{"ID":2864799,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.23409","arxiv_id":"2509.23409","title":"Mind the Links: Cross-Layer Attention for Link Prediction in Multiplex Networks","abstract":"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.","short_abstract":"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 co...","url_abs":"https://arxiv.org/abs/2509.23409","url_pdf":"https://arxiv.org/pdf/2509.23409v1","authors":"[\"Devesh Sharma\",\"Aditya Kishore\",\"Ayush Garg\",\"Debajyoti Mazumder\",\"Debasis Mohapatra\",\"Jasabanta Patro\"]","published":"2025-09-27T16:55:15Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[\"Transformer\",\"Graph Neural Network\"]","has_code":false}