Despite the success of Graph Neural Networks (GNNs) on various applications, GNNs encounter significant performance degradation when the amount of supervision signals, i.e., number of labeled nodes, is limited, which is expected as GNNs are trained solely based on the supervision obtained from the labeled nodes. On the other hand,recent self-supervised learning paradigm aims to train GNNs by solving pretext tasks that do not require any labeled nodes, and it has shown to even outperform GNNs trained with few labeled nodes. However, a major drawback of self-supervised methods is that they fall short of learning class discriminative node representations since no labeled information is utilized during training. To this end, we propose a novel semi-supervised method for graphs, GraFN, that leverages few labeled nodes to ensure nodes that belong to the same class to be grouped together, thereby achieving the best of both worlds of semi-supervised and self-supervised methods. Specifically, GraFN randomly samples support nodes from labeled nodes and anchor nodes from the entire graph. Then, it minimizes the difference between two predicted class distributions that are non-parametrically assigned by anchor-supports similarity from two differently augmented graphs. We experimentally show that GraFN surpasses both the semi-supervised and self-supervised methods in terms of node classification on real-world graphs. The source code for GraFN is available at https://github.com/Junseok0207/GraFN.
Many real world graphs contain time domain information. Temporal Graph Neural Networks capture temporal information as well as structural and contextual information in the generated dynamic node embeddings. Researchers have shown that these embeddings achieve state-of-the-art performance in many different tasks. In this work, we propose TGL, a unified framework for large-scale offline Temporal Graph Neural Network training where users can compose various Temporal Graph Neural Networks with simple configuration files. TGL comprises five main components, a temporal sampler, a mailbox, a node memory module, a memory updater, and a message passing engine. We design a Temporal-CSR data structure and a parallel sampler to efficiently sample temporal neighbors to formtraining mini-batches. We propose a novel random chunk scheduling technique that mitigates the problem of obsolete node memory when training with a large batch size. To address the limitations of current TGNNs only being evaluated on small-scale datasets, we introduce two large-scale real-world datasets with 0.2 and 1.3 billion temporal edges. We evaluate the performance of TGL on four small-scale datasets with a single GPU and the two large datasets with multiple GPUs for both link prediction and node classification tasks. We compare TGL with the open-sourced code of five methods and show that TGL achieves similar or better accuracy with an average of 13x speedup. Our temporal parallel sampler achieves an average of 173x speedup on a multi-core CPU compared with the baselines. On a 4-GPU machine, TGL can train one epoch of more than one billion temporal edges within 1-10 hours. To the best of our knowledge, this is the first work that proposes a general framework for large-scale Temporal Graph Neural Networks training on multiple GPUs.
The key towards learning informative node representations in graphs lies in how to gain contextual information from the neighbourhood. In this work, we present a simple-yet-effective self-supervised node representation learning strategy via directly maximizing the mutual information between the hidden representations of nodes and their neighbourhood, which can be theoretically justified by its link to graph smoothing. Following InfoNCE, our framework is optimized via a surrogate contrastive loss, where the positive selection underpins the quality and efficiency of representation learning. To this end, we propose a topology-aware positive sampling strategy, which samples positives from the neighbourhood by considering the structural dependencies between nodes and thus enables positive selection upfront. In the extreme case when only one positive is sampled, we fully avoid expensive neighbourhood aggregation. Our methods achieve promising performance on various node classification datasets. It is also worth mentioning by applying our loss function to MLP based node encoders, our methods can be orders of faster than existing solutions. Our codes and supplementary materials are available at https://github.com/dongwei156/n2n.
Due to the homophily assumption in graph convolution networks (GNNs), a common consensus in the graph node classification task is that GNNs perform well on homophilic graphs but may fail on heterophilic graphs with many inter-class edges. However, the previous inter-class edges perspective and related homo-ratio metrics cannot well explain the GNNs performance under some heterophilic datasets, which implies that not all the inter-class edges are harmful to GNNs. In this work, we propose a new metric based on von Neumann entropy to re-examine the heterophily problem of GNNs and investigate the feature aggregation of inter-class edges from an entire neighbor identifiable perspective. Moreover, we propose a simple yet effective Conv-Agnostic GNN framework (CAGNNs) to enhance the performance of most GNNs on heterophily datasets by learning the neighbor effect for each node. Specifically, we first decouple the feature of each node into the discriminative feature for downstream tasks and the aggregation feature for graph convolution. Then, we propose a shared mixer module to adaptively evaluate the neighbor effect of each node to incorporate the neighbor information. The proposed framework can be regarded as a plug-in component and is compatible with most GNNs. The experimental results over nine well-known benchmark datasets indicate that our framework can significantly improve performance, especially for the heterophily graphs. The average performance gain is 9.81%, 25.81%, and 20.61% compared with GIN, GAT, and GCN, respectively. Extensive ablation studies and robustness analysis further verify the effectiveness, robustness, and interpretability of our framework. Code is available at https://github.com/JC-202/CAGNN.
Graph Convolutional Networks (GCNs) have emerged as the state-of-the-art method for graph-based learning tasks. However, training GCNs at scale is still challenging, hindering both the exploration of more sophisticated GCN architectures and their applications to real-world large graphs. While it might be natural to consider graph partition and distributed training for tackling this challenge, this direction has only been slightly scratched the surface in the previous works due to the limitations of existing designs. In this work, we first analyze why distributed GCN training is ineffective and identify the underlying cause to be the excessive number of boundary nodes of each partitioned subgraph, which easily explodes the memory and communication costs for GCN training. Furthermore, we propose a simple yet effective method dubbed BNS-GCN that adopts random Boundary-Node-Sampling to enable efficient and scalable distributed GCN training. Experiments and ablation studies consistently validate the effectiveness of BNS-GCN, e.g., boosting the throughput by up to 16.2x and reducing the memory usage by up to 58%, while maintaining a full-graph accuracy. Furthermore, both theoretical and empirical analysis show that BNS-GCN enjoys a better convergence than existing sampling-based methods. We believe that our BNS-GCN has opened up a new paradigm for enabling GCN training at scale. The code is available at https://github.com/RICE-EIC/BNS-GCN.
Graph neural networks (GNNs) have been widely adopted for semi-supervised learning on graphs. A recent study shows that the graph random neural network (GRAND) model can generate state-of-the-art performance for this problem. However, it is difficult for GRAND to handle large-scale graphs since its effectiveness relies on computationally expensive data augmentation procedures. In this work, we present a scalable and high-performance GNN framework GRAND+ for semi-supervised graph learning. To address the above issue, we develop a generalized forward push (GFPush) algorithm in GRAND+ to pre-compute a general propagation matrix and employ it to perform graph data augmentation in a mini-batch manner. We show that both the low time and space complexities of GFPush enable GRAND+ to efficiently scale to large graphs. Furthermore, we introduce a confidence-aware consistency loss into the model optimization of GRAND+, facilitating GRAND+'s generalization superiority. We conduct extensive experiments on seven public datasets of different sizes. The results demonstrate that GRAND+ 1) is able to scale to large graphs and costs less running time than existing scalable GNNs, and 2) can offer consistent accuracy improvements over both full-batch and scalable GNNs across all datasets.
In recent years, plentiful evidence illustrates that Graph Convolutional Networks (GCNs) achieve extraordinary accomplishments on the node classification task. However, GCNs may be vulnerable to adversarial attacks on label-scarce dynamic graphs. Many existing works aim to strengthen the robustness of GCNs; for instance, adversarial training is used to shield GCNs against malicious perturbations. However, these works fail on dynamic graphs for which label scarcity is a pressing issue. To overcome label scarcity, self-training attempts to iteratively assign pseudo-labels to highly confident unlabeled nodes but such attempts may suffer serious degradation under dynamic graph perturbations. In this paper, we generalize noisy supervision as a kind of self-supervised learning method and then propose a novel Bayesian self-supervision model, namely GraphSS, to address the issue. Extensive experiments demonstrate that GraphSS can not only affirmatively alert the perturbations on dynamic graphs but also effectively recover the prediction of a node classifier when the graph is under such perturbations. These two advantages prove to be generalized over three classic GCNs across five public graph datasets.
The inception of the Relational Graph Convolutional Network (R-GCN) marked a milestone in the Semantic Web domain as a widely cited method that generalises end-to-end hierarchical representation learning to Knowledge Graphs (KGs). R-GCNs generate representations for nodes of interest by repeatedly aggregating parameterised, relation-specific transformations of their neighbours. However, in this paper, we argue that the the R-GCN's main contribution lies in this "message passing" paradigm, rather than the learned weights. To this end, we introduce the "Random Relational Graph Convolutional Network" (RR-GCN), which leaves all parameters untrained and thus constructs node embeddings by aggregating randomly transformed random representations from neighbours, i.e., with no learned parameters. We empirically show that RR-GCNs can compete with fully trained R-GCNs in both node classification and link prediction settings.
Unsupervised graph representation learning aims to distill various graph information into a downstream task-agnostic dense vector embedding. However, existing graph representation learning approaches are designed mainly under the node homophily assumption: connected nodes tend to have similar labels and optimize performance on node-centric downstream tasks. Their design is apparently against the task-agnostic principle and generally suffers poor performance in tasks, e.g., edge classification, that demands feature signals beyond the node-view and homophily assumption. To condense different feature signals into the embeddings, this paper proposes PairE, a novel unsupervised graph embedding method using two paired nodes as the basic unit of embedding to retain the high-frequency signals between nodes to support node-related and edge-related tasks. Accordingly, a multi-self-supervised autoencoder is designed to fulfill two pretext tasks: one retains the high-frequency signal better, and another enhances the representation of commonality. Our extensive experiments on a diversity of benchmark datasets clearly show that PairE outperforms the unsupervised state-of-the-art baselines, with up to 101.1\% relative improvement on the edge classification tasks that rely on both the high and low-frequency signals in the pair and up to 82.5\% relative performance gain on the node classification tasks.
In this paper, we study the problem of learning Graph Neural Networks (GNNs) with Differential Privacy (DP). We propose a novel differentially private GNN based on Aggregation Perturbation (GAP), which adds stochastic noise to the GNN's aggregation function to statistically obfuscate the presence of a single edge (edge-level privacy) or a single node and all its adjacent edges (node-level privacy). Tailored to the specifics of private learning, GAP's new architecture is composed of three separate modules: (i) the encoder module, where we learn private node embeddings without relying on the edge information; (ii) the aggregation module, where we compute noisy aggregated node embeddings based on the graph structure; and (iii) the classification module, where we train a neural network on the private aggregations for node classification without further querying the graph edges. GAP's major advantage over previous approaches is that it can benefit from multi-hop neighborhood aggregations, and guarantees both edge-level and node-level DP not only for training, but also at inference with no additional costs beyond the training's privacy budget. We analyze GAP's formal privacy guarantees using R\'enyi DP and conduct empirical experiments over three real-world graph datasets. We demonstrate that GAP offers significantly better accuracy-privacy trade-offs than state-of-the-art DP-GNN approaches and naive MLP-based baselines. Our code is publicly available at https://github.com/sisaman/GAP.
Misinformation is becoming increasingly prevalent on social media and in news articles. It has become so widespread that we require algorithmic assistance utilising machine learning to detect such content. Training these machine learning models require datasets of sufficient scale, diversity and quality. However, datasets in the field of automatic misinformation detection are predominantly monolingual, include a limited amount of modalities and are not of sufficient scale and quality. Addressing this, we develop a data collection and linking system (MuMiN-trawl), to build a public misinformation graph dataset (MuMiN), containing rich social media data (tweets, replies, users, images, articles, hashtags) spanning 21 million tweets belonging to 26 thousand Twitter threads, each of which have been semantically linked to 13 thousand fact-checked claims across dozens of topics, events and domains, in 41 different languages, spanning more than a decade. The dataset is made available as a heterogeneous graph via a Python package (mumin). We provide baseline results for two node classification tasks related to the veracity of a claim involving social media, and demonstrate that these are challenging tasks, with the highest macro-average F1-score being 62.55% and 61.45% for the two tasks, respectively. The MuMiN ecosystem is available at https://mumin-dataset.github.io/, including the data, documentation, tutorials and leaderboards.
Recently, transformers have shown promising performance in learning graph representations. However, there are still some challenges when applying transformers to real-world scenarios due to the fact that deep transformers are hard to train from scratch and the quadratic memory consumption w.r.t. the number of nodes. In this paper, we propose Graph Masked Autoencoders (GMAEs), a self-supervised transformer-based model for learning graph representations. To address the above two challenges, we adopt the masking mechanism and the asymmetric encoder-decoder design. Specifically, GMAE takes partially masked graphs as input, and reconstructs the features of the masked nodes. The encoder and decoder are asymmetric, where the encoder is a deep transformer and the decoder is a shallow transformer. The masking mechanism and the asymmetric design make GMAE a memory-efficient model compared with conventional transformers. We show that, when serving as a conventional self-supervised graph representation model, GMAE achieves state-of-the-art performance on both the graph classification task and the node classification task under common downstream evaluation protocols. We also show that, compared with training in an end-to-end manner from scratch, we can achieve comparable performance after pre-training and fine-tuning using GMAE while simplifying the training process.
Due to its geometric properties, hyperbolic space can support high-fidelity embeddings of tree- and graph-structured data, upon which various hyperbolic networks have been developed. Existing hyperbolic networks encode geometric priors not only for the input, but also at every layer of the network. This approach involves repeatedly mapping to and from hyperbolic space, which makes these networks complicated to implement, computationally expensive to scale, and numerically unstable to train. In this paper, we propose a simpler approach: learn a hyperbolic embedding of the input, then map once from it to Euclidean space using a mapping that encodes geometric priors by respecting the isometries of hyperbolic space, and finish with a standard Euclidean network. The key insight is to use a random feature mapping via the eigenfunctions of the Laplace operator, which we show can approximate any isometry-invariant kernel on hyperbolic space. Our method can be used together with any graph neural networks: using even a linear graph model yields significant improvements in both efficiency and performance over other hyperbolic baselines in both transductive and inductive tasks.
Contrastive learning is an effective unsupervised method in graph representation learning. Recently, the data augmentation based contrastive learning method has been extended from images to graphs. However, most prior works are directly adapted from the models designed for images. Unlike the data augmentation on images, the data augmentation on graphs is far less intuitive and much harder to provide high-quality contrastive samples, which are the key to the performance of contrastive learning models. This leaves much space for improvement over the existing graph contrastive learning frameworks. In this work, by introducing an adversarial graph view and an information regularizer, we propose a simple but effective method, Adversarial Graph Contrastive Learning (ARIEL), to extract informative contrastive samples within a reasonable constraint. It consistently outperforms the current graph contrastive learning methods in the node classification task over various real-world datasets and further improves the robustness of graph contrastive learning. The code is at https://github.com/Shengyu-Feng/ARIEL.
Cellular sheaves equip graphs with a "geometrical" structure by assigning vector spaces and linear maps to nodes and edges. Graph Neural Networks (GNNs) implicitly assume a graph with a trivial underlying sheaf. This choice is reflected in the structure of the graph Laplacian operator, the properties of the associated diffusion equation, and the characteristics of the convolutional models that discretise this equation. In this paper, we use cellular sheaf theory to show that the underlying geometry of the graph is deeply linked with the performance of GNNs in heterophilic settings and their oversmoothing behaviour. By considering a hierarchy of increasingly general sheaves, we study how the ability of the sheaf diffusion process to achieve linear separation of the classes in the infinite time limit expands. At the same time, we prove that when the sheaf is non-trivial, discretised parametric diffusion processes have greater control than GNNs over their asymptotic behaviour. On the practical side, we study how sheaves can be learned from data. The resulting sheaf diffusion models have many desirable properties that address the limitations of classical graph diffusion equations (and corresponding GNN models) and obtain competitive results in heterophilic settings. Overall, our work provides new connections between GNNs and algebraic topology and would be of interest to both fields.
Designing spectral convolutional networks is a challenging problem in graph learning. ChebNet, one of the early attempts, approximates the spectral graph convolutions using Chebyshev polynomials. GCN simplifies ChebNet by utilizing only the first two Chebyshev polynomials while still outperforming it on real-world datasets. GPR-GNN and BernNet demonstrate that the Monomial and Bernstein bases also outperform the Chebyshev basis in terms of learning the spectral graph convolutions. Such conclusions are counter-intuitive in the field of approximation theory, where it is established that the Chebyshev polynomial achieves the optimum convergent rate for approximating a function. In this paper, we revisit the problem of approximating the spectral graph convolutions with Chebyshev polynomials. We show that ChebNet's inferior performance is primarily due to illegal coefficients learnt by ChebNet approximating analytic filter functions, which leads to over-fitting. We then propose ChebNetII, a new GNN model based on Chebyshev interpolation, which enhances the original Chebyshev polynomial approximation while reducing the Runge phenomenon. We conducted an extensive experimental study to demonstrate that ChebNetII can learn arbitrary graph convolutions and achieve superior performance in both full- and semi-supervised node classification tasks. Most notably, we scale ChebNetII to a billion graph ogbn-papers100M, showing that spectral-based GNNs have superior performance. Our code is available at https://github.com/ivam-he/ChebNetII.
Most real-world networks contain well-defined community structures where nodes are densely connected internally within communities. To learn from these networks, we develop MarkovGNN that captures the formation and evolution of communities directly in different convolutional layers. Unlike most Graph Neural Networks (GNNs) that consider a static graph at every layer, MarkovGNN generates different stochastic matrices using a Markov process and then uses these community-capturing matrices in different layers. MarkovGNN is a general approach that could be used with most existing GNNs. We experimentally show that MarkovGNN outperforms other GNNs for clustering, node classification, and visualization tasks. The source code of MarkovGNN is publicly available at \url{https://github.com/HipGraph/MarkovGNN}.
We show how graph neural networks can be used to solve the canonical graph coloring problem. We frame graph coloring as a multi-class node classification problem and utilize an unsupervised training strategy based on the statistical physics Potts model. Generalizations to other multi-class problems such as community detection, data clustering, and the minimum clique cover problem are straightforward. We provide numerical benchmark results and illustrate our approach with an end-to-end application for a real-world scheduling use case within a comprehensive encode-process-decode framework. Our optimization approach performs on par or outperforms existing solvers, with the ability to scale to problems with millions of variables.
Recently, flat-minima optimizers, which seek to find parameters in low-loss neighborhoods, have been shown to improve a neural network's generalization performance over stochastic and adaptive gradient-based optimizers. Two methods have received significant attention due to their scalability: 1. Stochastic Weight Averaging (SWA), and 2. Sharpness-Aware Minimization (SAM). However, there has been limited investigation into their properties and no systematic benchmarking of them across different domains. We fill this gap here by comparing the loss surfaces of the models trained with each method and through broad benchmarking across computer vision, natural language processing, and graph representation learning tasks. We discover several surprising findings from these results, which we hope will help researchers further improve deep learning optimizers, and practitioners identify the right optimizer for their problem.
Graph Neural Networks (GNNs) have become a popular approach for various applications, ranging from social network analysis to modeling chemical properties of molecules. While GNNs often show remarkable performance on public datasets, they can struggle to learn long-range dependencies in the data due to over-smoothing and over-squashing tendencies. To alleviate this challenge, we propose PCAPass, a method which combines Principal Component Analysis (PCA) and message passing for generating node embeddings in an unsupervised manner and leverages gradient boosted decision trees for classification tasks. We show empirically that this approach provides competitive performance compared to popular GNNs on node classification benchmarks, while gathering information from longer distance neighborhoods. Our research demonstrates that applying dimensionality reduction with message passing and skip connections is a promising mechanism for aggregating long-range dependencies in graph structured data.