We first define the restricted Cheeger constant in the link prediction task. Then, according to Proposition 2.1, we have: Then, we can draw the same conclusion with Eq.12, and the Thus, Eq.16 can be simplified to: "sites" Based on the Eq.15 and Eq.17, we can rewrite L The inequality holds due to the assumption. Knowledge discovery: In the 5 random experiments, we add 500 pseudo links in each iteration. The metadata information of the nodes are all strongly relevant to "Linux" Both papers focus on the "malware"/"phishing" under the topic "Computer security". The detailed result of the case study is shown in Table 6.

Pseudo labeling (PL) is a wide-applied strategy to enlarge the labeled dataset by self-annotating the potential samples during the training process.

Based on our definitions, we identify and analyze six real-world benchmarks spanning from homophilic to heterophilic link prediction settings, with graphs containing up to 30M edges.

Organization In Section A, we first introduce the baselines and our model and then describe the experimental details of graph classification and link prediction tasks but also our in-depth analyses. Then, in Section B, we provide the additional experimental results about analyses on datasets, ablation study for our proposed objectives, effects of our hyperparameters (λ1, α, λ2, and the perturbation magnitude), ablation study of attribute masking, and the comparison with augmentation-freeapproaches. In particular,thepre-training dataset consists of306K unlabeled protein ego-networksof50species,andthe fine-tuning dataset consists of 88K protein ego-networks of 8 species with the label given by the functionalityoftheegoprotein. For pre-training, the number of epochs is 100, the batch size is128, the learning rate is0.001, and the margin is10. For fine-tuning, we also follow the conventional setting from Hu et al.[3]. ForJOAOandGraphLoG, we use the publicsource codes4,toobtain the pre-trained models.

Heterophily, or the tendency of connected nodes in networks to have different class labels or dissimilar features, has been identified as challenging for many Graph Neural Network (GNN) models. While the challenges of applying GNNs for node classification when class labels display strong heterophily are well understood, it is unclear how heterophily affects GNN performance in other important graph learning tasks where class labels are not available. In this work, we focus on the link prediction task and systematically analyze the impact of heterophily in node features on GNN performance. We first introduce formal definitions of homophilic and heterophilic link prediction tasks, and present a theoretical framework that highlights the different optimizations needed for the respective tasks. We then analyze how different link prediction encoders and decoders adapt to varying levels of feature homophily and introduce designs for improved performance. Based on our definitions, we identify and analyze six real-world benchmarks spanning from homophilic to heterophilic link prediction settings, with graphs containing up to 30M edges. Our empirical analysis on a variety of synthetic and real-world datasets confirms our theoretical insights and highlights the importance of adopting learnable decoders and GNN encoders with ego-and neighbor-embedding separation in message passing for link prediction tasks beyond homophily.