Mind the Links: Cross-Layer Attention for Link Prediction in Multiplex Networks
This addresses the problem of capturing inter-layer dependencies in multiplex networks for researchers and practitioners, representing an incremental improvement over existing methods.
The paper tackles link prediction in multiplex networks by framing it as multi-view edge classification and using cross-layer self-attention to fuse evidence across layers, achieving consistent macro-F1 gains over strong baselines on six public datasets.
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.