将记忆检索与图平滑结合，提升节点分类性能。
Graph Hopfield Networks: Energy-Based Node Classification with Associative Memory
- 能量函数融合记忆检索与图拉普拉斯平滑
- 稀疏引用网络上准确率提升2.0~5.0个百分点
- 无需修改结构即可适应异质图数据
我们提出图霍普菲尔德网络，其能量函数将关联记忆检索与图拉普拉斯平滑相结合，用于节点分类。对该联合能量进行梯度下降，得到一种交替执行霍普菲尔德检索与拉普拉斯传播的迭代更新过程。记忆检索在不同场景下带来增益：在稀疏引用网络中准确率提升达2.0~5.0个百分点；在特征遮蔽下额外增强5.0个百分点鲁棒性。该迭代能量下降架构本身构成强归纳偏置，所有变体（包括禁用记忆的NoMem对照实验）在Amazon共购图上均优于标准基线。通过调参可实现对异质性基准的图锐化，无需改变网络结构。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。