arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2407.09173cs.LG
收藏

共形归纳图神经网络

Conformal Inductive Graph Neural Networks

CISPA Helmholtz Center for Information Security(CISPA亥姆霍兹信息安全中心);University of Cologne(科隆大学)

Soroush H. Zargarbashi, Aleksandar Bojchevski

AI总结:

针对传统共形预测因消息传递导致校准分数偏移、无法用于归纳式图节点分类的问题,提出适配节点/边可交换图的方法,在保障统计效率的同时恢复标准覆盖保证,且保证与预测时间无关。

摘要:

共形预测(CP)可将任意模型的输出转换为预测集,保证包含(覆盖)真实标签。CP需要可交换性(i.i.d.假设的一种松弛形式)来获得有效的无分布覆盖保证,这使其可直接应用于直推式节点分类。但传统CP无法应用于归纳场景,因为新节点参与消息传递会导致(校准)分数出现隐式偏移。我们针对节点可交换和边可交换的两类图解决了该问题,在不损失统计效率的前提下恢复了标准覆盖保证。我们进一步证明,该保证与预测时间无关,例如在新节点/边到达时或后续任意时刻均成立。

英文摘要:

Conformal prediction (CP) transforms any model's output into prediction sets guaranteed to include (cover) the true label. CP requires exchangeability, a relaxation of the i.i.d. assumption, to obtain a valid distribution-free coverage guarantee. This makes it directly applicable to transductive node-classification. However, conventional CP cannot be applied in inductive settings due to the implicit shift in the (calibration) scores caused by message passing with the new nodes. We fix this issue for both cases of node and edge-exchangeable graphs, recovering the standard coverage guarantee without sacrificing statistical efficiency. We further prove that the guarantee holds independently of the prediction time, e.g. upon arrival of a new node/edge or at any subsequent moment.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑