用跨层注意力提升多层网络链接预测性能
Mind the Links: Cross-Layer Attention for Link Prediction in Multiplex Networks
- 将多层图链接预测转为多视图边分类，用跨层自注意力融合各层证据
- 在6个公开数据集上，宏F1提升显著，优于MELL、HOPLP-MUL等强基线
- 模型轻量可扩展，支持预计算嵌入和GNN编码器，适合实际应用
多层图能刻画共享节点间的多样化关系。现有方法或简单合并层，或独立处理每层，忽略关键的层间依赖且难以扩展。本文将多层链接预测建模为多视图边分类任务：对每对节点构建各层的边视图，利用跨层自注意力融合目标层的判别证据。提出两种模型实例：Trans-SLE（基于静态嵌入的轻量Transformer）和Trans-GAT（结合层特定GAT编码器与Transformer融合）。为保证可扩展性与公平性，引入联合候选池及两种无泄漏协议：跨层与归纳子图泛化。在六个公开多层数据集上的实验显示，本方法在宏F1上持续优于强基线（如MELL、HOPLP-MUL、RMNE），且方法简洁、可扩展，兼容预计算嵌入与GNN编码器。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。