of 6)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [Combinatorial Analysis of Multiple Networks](https://mlsanity.com/paper/1303.4986/) (2013)
- [Interlayer link prediction in multiplex social networks: an iterative degree penalty algorithm](https://mlsanity.com/paper/2002.02140/) (2020)
- [Link prediction in multiplex networks via triadic closure](https://mlsanity.com/paper/2011.09126/) (2020)

## Built on by (most cited first, 1 of 1)

- [MxGPS: Multiplex Graph Transformers for a Power Grid Foundation Model](https://mlsanity.com/paper/2607.13763/) (2026)

## Abstract (arXiv)

Multiplex graphs capture diverse relations among shared nodes. Most predictors either collapse layers or treat them independently. This loses crucial inter-layer dependencies and struggles with scalability. To overcome this, we frame multiplex link prediction as multi-view edge classification. For each node pair, we construct a sequence of per-layer edge views and apply cross-layer self-attention to fuse evidence for the target layer. We present two models as instances of this framework: Trans-SLE, a lightweight transformer over static embeddings, and Trans-GAT, which combines layer-specific GAT encoders with transformer fusion. To ensure scalability and fairness, we introduce a Union--Set candidate pool and two leakage-free protocols: cross-layer and inductive subgraph generalization. Experiments on six public multiplex datasets show consistent macro-F_1 gains over strong baselines (MELL, HOPLP-MUL, RMNE). Our approach is simple, scalable, and compatible with both precomputed embeddings and GNN encoders.