Kdd 2026 Communication Efficient Federated Graph Classification Via Generative Diffusion Modeling

Pdf Communication Efficient Federated Graph Classification Via The core idea of cefgc is to leverage generative diffusion models to minimize direct client server communication. each client trains a generative diffusion model that captures its local graph distribution and shares this model with the server, which then redistributes it back to all clients. In this paper, we propose a globally consistent federated graph autoencoder (gcfgae) to overcome the non iid problem in unsupervised federated graph learning via three innovations.

Kdd 2026 Kdd 2026 Korea Kdd 2026 communication efficient federated graph classification via generative diffusion modeling association for computing machinery (acm) 48.3k subscribers subscribe. Cefgc tackles the dual challenges of communication overhead and non iid data in federated graph learning by introducing a three round fgnn framework that uses graph generative diffusion models (ggdms) to share synthetic data rather than frequent parameter updates. Graph neural networks (gnns) unlock new ways of learning from graph structured data, proving highly effective in capturing complex relationships and patterns. federated gnns (fgnns) have emerged as a prominent distributed learning paradigm for training gnns over decentralized data. The work introduces two major advancements: a three round communication framework and the integration of generative diffusion models to improve performance on non iid graphs.

Efficient And Degree Guided Graph Generation Via Discrete Diffusion Graph neural networks (gnns) unlock new ways of learning from graph structured data, proving highly effective in capturing complex relationships and patterns. federated gnns (fgnns) have emerged as a prominent distributed learning paradigm for training gnns over decentralized data. The work introduces two major advancements: a three round communication framework and the integration of generative diffusion models to improve performance on non iid graphs. Abstract graph neural networks (gnns) unlock new ways of learning from graph structured data, proving highly effective in capturing com plex relationships and patterns. federated gnns (fgnns) have emerged as a prominent distributed learning paradigm for train ing gnns over decentralized data. Our papers “‘adversarial signed graph learning with differential privacy” and “communication efficient federated graph classification via generative diffusion modeling” are accepted by sigkdd conference on knowledge discovery and data mining (kdd), 2026. Communication efficient federated graph classification via generative diffusion modeling, in proceedings of acm sigkdd conference on knowledge discovery and data mining (kdd),.

Communication Efficient Federated Learning And Permissioned Blockchain Abstract graph neural networks (gnns) unlock new ways of learning from graph structured data, proving highly effective in capturing com plex relationships and patterns. federated gnns (fgnns) have emerged as a prominent distributed learning paradigm for train ing gnns over decentralized data. Our papers “‘adversarial signed graph learning with differential privacy” and “communication efficient federated graph classification via generative diffusion modeling” are accepted by sigkdd conference on knowledge discovery and data mining (kdd), 2026. Communication efficient federated graph classification via generative diffusion modeling, in proceedings of acm sigkdd conference on knowledge discovery and data mining (kdd),.