To improve the performance of Graph Neural Networks (GNNs), Graph Structure Learning (GSL) has been extensively applied to reconstruct or refine original graph structures, effectively addressing issues like heterophily, over-squashing, and noisy structures. While GSL is generally thought to improve GNN performance, it often leads to longer training times and more hyperparameter tuning. Besides, the distinctions among current GSL methods remain ambiguous from the perspective of GNN training, and there is a lack of theoretical analysis to quantify their effectiveness. Recent studies further suggest that, under fair comparisons with the same hyperparameter tuning, GSL does not consistently outperform baseline GNNs. This motivates us to ask a critical question: is GSL really useful for GNNs? To address this question, this paper makes two key contributions. First, we propose a new GSL framework, which includes three steps: GSL base (the representation used for GSL) construction, new structure construction, and view fusion, to better understand the effectiveness of GSL in GNNs. Second, after graph convolution, we analyze the differences in mutual information (MI) between node representations derived from the original topology and those from the newly constructed topology. Surprisingly, our empirical observations and theoretical analysis show that no matter which type of graph structure construction methods are used, after feeding the same GSL bases to the newly constructed graph, there is no MI gain compared to the original GSL bases. To fairly reassess the effectiveness of GSL, we conduct ablation experiments and find that it is the pretrained GSL bases that enhance GNN performance, and in most cases, GSL cannot improve GNN performance. This finding encourages us to rethink the essential components in GNNs, such as self-training and structural encoding, in GNN design rather than GSL.

翻译：为提高图神经网络（GNN）的性能，图结构学习（GSL）已被广泛应用于重构或优化原始图结构，有效解决了异质性、过度挤压及噪声结构等问题。尽管GSL通常被认为能提升GNN性能，但其往往导致更长的训练时间和更多的超参数调优。此外，从GNN训练的角度看，现有GSL方法间的差异仍不明确，且缺乏量化其有效性的理论分析。近期研究进一步表明，在与基线GNN进行相同超参数调优的公平比较下，GSL并未持续表现出更优性能。这促使我们提出一个关键问题：GSL对GNN真的有用吗？为回答此问题，本文作出两项关键贡献。首先，我们提出一个新的GSL框架，包含三个步骤：GSL基（用于GSL的表征）构建、新结构构建和视图融合，以更好地理解GSL在GNN中的有效性。其次，在图卷积后，我们分析了基于原始拓扑的节点表征与基于新构建拓扑的节点表征之间互信息（MI）的差异。令人惊讶的是，我们的实证观察与理论分析表明：无论使用何种图结构构建方法，在将相同的GSL基输入新构建的图后，相较于原始GSL基均未产生MI增益。为公平重估GSL的有效性，我们进行了消融实验，发现提升GNN性能的关键在于预训练的GSL基，而在多数情况下GSL本身并不能改善GNN性能。这一发现促使我们重新思考GNN设计中的核心要素（如自训练和结构编码）而非GSL。