More Like this

1. PaGE-Link: Path-based Graph Neural Network Explanation for Heterogeneous Link Prediction

   https://doi.org/10.1145/3543507.3583511  

   Zhang, Shichang; Zhang, Jiani; Song, Xiang; Adeshina, Soji; Zheng, Da; Faloutsos, Christos; Sun, Yizhou (April 2023, WWW '23: Proceedings of the ACM Web Conference 2023)

   Transparency and accountability have become major concerns for black-box machine learning (ML) models. Proper explanations for the model behavior increase model transparency and help researchers develop more accountable models. Graph neural networks (GNN) have recently shown superior performance in many graph ML problems than traditional methods, and explaining them has attracted increased interest. However, GNN explanation for link prediction (LP) is lacking in the literature. LP is an essential GNN task and corresponds to web applications like recommendation and sponsored search on web. Given existing GNN explanation methods only address node/graph-level tasks, we propose Path-based GNN Explanation for heterogeneous Link prediction (PaGE-Link) that generates explanations with connection interpretability, enjoys model scalability, and handles graph heterogeneity. Qualitatively, PaGE-Link can generate explanations as paths connecting a node pair, which naturally captures connections between the two nodes and easily transfer to human-interpretable explanations. Quantitatively, explanations generated by PaGE-Link improve AUC for recommendation on citation and user-item graphs by 9 - 35% and are chosen as better by 78.79% of responses in human evaluation. 

   more » « less
2. Graph InfoClust: Maximizing Coarse-Grain Mutual Information in Graphs

   https://doi.org/https://doi.org/10.1007/978-3-030-75762-5_43  

   Mavromatis, Costas; Karypis, George (January 2021, Advances in Knowledge Discovery and Data Mining. PAKDD)

   null (Ed.)

   This work proposes a new unsupervised (or self-supervised) node representation learning method that aims to leverage the coarse-grain information that is available in most graphs. This extends previous attempts that only leverage fine-grain information (similarities within local neighborhoods) or global graph information (similarities across all nodes). Intuitively, the proposed method identifies nodes that belong to the same clusters and maximizes their mutual information. Thus, coarse-grain (cluster-level) similarities that are shared between nodes are preserved in their representations. The core components of the proposed method are (i) a jointly optimized clustering of nodes during learning and (ii) an Infomax objective term that preserves the mutual information among nodes of the same clusters. Our method is able to outperform competing state-of-art methods in various downstream tasks, such as node classification, link prediction, and node clustering. Experiments show that the average gain is between 0.2% and 6.1%, over the best competing approach, over all tasks. Our code is publicly available at: https://github.com/cmavro/Graph-InfoClust-GIC. 

   more » « less
3. Identity-Aware Graph Neural Networks

   You, Jiaxuan; Gomes-Selman, Jonathan; Ying, Rex; Leskovec, Jure. (January 2021, Conference on Artificial Intelligence (AAAI))

   null (Ed.)

   Message passing Graph Neural Networks (GNNs) provide a powerful modeling framework for relational data. However, the expressive power of existing GNNs is upper-bounded by the 1-Weisfeiler-Lehman (1-WL) graph isomorphism test, which means GNNs that are not able to predict node clustering coefficients and shortest path distances, and cannot differentiate between different d regular graphs. Here we develop a class of message passing GNNs, named Identity-aware Graph Neural Networks (ID-GNNs), with greater expressive power than the 1-WL test. ID-GNN offers a minimal but powerful solution to limitations of existing GNNs. ID-GNN extends existing GNN architectures by inductively considering nodes’ identities during message passing. To embed a given node, IDGNN first extracts the ego network centered at the node, then conducts rounds of heterogeneous message passing, where different sets of parameters are applied to the center node than to other surrounding nodes in the ego network. We further propose a simplified but faster version of ID-GNN that injects node identity information as augmented node features. Altogether, both versions of ID GNN represent general extensions of message passing GNNs, where experiments show that transforming existing GNNs to ID-GNNs yields on average 40% accuracy improvement on challenging node, edge, and graph property prediction tasks; 3% accuracy improvement on node and graph classification benchmarks; and 15% ROC AUC improvement on real-world link prediction tasks. Additionally, ID-GNNs demonstrate improved or comparable performance over other task-specific graph networks. 

   more » « less
4. Identity-aware Graph Neural Networks

   You, Jiaxuan; Gomes-Selman, Jonathan; Ying, Rex; Leskovec, Jure (January 2021, Proceedings of the AAAI Conference on Artificial Intelligence)

   null (Ed.)

   Message passing Graph Neural Networks (GNNs) provide a powerful modeling framework for relational data. However, the expressive power of existing GNNs is upper-bounded by the 1-Weisfeiler-Lehman (1-WL) graph isomorphism test, which means GNNs that are not able to predict node clustering coefficients and shortest path distances, and cannot differentiate between different d-regular graphs. Here we develop a class of message passing GNNs, named Identity-aware Graph Neural Networks (ID-GNNs), with greater expressive power than the 1-WL test. ID-GNN offers a minimal but powerful solution to limitations of existing GNNs. ID-GNN extends existing GNN architectures by inductively considering nodes’ identities during message passing. To embed a given node, IDGNN first extracts the ego network centered at the node, then conducts rounds of heterogeneous message passing, where different sets of parameters are applied to the center node than to other surrounding nodes in the ego network. We further propose a simplified but faster version of ID-GNN that injects node identity information as augmented node features. Altogether, both versions of ID-GNN represent general extensions of message passing GNNs, where experiments show that transforming existing GNNs to ID-GNNs yields on average 40% accuracy improvement on challenging node, edge, and graph property prediction tasks; 3% accuracy improvement on node and graph classification benchmarks; and 15% ROC AUC improvement on real-world link prediction tasks. Additionally, ID-GNNs demonstrate improved or comparable performance over other task-specific graph networks. 

   more » « less
5. Distance Encoding: Design Provably More Powerful Neural Networks for Graph Representation Learning

   Li, Pan; Wang, Yanbang; Wang, Hongwei; Leskovec, Jure. (January 2020, Neural Information Processing Systems (NeurIPS))

   Learning representations of sets of nodes in a graph is crucial for applications ranging from node-role discovery to link prediction and molecule classification. Graph Neural Networks (GNNs) have achieved great success in graph representation learning. However, expressive power of GNNs is limited by the 1-Weisfeiler-Lehman (WL) test and thus GNNs generate identical representations for graph substructures that may in fact be very different. More powerful GNNs, proposed recently by mimicking higher-order-WL tests, only focus on representing entire graphs and they are computationally inefficient as they cannot utilize sparsity of the underlying graph. Here we propose and mathematically analyze a general class of structure related features, termed Distance Encoding (DE). DE assists GNNs in representing any set of nodes, while providing strictly more expressive power than the 1-WL test. DE captures the distance between the node set whose representation is to be learned and each node in the graph. To capture the distance DE can apply various graph-distance measures such as shortest path distance or generalized PageRank scores. We propose two ways for GNNs to use DEs (1) as extra node features, and (2) as controllers of message aggregation in GNNs. Both approaches can utilize the sparse structure of the underlying graph, which leads to computational efficiency and scalability. We also prove that DE can distinguish node sets embedded in almost all regular graphs where traditional GNNs always fail. We evaluate DE on three tasks over six real networks: structural role prediction, link prediction, and triangle prediction. Results show that our models outperform GNNs without DE by up-to 15% in accuracy and AUROC. Furthermore, our models also significantly outperform other state-of-the-art methods especially designed for the above tasks. 

   more » « less