{
  "id": 10602343,
  "title": "HARMONIA: Interpretable Graph Learning through Mixtures of Neural Bases",
  "url": "https://urgent.news/2026/09/27/harmonia-interpretable-graph-learning-through-mixtures-of-neural-bases",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-27T22:15:57.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2609.33972v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Existing interpretable graph additive models still face limitations in either computational scalability or modeling flexibility. In terms of structural modeling, previous approaches either face quadratic scaling costs or sacrifice explicit source-to-target contribution decomposition. In terms of feature components, they rely either on per-feature neural networks or on single shared bases with…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}