This work proposes a counterfactual multi-view framework to explicitly learn a structure masker for extracting consensus subgraphs and proposes a history-aware adaptive multi-channel aggregation mechanism to enable dynamic and personalized sharing driven by channel similarity while preventing collaborative oscillation.
This work proposes a FedIGL framework based on invariant learning, which effectively disrupts spurious correlations and further mines the invariant factors across different distributions, and proposes a novel Bi-Gradient Regularization strategy that introduces gradient constraints to guide the model in identifying client-agnostic and client-specific subgraph patterns for better graph representations.
Lingren Wang, Wenxuan Tu, Jiaxin Wang et al.· Neural Information Processin...· 2 citations
FedDUA is proposed, a novel disagreement-aware and uncertainty-guided framework for subgraph FL that first models cross-client semantic disagreement via a lightweight semantic anchor graph and derives adaptive aggregation weights for reliable global federated knowledge.
Keao Xi, Nannan Wu, Yiming Zhao et al.· Proceedings of the 32nd ACM...· 0 citations
Cross-domain collaborative filtering effectively alleviates the data sparsity issue but raises serious privacy concerns. Federated learning has been integrated into cross-domain collaborative filtering to reduce these risks by securely exchanging embeddings or model parameters. However, the current federated paradigm often relies on the simple alignment of coarse-grained representations, while propagating information on a rigid local graph. Without fine-grained preference modeling, models easily suffer from representation collapse. The inherent sparsity of local graphs further limits their robustness. To address these issues, we propose P2P-IAGR, a privacy-preserving peer-to-peer cross-domain collaborative filtering framework based on intent-adaptive graph reconstruction. Specifically, our framework first disentangles user and item representations into fine-grained latent intent prototypes. We perturb these prototypes using Local Differential Privacy (LDP) and securely exchange them across domains. A contrastive learning strategy is then used for cross-domain alignment. Next, guided by the combined cross-domain intent prior, P2P-IAGR differentiably reconstructs an augmented graph view. We apply a dual-view structural contrastive learning objective to dynamically inject external collaborative signals into the sparse local topology. Extensive experiments on real-world datasets show that P2P-IAGR significantly outperforms state-of-the-art methods, achieving an average improvement of 5.85% in NDCG and 6.89% in HR.
Munan Li, Hao Zhang, Jialong Li et al.· Electronics· 0 citations
Cross-domain recommendation (CDR) transfers preference knowledge across related domains, but federated deployment makes cross-domain alignment difficult because the behavioral anchors that align item spaces, such as overlapping users and shared interaction signals, are often sparse, unavailable, or privacy-sensitive across clients. To address this tension, we revisit federated CDR as generation over a stable semantic item language. By representing items as discrete semantic ID (SID) sequences derived from public item-side metadata, cross-domain item alignment is induced by a shared vocabulary rather than by exchanging private interactions or aligning domain-specific embeddings. Directly federating SID-based generators, however, introduces two design constraints: the SID tokenizer must remain fixed to preserve cross-client token consistency, which creates a semantic-only bottleneck because local collaborative filtering (CF) signals cannot be globally shared or aligned; meanwhile, standard federated averaging can cause negative transfer under domain heterogeneity. To overcome these constraints, we propose FedCGR, a federated generative CDR framework that keeps the item language stable and makes adaptation explicit. FedCGR injects local CF evidence through a reliability-aware semantic interface and trains a prototype-personalized generator that selectively aggregates shared parameters according to domain relatedness while keeping domain-specific quantities local. Experiments on six Amazon cross-domain scenarios show that FedCGR consistently outperforms federated generative baselines and achieves competitive performance against strong sequential and federated CDR methods under both full-ranking and sampled evaluation protocols.
Zhuodong Liu, Hugen Lv, Xiangyu Li et al.· 0 citations
HGAT-Rec is proposed, which incorporates a heterogeneity-aware contrastive learning (HCL) objective that grounds view construction and sample selection in the typed relational structure of a cross-domain heterogeneous graph: type-stratified edge dropout preserves high-signal interaction channels proportionally to their attention weight.
Rui Zhang, YaTing Zhao, FengBo Wang et al.· Journal of King Saud Univers...· 0 citations
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.
Zekai Chen, Haodong Lu, Shihao Li et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
