Metraipolis › archive › dc_9fcd9bd242de
Graph Memory: Spectral Associative Memory via Dirichlet Energy — arXiv:2609.32365
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.32365
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T22:36:31.600Z
- SHA-256 of the archived text
b5bbe13b93b0526a330d4844bc0ffddc17c5b07bb1c2b7b7b59634708e917b52- Stable URL of this page
https://metraipolis.com/documento/dc_9fcd9bd242de
How to cite
Graph Memory: Spectral Associative Memory via Dirichlet Energy — arXiv:2609.32365 — arXiv (en), https://arxiv.org/abs/2609.32365 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9fcd9bd242de (Metraipolis archive dc_9fcd9bd242de, sha256 b5bbe13b93b0526a330d4844bc0ffddc17c5b07bb1c2b7b7b59634708e917b52)
BibTeX
@misc{dc9fcd9bd242de,
title = {Graph Memory: Spectral Associative Memory via Dirichlet Energy — arXiv:2609.32365},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.32365},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9fcd9bd242de; sha256 b5bbe13b93b0526a330d4844bc0ffddc17c5b07bb1c2b7b7b59634708e917b52},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32365. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Dense associative memories have traditionally focused on storing and retrieving vector-valued patterns. Many modern machine learning problems, however, are naturally graph-structured, requiring memory mechanisms for relational patterns, graph diffusion geometries, community structures, and graph-based inductive biases. We propose a spectral dense associative memory for storage and retrieval of graph data, extending the classical vector-valued memories. Retrieval is performed through a log-sum-exp energy induced by Dirichlet energy with spectral norm distances, producing a softmax-weighted average of the stored Laplacians that remains a valid graph Laplacian. We prove exponential storage capacity and exponentially decaying retrieval error. Beyond graph retrieval, we establish theoretical guarantees for spectral quantities central to graph learning, including eigenvalues, eigenspaces, and diffusion operators. Experiments on synthetic graph data, real-world airline network, protein conformation data and wearable sensor data demonstrate robust graph retrieval while preserving the graph geometry of the data. Our framework provides a new associative memory paradigm for graph-structured data and bridges dense associative memory with modern graph learning and generative AI. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG). Categorie arXiv: Machine Learning (cs.LG) ; Information Retrieval (cs.IR). Pagina del lavoro: https://arxiv.org/abs/2609.32365 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T22:14:27.666Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).