FedOGL: Combating Catastrophic Forgetting in Federated Open-World Multimodal Graph Learning

• URL: http://arxiv.org/abs/2607.27665v1
• Date: Thu, 30 Jul 2026 04:24:41 GMT
• Title: FedOGL: Combating Catastrophic Forgetting in Federated Open-World Multimodal Graph Learning
• Abstract summary: Federated graph learning enables collaborative training over decentralized graph data without sharing raw graph information.<n>Clients must learn emerging classes from private multimodal graph streams while preserving historical categories and rejecting samples outside the current known class space.<n>We propose textbfFedOGL, a semantic-structural memory preservation framework.
• Score: 26.774513573509108
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Federated graph learning enables collaborative training over decentralized graph data without sharing raw graph information. As such risks evolve, clients must learn emerging classes from private multimodal graph streams, retain historical categories, and reject samples outside the known class space. In this setting, clients must learn emerging classes from private multimodal graph streams while preserving historical categories and rejecting samples outside the current known class space. The core challenge is catastrophic forgetting, which in federated multimodal graphs is not merely a classifier-level failure: old knowledge can be erased through modality-semantic overwriting, topology-induced structural erosion, and federated memory fragmentation. To address this challenge, we propose \textbf{FedOGL}, a semantic-structural memory preservation framework. On the client side, FedOGL preserves historical decision behavior through replay and task-start distillation, while protecting graph-propagation memory via projection onto a globally shared structure basis. On the server side, FedOGL maintains and transfers compact category prototypes to facilitate cross-client knowledge sharing without exposing raw graph data. Extensive experiments demonstrate that, compared with the best-performing baselines, FedOGL reduces performance degradation caused by catastrophic forgetting by \textbf{42.67\%}, while maintaining or improving performance on downstream tasks.

Related papers

• FedLAB: Traceable Semantic Codebooks for Federated Multimodal Graph Foundation Learning [47.940785803361415]
  FedLAB is a traceable semantic codebook framework that organizes multimodal graph knowledge into typed codebooks for modality evidence, node semantics, and topology context.<n>Experiments show that FedLAB improves over state-of-the-art baselines by up to 7.53%, while preserving a native semantic trace interface.
  arXiv  Detail & Related papers  (2026-06-30T17:47:39Z)
• PRISM: Topology-Aware Cross-Modal Imputation for Modality-Deficient Federated Graph Learning [54.55726437469762]
  We propose textbfPRISM (textbfProactive textbfRetrieval and textbfImputation via textbfStructural textbfMeta-prompting), a topology-aware cross-modal imputation framework.<n>Experiments show PRISM consistently improves modality-deficient clients, outperforming state-of-the-art baselines by textbf4.48% on average.
  arXiv  Detail & Related papers  (2026-06-08T10:08:52Z)
• Towards Federated Clustering: A Client-wise Private Graph Aggregation Framework [57.04850867402913]
  Federated clustering addresses the challenge of extracting patterns from decentralized, unlabeled data.<n>We propose Structural Privacy-Preserving Federated Graph Clustering (SPP-FGC), a novel algorithm that innovatively leverages local structural graphs as the primary medium for privacy-preserving knowledge sharing.<n>Our framework achieves state-of-the-art performance, improving clustering accuracy by up to 10% (NMI) over federated baselines while maintaining provable privacy guarantees.
  arXiv  Detail & Related papers  (2025-11-14T03:05:22Z)
• Cooperative Pseudo Labeling for Unsupervised Federated Classification [62.9387841396335]
  Unsupervised Federated Learning (UFL) aims to collaboratively train a global model across distributed clients without sharing data or accessing label information.<n>We propose a novel method, underlinetextbfFederated underlinetextbfCooperative underlinetextbfPseudo underlinetextbfLabeling (textbfFedCoPL)<n>In particular, visual prompts containing general image features are aggregated at the server, while text prompts encoding personalized knowledge are retained locally.
  arXiv  Detail & Related papers  (2025-10-11T08:18:26Z)
• Curriculum Guided Personalized Subgraph Federated Learning [8.721619913104899]
  Subgraph Federated Learning (FL) aims to train Graph Neural Networks (GNNs) across distributed private subgraphs.<n> weighted model aggregation personalizes each local GNN by assigning larger weights to parameters from clients with similar subgraph characteristics.<n>We propose a novel personalized subgraph FL framework called Curriculum guided personalized sUbgraph Federated Learning (CUFL)
  arXiv  Detail & Related papers  (2025-08-30T08:01:36Z)
• GraphFedMIG: Tackling Class Imbalance in Federated Graph Learning via Mutual Information-Guided Generation [19.1700923188257]
  Federated graph learning (FGL) enables multiple clients to collaboratively train powerful graph neural networks without sharing their private, decentralized graph data.<n>We propose GraphFedMIG, a novel FGL framework that reframes the problem as a federated generative data augmentation task.<n>We conduct extensive experiments on four real-world datasets, and the results demonstrate the superiority of the proposed GraphFedMIG compared with other baselines.
  arXiv  Detail & Related papers  (2025-08-14T09:16:56Z)
• Rethinking Federated Graph Learning: A Data Condensation Perspective [4.044673636393338]
  Federated graph learning (FGL) promotes collaborative training of graph neural networks (GNNs) by multi-client graphs.<n>We introduce the concept of a condensed graph as a novel optimization carrier to address FGL data heterogeneity.<n>Specifically, we utilize a generalized condensation graph consensus to aggregate comprehensive knowledge from distributed graphs.
  arXiv  Detail & Related papers  (2025-05-05T11:23:29Z)
• A Pure Transformer Pretraining Framework on Text-attributed Graphs [50.833130854272774]
  We introduce a feature-centric pretraining perspective by treating graph structure as a prior. Our framework, Graph Sequence Pretraining with Transformer (GSPT), samples node contexts through random walks. GSPT can be easily adapted to both node classification and link prediction, demonstrating promising empirical success on various datasets.
  arXiv  Detail & Related papers  (2024-06-19T22:30:08Z)
• Federated Graph Condensation with Information Bottleneck Principles [44.404509071881364]
  We propose and study the novel problem of federated graph condensation (FGC) for graph neural networks (GNNs)<n>Under the federated setting, the condensed graph will consistently leak data membership privacy.<n>Our framework consistently protects membership privacy during training.
  arXiv  Detail & Related papers  (2024-05-07T00:08:15Z)
• Privacy-preserving design of graph neural networks with applications to vertical federated learning [56.74455367682945]
  We present an end-to-end graph representation learning framework called VESPER. VESPER is capable of training high-performance GNN models over both sparse and dense graphs under reasonable privacy budgets.
  arXiv  Detail & Related papers  (2023-10-31T15:34:59Z)
• Federated Graph-based Networks with Shared Embedding [1.323497585762675]
  We propose Federated Graph-based Networks with Shared Embedding (Feras), which uses shared embedding data to train the network and avoids the direct sharing of original data. Feras enables the training of current graph-based models in the federated learning framework for privacy concern.
  arXiv  Detail & Related papers  (2022-10-03T12:51:15Z)
• Towards Unsupervised Deep Graph Structure Learning [67.58720734177325]
  We propose an unsupervised graph structure learning paradigm, where the learned graph topology is optimized by data itself without any external guidance. Specifically, we generate a learning target from the original data as an "anchor graph", and use a contrastive loss to maximize the agreement between the anchor graph and the learned graph.
  arXiv  Detail & Related papers  (2022-01-17T11:57:29Z)

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.