通过调节对称性提升图生成模型训练速度与效果
Balancing Symmetry and Efficiency in Graph Flow Matching
- 用正弦位置编码和节点置换控制对称性松弛
- 仅用基线19%训练轮次即达更优性能
- 适合追求高效图生成的算法研究者
等变性是图生成模型的核心，确保模型尊重图的节点置换对称性。然而，严格的等变性会因架构约束增加计算开销，并因需在大量可能的节点置换空间中保持一致性而减慢收敛速度。本文研究这一权衡，从一个等变的离散流匹配模型出发，通过基于正弦位置编码和节点置换的可控对称性调制方案，在训练过程中松弛其等变性。实验表明，破坏对称性可加速早期训练，但会引发捷径解导致过拟合，即重复生成训练集中的图。而合理调节对称性信号可在延迟过拟合的同时加速收敛，使模型在仅19%的基线训练轮次内达到更强性能。
原文摘要 · Abstract (English)
Equivariance is central to graph generative models, as it ensures the model respects the permutation symmetry of graphs. However, strict equivariance can increase computational cost due to added architectural constraints, and can slow down convergence because the model must be consistent across a large space of possible node permutations. We study this trade-off for graph generative models. Specifically, we start from an equivariant discrete flow-matching model, and relax its equivariance during training via a controllable symmetry modulation scheme based on sinusoidal positional encodings and node permutations. Experiments first show that symmetry-breaking can accelerate early training by providing an easier learning signal, but at the expense of encouraging shortcut solutions that can cause overfitting, where the model repeatedly generates graphs that are duplicates of the training set. On the contrary, properly modulating the symmetry signal can delay overfitting while accelerating convergence, allowing the model to reach stronger performance with $19\%$ of the baseline training epochs.
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。