Guardado en:
Detalles Bibliográficos
Autores principales: Chen, Jiazhen, Ma, Zheng, Fu, Sichao, Feng, Mingbin, Wirjanto, Tony S., Ou, Weihua
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2507.17687
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911073118978048
author Chen, Jiazhen
Ma, Zheng
Fu, Sichao
Feng, Mingbin
Wirjanto, Tony S.
Ou, Weihua
author_facet Chen, Jiazhen
Ma, Zheng
Fu, Sichao
Feng, Mingbin
Wirjanto, Tony S.
Ou, Weihua
contents Graph class-incremental learning (GCIL) allows graph neural networks (GNNs) to adapt to evolving graph analytical tasks by incrementally learning new class knowledge while retaining knowledge of old classes. Existing GCIL methods primarily focus on a closed-set assumption, where all test samples are presumed to belong to previously known classes. Such an assumption restricts their applicability in real-world scenarios, where unknown classes naturally emerge during inference, and are absent during training. In this paper, we explore a more challenging open-set graph class-incremental learning scenario with two intertwined challenges: catastrophic forgetting of old classes, which impairs the detection of unknown classes, and inadequate open-set recognition, which destabilizes the retention of learned knowledge. To address the above problems, a novel OGCIL framework is proposed, which utilizes pseudo-sample embedding generation to effectively mitigate catastrophic forgetting and enable robust detection of unknown classes. To be specific, a prototypical conditional variational autoencoder is designed to synthesize node embeddings for old classes, enabling knowledge replay without storing raw graph data. To handle unknown classes, we employ a mixing-based strategy to generate out-of-distribution (OOD) samples from pseudo in-distribution and current node embeddings. A novel prototypical hypersphere classification loss is further proposed, which anchors in-distribution embeddings to their respective class prototypes, while repelling OOD embeddings away. Instead of assigning all unknown samples into one cluster, our proposed objective function explicitly models them as outliers through prototype-aware rejection regions, ensuring a robust open-set recognition. Extensive experiments on five benchmarks demonstrate the effectiveness of OGCIL over existing GCIL and open-set GNN methods.
format Preprint
id arxiv_https___arxiv_org_abs_2507_17687
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Effective Open-set Graph Class-incremental Learning
Chen, Jiazhen
Ma, Zheng
Fu, Sichao
Feng, Mingbin
Wirjanto, Tony S.
Ou, Weihua
Machine Learning
Graph class-incremental learning (GCIL) allows graph neural networks (GNNs) to adapt to evolving graph analytical tasks by incrementally learning new class knowledge while retaining knowledge of old classes. Existing GCIL methods primarily focus on a closed-set assumption, where all test samples are presumed to belong to previously known classes. Such an assumption restricts their applicability in real-world scenarios, where unknown classes naturally emerge during inference, and are absent during training. In this paper, we explore a more challenging open-set graph class-incremental learning scenario with two intertwined challenges: catastrophic forgetting of old classes, which impairs the detection of unknown classes, and inadequate open-set recognition, which destabilizes the retention of learned knowledge. To address the above problems, a novel OGCIL framework is proposed, which utilizes pseudo-sample embedding generation to effectively mitigate catastrophic forgetting and enable robust detection of unknown classes. To be specific, a prototypical conditional variational autoencoder is designed to synthesize node embeddings for old classes, enabling knowledge replay without storing raw graph data. To handle unknown classes, we employ a mixing-based strategy to generate out-of-distribution (OOD) samples from pseudo in-distribution and current node embeddings. A novel prototypical hypersphere classification loss is further proposed, which anchors in-distribution embeddings to their respective class prototypes, while repelling OOD embeddings away. Instead of assigning all unknown samples into one cluster, our proposed objective function explicitly models them as outliers through prototype-aware rejection regions, ensuring a robust open-set recognition. Extensive experiments on five benchmarks demonstrate the effectiveness of OGCIL over existing GCIL and open-set GNN methods.
title Towards Effective Open-set Graph Class-incremental Learning
topic Machine Learning
url https://arxiv.org/abs/2507.17687