arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.19907cs.LGcs.AI
收藏

超越已知:面向开放世界图学习的新类发现

Beyond the Known: Novel Class Discovery for Open-world Graph Learning

Fudan University(复旦大学);Tianjin University(天津大学);University of Edinburgh(爱丁堡大学);University of Illinois at Chicago(伊利诺伊大学芝加哥分校)

Yucheng Jin, Yun Xiong, Juncheng Fang, Xixi Wu, Dongxiao He, Xing Jia, Bingchen Zhao, Philip Yu

AI总结:

本文提出开放世界图神经网络ORAL,通过半监督原型学习、原型注意力网络消除类间相关性,并利用多尺度特征对齐集成生成伪标签,以解决图上新类发现问题。

摘要:

图上的节点分类在许多应用中具有重要意义。由于现实开放场景中标注能力有限且数据不断演化,未标注的测试节点上可能出现新类。然而,图上新类发现的研究很少受到关注。发现新类具有挑战性,因为新类节点与已知类节点通过边相关联,这使得在应用消息传递图神经网络时它们的表示难以区分。此外,新类缺乏标注信息来指导学习过程。本文提出了一种新方法——开放世界图神经网络(ORAL)来应对这些挑战。ORAL首先通过半监督原型学习检测类之间的相关性。随后,通过原型注意力网络消除类间相关性,从而为不同类获得具有区分性的表示。此外,为了充分探索多尺度图特征以缓解标签不足问题,ORAL通过对多个堆叠的原型注意力网络的标签估计进行对齐和集成来生成伪标签。在多个基准数据集上的大量实验证明了所提方法的有效性。

英文摘要:

Node classification on graphs is of great importance in many applications. Due to the limited labeling capability and evolution in real-world open scenarios, novel classes can emerge on unlabeled testing nodes. However, little attention has been paid to novel class discovery on graphs. Discovering novel classes is challenging as novel and known class nodes are correlated by edges, which makes their representations indistinguishable when applying message passing GNNs. Furthermore, the novel classes lack labeling information to guide the learning process. In this paper, we propose a novel method Open-world gRAph neuraL network (ORAL) to tackle these challenges. ORAL first detects correlations between classes through semi-supervised prototypical learning. Inter-class correlations are subsequently eliminated by the prototypical attention network, leading to distinctive representations for different classes. Furthermore, to fully explore multi-scale graph features for alleviating label deficiencies, ORAL generates pseudo-labels by aligning and ensembling label estimations from multiple stacked prototypical attention networks. Extensive experiments on several benchmark datasets show the effectiveness of our proposed method.

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。

↑