AI 中文总结
该研究针对GNN同图跨任务迁移的评估缺陷，提出无泄漏协议，发现迁移方向性规律，引入CTS指标，表明数据集同质性可指导机制选择以避免负迁移。
AI 中文摘要
许多真实图在同一底层结构上支持多个预测任务，为节点分类（NC）和链接预测（LP）之间复用监督信号创造了机会。但现有评估常依赖不兼容的划分、观测图假设及负采样规则，导致同图跨任务迁移的结论不可靠。我们将同图NC-LP迁移形式化，提出无泄漏协议，该协议固定节点和边划分，使用排除待评估边的共享消息传递图，并为LP采用固定负样本。在GCN、GraphSAGE、GPS三种骨干网络上，我们发现迁移具有强方向性且可预测：同质性图上NC→LP始终有益，而LP→NC脆弱，在朴素表示复用下甚至会降低准确率；LP→NC可靠为正主要出现在结构主导 regime，此时LP易完成但NC未饱和，表明LP可作为结构预训练。最后，我们引入CoTask Score（CTS），用于在共享编码器需同时服务两个任务时总结NC+LP的联合效用，结果显示简单的数据集统计量（尤其是同质性）可指导机制选择，帮助避免负迁移。
英文摘要
Many real-world graphs support multiple predictive tasks over the same underlying structure, creating an opportunity to reuse supervision across node classification (NC) and link prediction (LP). However, existing evaluations often rely on incompatible splits, observed-graph assumptions, and negative sampling rules, making conclusions about same-graph cross-task transfer unreliable. We formalize same-graph NC-LP transfer and propose a leakage-free protocol that fixes node and edge splits, uses a shared message-passing graph that excludes evaluated edges, and employs fixed negatives for LP. Across three backbones (GCN, GraphSAGE, GPS), we find that transfer is strongly directional and predictable: NC $\to$ LP is consistently beneficial on homophilic graphs, while LP $\to$ NC is fragile and can even degrade accuracy under naive representation reuse. LP $\to$ NC becomes reliably positive mainly in a structure-dominant regime where LP is easy but NC is unsaturated, suggesting that LP acts as structural pretraining. Finally, we introduce the CoTask Score (CTS) to summarize joint NC+LP utility when a shared encoder must serve both tasks, and show that simple dataset statistics, especially homophily, can guide mechanism choice and help avoid negative transfer.
Comments17 pages, 2 figures
Journal refICML 2026
