根据下游任务动态选择更新节点，高效利用有限资源提升图学习效果
Budgeted Task-Aware Acquisition of Dynamic Networks
- 通过学习节点查询的任务价值，智能决定更新哪些过时信息
- 在21个设置中19次表现最佳，链接预测AUC提升0.012-0.016
- 适合资源受限下需精准更新图结构的图神经网络应用
动态图学习在底层网络变化仅部分可观测时面临挑战。获取当前图信息需付出观测与计算成本，资源有限下完全更新不现实。本文聚焦预算约束下的任务感知图信息获取，研究模型如何决策刷新哪些过时信息以完成下游任务。提出Scout框架，通过维护图状态与观测历史，轻量级学习每个节点查询的任务价值。评估涵盖一个合成数据集和四个真实动态网络、两项下游任务、九种采集基线及多个查询预算。Scout在21个基准-预算设置中19次达到最高平均性能；任务效用监督在16个真实场景中13次优于结构变化监督。同一网络上，任务匹配采集使链接预测AUC提升0.012–0.016，节点分类准确率提升0.064–0.09，远超任务不匹配采集。结果表明，有效观测依赖下游任务，直接从任务效用学习可更优分配有限观测预算。
原文摘要 · Abstract (English)
Learning on dynamic graphs is difficult when changes in the underlying network are only partially observed. Acquiring current graph information incurs observation and computational costs, making complete updates impractical under limited resources. This paper focuses on budgeted task-aware acquisition on dynamic networks, where a model needs to decide which stale graph information to refresh for a downstream task. We propose Scout, a lightweight framework that learns the task value of querying each node from the maintained graph and observation history. Our evaluation covers one synthetic and four real-world dynamic networks, two downstream tasks, nine acquisition baselines, and several query budgets. Scout achieves the highest mean downstream performance in 19 of the 21 benchmark-budget settings. Task-utility supervision also outperforms structural-change supervision in 13 of the 16 real-world settings. On the same dynamic network, task-matched acquisition improves link-prediction AUC by 0.012-0.016 and node-classification accuracy by 0.064-0.09 over task-mismatched acquisition. These results show that useful graph observations depend on the downstream task and that limited observation budgets can be allocated more effectively by learning directly from downstream utility.
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。