{
  "id": 11878,
  "url": "https://arxiv.org/abs/2607.15687v1",
  "title": "Toward Federated Multimodal Graph Foundation Models: A Topology-Aware Multimodal Alignment Framework",
  "summary": "Multimodal-attributed graphs (MAGs), whose nodes carry modalities such as images and text alongside topological structure, now pervade applications including social platforms, e-commerce, and biomedical networks, offering richer semantic signals than single-modality graphs. In practice, such graphs are fragmented across privacy-restricted silos owned by different platforms and institutions, so learning a broadly transferable model over them demands collaborative training that never exposes raw d",
  "authors": "Xunkai Li, Guohao Fu, Yuming Ai, Zhengyu Wu, Hongchao Qin, Rong-Hua Li et al.",
  "category": "research",
  "topics": "safety-alignment,privacy-surveillance",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-17T06:57:41.000Z",
  "fetched_at": "2026-07-20T05:10:09.534Z",
  "source_slug": "arxiv-cslg",
  "source_name": "arXiv cs.LG",
  "source_homepage": "https://arxiv.org/list/cs.LG/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/11878",
  "original_url": "https://arxiv.org/abs/2607.15687v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}