Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.03464 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917311901859840 |
|---|---|
| author | Rao, Abinav Wa, Alex Athavale, Rishi |
| author_facet | Rao, Abinav Wa, Alex Athavale, Rishi |
| contents | We introduce Graph Hopfield Networks, whose energy function couples associative memory retrieval with graph Laplacian smoothing for node classification. Gradient descent on this joint energy yields an iterative update interleaving Hopfield retrieval with Laplacian propagation. Memory retrieval provides regime-dependent benefits: up to 2.0~pp on sparse citation networks and up to 5 pp additional robustness under feature masking; the iterative energy-descent architecture itself is a strong inductive bias, with all variants (including the memory-disabled NoMem ablation) outperforming standard baselines on Amazon co-purchase graphs. Tuning enables graph sharpening for heterophilous benchmarks without architectural changes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_03464 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Graph Hopfield Networks: Energy-Based Node Classification with Associative Memory Rao, Abinav Wa, Alex Athavale, Rishi Machine Learning Artificial Intelligence Information Retrieval We introduce Graph Hopfield Networks, whose energy function couples associative memory retrieval with graph Laplacian smoothing for node classification. Gradient descent on this joint energy yields an iterative update interleaving Hopfield retrieval with Laplacian propagation. Memory retrieval provides regime-dependent benefits: up to 2.0~pp on sparse citation networks and up to 5 pp additional robustness under feature masking; the iterative energy-descent architecture itself is a strong inductive bias, with all variants (including the memory-disabled NoMem ablation) outperforming standard baselines on Amazon co-purchase graphs. Tuning enables graph sharpening for heterophilous benchmarks without architectural changes. |
| title | Graph Hopfield Networks: Energy-Based Node Classification with Associative Memory |
| topic | Machine Learning Artificial Intelligence Information Retrieval |
| url | https://arxiv.org/abs/2603.03464 |