同一张图上节点分类和链接预测怎么互相迁移？这篇用 GCN/GraphSAGE/GPS 跑出规律，还给了 CTS 分数避免负迁移。
论文提出一套无泄漏的 NC→LP 同图跨任务迁移协议，固定节点和边划分，并用排除被评估边的共享消息传递图配合固定负样本。在 GCN、GraphSAGE、GPS 三种主干上，实验显示迁移方向性很强：同质图上 NC→LP 稳定有益，而 LP→NC 在朴素表征复用时可能降低精度。LP→NC 主要只有在结构主导（LP 容易、NC 未饱和）时正向，说明 LP 相当于结构预训练。最后，论文提出 CoTask Score（CTS）来综合衡量共享编码器的 NC+LP 联合效用，并发现同质性等统计量可指导选择、避免负迁移。
Same Graph Cross-Task Transfer in GNNs: Protocols and Predictors
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.