1 minute read

我们有 1 篇论文被 NeurIPS 2025 收录！该研究聚焦图领域增量学习（Domain-IL）这一方向 —— 随着图基础模型（GFMs）的发展，该方向至关重要但尚未被充分探索，旨在解决跨域序列学习场景中，由嵌入偏移和决策边界偏差引发的灾难性遗忘问题。各论文的详细信息如下。

GraphKeeper: Graph Domain-Incremental Learning via Knowledge Disentanglement and Preservation

Authors: Zihao Guo, Qingyun Sun, Ziwei Zhang, Haonan Yuan, Huiping Zhuang, Xingcheng Fu, Jianxin Li

Abstract:

Graph incremental learning (GIL), which continuously updates graph models by sequential knowledge acquisition, has garnered significant interest recently. However, existing GIL approaches focus on task-incremental and class-incremental scenarios within a single domain. Graph domain-incremental learning (Domain-IL), aiming at updating models across multiple graph domains, has become critical with the development of graph foundation models (GFMs), but remains unexplored in the literature. In this paper, we propose Graph Domain-Incremental Learning via Knowledge Dientanglement and Preservation (GraphKeeper), to address catastrophic forgetting in Domain-IL scenario from the perspectives of embedding shifts and decision boundary deviations. Specifically, to prevent embedding shifts and confusion across incremental graph domains, we first propose the domain-specific parameter-efficient fine-tuning together with intra- and inter-domain disentanglement objectives. Consequently, to maintain a stable decision boundary, we introduce deviation-free knowledge preservation to continuously fit incremental domains. Additionally, for graphs with unobservable domains, we perform domain-aware distribution discrimination to obtain precise embeddings. Extensive experiments demonstrate the proposed GraphKeeper achieves state-of-the-art results with 6.5%~16.6% improvement over the runner-up with negligible forgetting. Moreover, we show GraphKeeper can be seamlessly integrated with various representative GFMs, highlighting its broad applicative potential.

Paradigm of proposed analytic continual learning

The overall framework of GraphKeeper

Paper: https://arxiv.org/abs/2511.00097

Code: https://github.com/RingBDStack/GraphKeeper

Updated:

You may also enjoy

We have 3 papers accepted by ICLR 2026!

3 minute read

We have three papers accepted by ICLR 2026! One paper advances federated learning with a novel analytic deep framework that tackles data heterogeneity and ef...

We have 2 papers accepted by AAAI 2026!

2 minute read

We have two papers accepted by AAAI 2026 ! One oral paper contributes to the field of continual learning, addressing the storage burden and data privacy conc...

We have 1 paper accepted by NeurIPS 2025 !

1 minute read

We have 1 paper accepted by NeurIPS 2025! This work focuses on graph domain-incremental learning (Domain-IL), a critical yet unexplored setting amid the deve...