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

• URL: http://arxiv.org/abs/2511.00097v1
• Date: Thu, 30 Oct 2025 13:14:51 GMT
• Title: 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 summary: Graph domain-incremental learning (Domain-IL) aims at updating models across multiple graph domains.<n>We propose GraphKeeper to address catastrophic forgetting in Domain-IL scenario.<n>We show GraphKeeper achieves 6.5%16.6% improvement over the runner-up with negligible forgetting.
• Score: 39.188993605319276
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Towards Unsupervised Open-Set Graph Domain Adaptation via Dual Reprogramming [38.28291648575204]
  We investigate the problem of unsupervised open-set graph domain adaptation.<n>We propose a novel framework called GraphRTA, which conducts reprogramming on both the graph and model sides.<n>Our proposed model can achieve satisfied performance compared with recent state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-10-21T07:34:58Z)
• Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning [40.56379624114316]
  We propose a novel multi-domain pre-training and cross-domain transfer framework, namely MDGCL.<n>In the pre-training stage, we design a contrastive learning strategy to substantially recognize and capture domain differences.<n>In the downstream stage, we introduce a domain attention mechanism to enable fine-grained domain knowledge transfer.
  arXiv  Detail & Related papers  (2025-06-26T03:14:50Z)
• GCAL: Adapting Graph Models to Evolving Domain Shifts [24.035518818536445]
  This paper introduces the Graph Continual Adaptive Learning (GCAL) method, designed to enhance model sustainability and adaptability across various graph domains.<n>The "adapt" phase uses an information approach to fine-tune the model with new graph domains while re-adapting past memories to forgetting.<n>The "generate memory" phase, guided by a theoretical lower bound derived from information bottleneck theory, involves a variational memory graph generation module to condense original graphs into memories.
  arXiv  Detail & Related papers  (2025-05-22T16:19:19Z)
• GraphBridge: Towards Arbitrary Transfer Learning in GNNs [65.01790632978962]
  GraphBridge is a novel framework to enable knowledge transfer across disparate tasks and domains in GNNs.<n>It allows for the augmentation of any pre-trained GNN with prediction heads and a bridging network that connects the input to the output layer.<n> Empirical validation, conducted over 16 datasets representative of these scenarios, confirms the framework's capacity for task- and domain-agnostic transfer learning.
  arXiv  Detail & Related papers  (2025-02-26T15:57:51Z)
• Gradual Domain Adaptation for Graph Learning [15.648578809740414]
  We present a graph gradual domain adaptation (GGDA) framework, which constructs a compact domain sequence that minimizes information loss during adaptation.<n>Our framework provides implementable upper and lower bounds for the intractable inter-domain Wasserstein distance, $W_p(mu_t,mu_t+1)$, enabling its flexible adjustment for optimal domain formation.
  arXiv  Detail & Related papers  (2025-01-29T06:48:59Z)
• Revisiting Graph Neural Networks on Graph-level Tasks: Comprehensive Experiments, Analysis, and Improvements [54.006506479865344]
  We propose a unified evaluation framework for graph-level Graph Neural Networks (GNNs)<n>This framework provides a standardized setting to evaluate GNNs across diverse datasets.<n>We also propose a novel GNN model with enhanced expressivity and generalization capabilities.
  arXiv  Detail & Related papers  (2025-01-01T08:48:53Z)
• One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs [59.7297608804716]
  Graph Neural Networks (GNNs) have emerged as a powerful tool to capture intricate network patterns.<n>Existing GNNs require careful domain-specific architecture designs and training from scratch on each dataset.<n>We propose a novel cross-domain pretraining framework, "one model for one graph"
  arXiv  Detail & Related papers  (2024-11-30T01:49:45Z)
• Text-Free Multi-domain Graph Pre-training: Toward Graph Foundation Models [33.2696184519275]
  We propose MDGPT, a text free Multi-Domain Graph Pre-Training and adaptation framework. First, we propose a set of domain tokens to align features across source domains for synergistic pre-training. Second, we propose a dual prompts, consisting of a unifying prompt and a mixing prompt, to further adapt the target domain with unified multi-domain knowledge.
  arXiv  Detail & Related papers  (2024-05-22T19:06:39Z)
• Augmenting Knowledge Transfer across Graphs [16.50013525404218]
  We present TRANSNET, a generic learning framework for augmenting knowledge transfer across graphs. In particular, we introduce a novel notion named trinity signal that can naturally formulate various graph signals at different granularity. We show that TRANSNET outperforms all existing approaches on seven benchmark datasets by a significant margin.
  arXiv  Detail & Related papers  (2022-12-09T08:46:02Z)
• Source Free Unsupervised Graph Domain Adaptation [60.901775859601685]
  Unsupervised Graph Domain Adaptation (UGDA) shows its practical value of reducing the labeling cost for node classification. Most existing UGDA methods heavily rely on the labeled graph in the source domain. In some real-world scenarios, the source graph is inaccessible because of privacy issues. We propose a novel scenario named Source Free Unsupervised Graph Domain Adaptation (SFUGDA)
  arXiv  Detail & Related papers  (2021-12-02T03:18:18Z)
• GraphMI: Extracting Private Graph Data from Graph Neural Networks [59.05178231559796]
  We present textbfGraph textbfModel textbfInversion attack (GraphMI), which aims to extract private graph data of the training graph by inverting GNN. Specifically, we propose a projected gradient module to tackle the discreteness of graph edges while preserving the sparsity and smoothness of graph features. We design a graph auto-encoder module to efficiently exploit graph topology, node attributes, and target model parameters for edge inference.
  arXiv  Detail & Related papers  (2021-06-05T07:07:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.