In the past years, Graph Neural Networks (GNNs) have become the `de facto' standard in various deep learning domains, thanks to their flexibility in modeling real-world phenomena represented as graphs. However, the message-passing mechanism of GNNs faces challenges in learnability and expressivity, hindering high performance on heterophilic graphs, where adjacent nodes frequently have different labels. Most existing solutions addressing these challenges are primarily confined to specific benchmarks focused on node classification tasks. This narrow focus restricts the potential impact that link prediction under heterophily could offer in several applications, including recommender systems. For example, in social networks, two users may be connected for some latent reason, making it challenging to predict such connections in advance. Physics-Inspired GNNs such as GRAFF provided a significant contribution to enhance node classification performance under heterophily, thanks to the adoption of physics biases in the message-passing. Drawing inspiration from these findings, we advocate that the methodology employed by GRAFF can improve link prediction performance as well. To further explore this hypothesis, we introduce GRAFF-LP, an extension of GRAFF to link prediction. We evaluate its efficacy within a recent collection of heterophilic graphs, establishing a new benchmark for link prediction under heterophily. Our approach surpasses previous methods, in most of the datasets, showcasing a strong flexibility in different contexts, and achieving relative AUROC improvements of up to 26.7%.

翻译：在过去几年中，图神经网络（GNNs）因其对以图形式表示的真实世界现象建模的灵活性，已成为多个深度学习领域的“事实标准”。然而，GNN的消息传递机制在可学习性与表达能力上面临挑战，阻碍了其在异质性图（即邻近节点常具有不同标签）上实现高性能。现有解决这些挑战的方法主要局限于特定基准测试中的节点分类任务，这种狭隘的关注限制了异质性下链接预测在推荐系统等应用中的潜在影响。例如，在社交网络中，两个用户可能因某些潜在原因而连接，这使得提前预测此类连接极具挑战性。物理启发的GNN（如GRAFF）通过在消息传递中引入物理偏置，显著提升了异质性下的节点分类性能。受此启发，我们认为GRAFF所采用的方法同样能够改善链接预测性能。为深入验证这一假设，我们提出了GRAFF-LP——GRAFF在链接预测任务上的扩展。我们在近期收集的异质性图集合中评估其有效性，建立了异质性下链接预测的新基准。我们的方法在大多数数据集上超越了以往方法，展现出对不同场景的强适应性，AUROC相对提升最高达26.7%。