图神经网络的深度集成效果有限，主要因模型预测趋同，难以捕捉不确定性。
Do Deep Ensembles Actually Capture Uncertainty in Graph Neural Networks?
- 通过对比单模型与集成模型在七大数据集上的表现，分析其不确定性估计能力。
- 集成模型仅小幅提升预测稳定性，未显著改善不确定性估计，关键在于缺乏预测差异。
- 发现模型收敛于功能相似而非参数差异，导致信息熵降低，适合研究图学习不确定性机制者阅读。
尽管深度集成被广泛认为是深度学习中不确定性量化的方法首选，但其在图结构数据上的有效性常基于计算机视觉等领域的成功而被默认。本文针对消息传递型图神经网络系统评估了标准深度集成方法。在涵盖多种任务与复杂度的七个数据集上进行基准测试，结果表明集成模型相比单模型仅带来微弱改进。这些有限收益主要源于稳定优化噪声带来的点预测精度提升，而非真正改善不确定性估计。通过分解认知不确定性和随机不确定性，我们发现存在‘认知坍缩’现象：独立训练的网络模型趋于产生高度相似的预测。由于集成的核心机制依赖于模型间的分歧以捕获认知不确定性，预测趋同使得该优势失效。进一步分析表明，这种坍缩由函数空间而非权重空间的凸性驱动，即不同参数解产生几乎相同的输出行为。研究结果表明，深度集成的成功无法直接迁移至图机器学习领域。
原文摘要 · Abstract (English)
While deep ensembles are widely considered to be the default method for uncertainty quantification in deep learning, their effectiveness for graph-structured data is often simply assumed based on successes in domains like computer vision. We investigate standard deep ensembles specifically for message-passing graph neural networks. Benchmarking across seven datasets representing varied tasks and complexities, we reveal that ensembles provide surprisingly little improvement over a single model. Instead, the observed marginal gains stem primarily from stabilizing optimization noise in point predictions rather than yielding meaningfully better uncertainty estimates. Through an aleatoric-epistemic decomposition, we identify epistemic collapse: independently trained networks consistently converge to overly similar predictions. Because disagreement is the fundamental mechanism through which ensembles capture epistemic uncertainty, this lack of diversity neutralizes their key advantage. Analyzing this phenomenon further, we suggest this collapse is driven by functional rather than weight-space convexity, where distinct parameter solutions induce almost identical behavior. Our results suggest that deep ensemble success does not seamlessly transfer to graph machine learning.
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。