Learning effective representations for Continuous-Time Dynamic Graphs (CTDGs) has garnered significant research interest, largely due to its powerful capabilities in modeling complex interactions between nodes. A fundamental and crucial requirement for representation learning in CTDGs is the appropriate estimation and preservation of proximity. However, due to the sparse and evolving characteristics of CTDGs, the spatial-temporal properties inherent in high-order proximity remain largely unexplored. Despite its importance, this property presents significant challenges due to the computationally intensive nature of personalized interaction intensity estimation and the dynamic attributes of CTDGs. To this end, we propose a novel Correlated Spatial-Temporal Positional encoding that incorporates a parameter-free personalized interaction intensity estimation under the weak assumption of the Poisson Point Process. Building on this, we introduce the Dynamic Graph Transformer with Correlated Spatial-Temporal Positional Encoding (CorDGT), which efficiently retains the evolving spatial-temporal high-order proximity for effective node representation learning in CTDGs. Extensive experiments on seven small and two large-scale datasets demonstrate the superior performance and scalability of the proposed CorDGT. The code is available at: https://github.com/wangz3066/CorDGT.

Unsupervised Graph Domain Adaptation (UGDA) has emerged as a practical solution to transfer knowledge from a label-rich source graph to a completely unlabelled target graph. However, most methods require a labelled source graph to provide supervision signals, which might not be accessible in the real-world settings due to regulations and privacy concerns. In this paper, we explore the scenario of source-free unsupervised graph domain adaptation, which tries to address the domain adaptation problem without accessing the labelled source graph. Specifically, we present a novel paradigm called GraphCTA, which performs model adaptation and graph adaptation collaboratively through a series of procedures: (1) conduct model adaptation based on node's neighborhood predictions in target graph considering both local and global information; (2) perform graph adaptation by updating graph structure and node attributes via neighborhood contrastive learning; and (3) the updated graph serves as an input to facilitate the subsequent iteration of model adaptation, thereby establishing a collaborative loop between model adaptation and graph adaptation. Comprehensive experiments are conducted on various public datasets. The experimental results demonstrate that our proposed model outperforms recent source-free baselines by large margins.

In this demonstration, we introduce Spade, a sophisticated real-time fraud detection framework adept at navigating the complex transaction graph. Unlike conventional methods that are limited by performance and lack incremental update capabilities, Spade leverages advanced incremental updates in dense subgraph peeling algorithms to enhance efficiency, usability, and reduce latency, achieving a significantly better fraud prevention ratio. The demo showcases an interactive GUI prototype, allowing users to customize and explore dense subgraphs with various metrics and algorithms. This interactive demonstration also effectively highlights Spade's robust capacity to unearth fraudulent transactions within varied settings, including Grab's services and cryptocurrency transactions.

Online learning is a powerful technique that allows models to adjust to concept drift in dynamically changing graphs. This approach is crucial for large mobility-based companies like Grab, where batch-learning methods fail to keep up with the large amount of training data. Our work focuses on scaling graph neural network mixture of expert (MoE) models for real-time traffic speed prediction on road networks, while meeting high accuracy and low latency requirements. Conventional spatio-temporal and incremental MoE frameworks struggle with poor inference accuracy and linear time complexity when scaling experts, for the latter, leading to prohibitively high latency in model updates. To address this issue, we introduce the Indexed Router, a novel method that categorizes experts into a structured hierarchy called the indexed tree. This approach reduces the time to scale and search N number of experts from O(N) to O(log N), making it ideal for online learning under tight service level agreements. Our experiments show that these time savings do not compromise inference accuracy, and our Indexed Router outperforms state-of-the-art spatio-temporal and incremental MoE models in terms of traffic speed prediction accuracy on real-life GPS traces from Grab's database and publicly available records. In summary, the Indexed Router enables MoE models to scale across large numbers of experts with low latency, while accurately identifying the relevant experts for inference.

As various forms of fraud proliferate on Ethereum, it is imperative to safeguard against these malicious activities to protect susceptible users from being victimized. While current studies solely rely on graph-based fraud detection approaches, it is argued that they may not be well-suited for dealing with highly repetitive, skew-distributed and heterogeneous Ethereum transactions. To address these challenges, we propose BERT4ETH, a universal pre-trained Transformer encoder that serves as an account representation extractor for detecting various fraud behaviors on Ethereum. BERT4ETH features the superior modeling capability of Transformer to capture the dynamic sequential patterns inherent in Ethereum transactions, and addresses the challenges of pre-training a BERT model for Ethereum with three practical and effective strategies, namely repetitiveness reduction, skew alleviation and heterogeneity modeling. Our empirical evaluation demonstrates that BERT4ETH outperforms state-of-the-art methods with significant enhancements in terms of the phishing account detection and de-anonymization tasks. The code for BERT4ETH is available at: https://github.com/git-disl/BERT4ETH.

With the proliferation of pump-and-dump schemes (P&Ds) in the cryptocurrency market, it becomes imperative to detect such fraudulent activities in advance to alert potentially susceptible investors. In this paper, we focus on predicting the pump probability of all coins listed in the target exchange before a scheduled pump time, which we refer to as the target coin prediction task. Firstly, we conduct a comprehensive study of the latest 709 P&D events organized in Telegram from Jan. 2019 to Jan. 2022. Our empirical analysis reveals some interesting patterns of P&Ds, such as that pumped coins exhibit intra-channel homogeneity and inter-channel heterogeneity. Here channel refers a form of group in Telegram that is frequently used to coordinate P&D events. This observation inspires us to develop a novel sequence-based neural network, dubbed SNN, which encodes a channel's P&D event history into a sequence representation via the positional attention mechanism to enhance the prediction accuracy. Positional attention helps to extract useful information and alleviates noise, especially when the sequence length is long. Extensive experiments verify the effectiveness and generalizability of proposed methods. Additionally, we release the code and P&D dataset on GitHub https://github.com/Bayi-Hu/Pump-and-Dump-Detection-on-Cryptocurrency, and regularly update the dataset.

Graph Neural Networks (GNNs), which generalize deep neural networks to graph-structured data, have drawn considerable attention and achieved state-of-the-art performance in numerous graph related tasks. However, existing GNN models mainly focus on designing graph convolution operations. The graph pooling (or downsampling) operations, that play an important role in learning hierarchical representations, are usually overlooked. In this paper, we proposed a novel multi-view graph pooling operator dubbed as MVPool, which ranks nodes across different views with different contextual graph information. Meanwhile, attention mechanism is utilized to promote the collaboration of different views for generating robust node rankings. Then the pooling operation adaptively selects a subset of nodes to form an induced subgraph based on the ranking list. To preserve the underlying graph topological information, we further introduce a structure learning mechanism to learn a refined graph structure for the pooled graph at each layer. The proposed MVPool operator is a general strategy that can be integrated into various graph neural network architectures. By combining MVPool operator with graph neural networks, we perform hierarchical representation learning for both node and graph level classification as well as clustering tasks. Experimental results on nine widely used benchmarks demonstrate the effectiveness of our proposed model.

User recommendation aims at recommending users with potential interests in the social network. Previous works have mainly focused on the undirected social networks with symmetric relationship such as friendship, whereas recent advances have been made on the asymmetric relationship such as the following and followed by relationship. Among the few existing direction-aware user recommendation methods, the random walk strategy has been widely adopted to extract the asymmetric proximity between users. However, according to our analysis on real-world directed social networks, we argue that the asymmetric proximity captured by existing random walk based methods are insufficient due to the inbalance in-degree and out-degree of nodes. To tackle this challenge, we propose InfoWalk, a novel informative walk strategy to efficiently capture the asymmetric proximity solely based on random walks. By transferring the direction information into the weights of each step, InfoWalk is able to overcome the limitation of edges while simultaneously maintain both the direction and proximity. Based on the asymmetric proximity captured by InfoWalk, we further propose the qualitative (DNE-L) and quantitative (DNE-T) directed network embedding methods, capable of preserving the two properties in the embedding space. Extensive experiments conducted on six real-world benchmark datasets demonstrate the superiority of the proposed DNE model over several state-of-the-art approaches in various tasks.

Graph similarity learning, which measures the similarities between a pair of graph-structured objects, lies at the core of various machine learning tasks such as graph classification, similarity search, etc. In this paper, we devise a novel graph neural network based framework to address this challenging problem, motivated by its great success in graph representation learning. As the vast majority of existing graph neural network models mainly concentrate on learning effective node or graph level representations of a single graph, little effort has been made to jointly reason over a pair of graph-structured inputs for graph similarity learning. To this end, we propose Hierarchical Hypergraph Matching Networks (H2sup>MN) to calculate the similarities between graph pairs with arbitrary structure. Specifically, our proposed H2MN learns graph representation from the perspective of hypergraph, and takes each hyperedge as a subgraph to perform subgraph matching, which could capture the rich substructure similarities across the graph. To enable hierarchical graph representation and fast similarity computation, we further propose a hyperedge pooling operator to transform each graph into a coarse graph of reduced size. Then, a multi-perspective cross-graph matching layer is employed on the coarsened graph pairs to extract the inter-graph similarity. Comprehensive experiments on five public datasets empirically demonstrate that our proposed model can outperform state-of-the-art baselines with different gains for graph-graph classification and regression tasks.

Graph classification aims to extract accurate information from graph-structured data for classification and is becoming more and more important in the graph learning community. Although Graph Neural Networks (GNNs) have been successfully applied to graph classification tasks, most of them overlook the scarcity of labeled graph data in many applications. For example, in bioinformatics, obtaining protein graph labels usually needs laborious experiments. Recently, few-shot learning has been explored to alleviate this problem with only a few labeled graph samples of test classes. The shared sub-structures between training classes and test classes are essential in the few-shot graph classification. Existing methods assume that the test classes belong to the same set of super-classes clustered from training classes. However, according to our observations, the label spaces of training classes and test classes usually do not overlap in a real-world scenario. As a result, the existing methods don't well capture the local structures of unseen test classes. To overcome the limitation, in this paper, we propose a direct method to capture the sub-structures with a well initialized meta-learner within a few adaptation steps. More specifically, (1) we propose a novel framework consisting of a graph meta-learner, which uses GNNs based modules for fast adaptation on graph data, and a step controller for the robustness and generalization of meta-learner; (2) we provide quantitative analysis for the framework and give a graph-dependent upper bound of the generalization error based on our framework; (3) the extensive experiments on real-world datasets demonstrate that our framework gets state-of-the-art results on several few-shot graph classification tasks compared to baselines.

Graph embedding has become the research focus in both academic and industrial communities due to its powerful capabilities. The majority of existing work overwhelmingly learn node embeddings in the context of static, plain or attributed, homogeneous graphs. However, many real-world applications frequently involve bipartite graphs with temporal and attributed interaction edges, named temporal interaction graphs. The temporal interactions usually imply different facets of interest and might even evolve over time, thus putting forward huge challenges in learning effective node representations. In this paper, we propose a novel framework named TigeCMN to learn node representations from a sequence of temporal interactions. Specifically, we devise two coupled memory networks to store and update node embeddings in external matrices explicitly and dynamically, which forms deep matrix representations and could enhance the expressiveness of the node embeddings. We conduct experiments on two real-world datasets and the experimental results empirically demonstrate that TigeCMN can outperform the state-of-the-arts with different gains.