Distribution shifts on graphs—the discrepancies in data distribution between training and employing a graph machine learning model—are ubiquitous and often unavoidable in real-world applications. These shifts may severely deteriorate model performance, posing significant challenges for reliable graph machine learning. In recent years, there has been a surge in research on graph machine learning specifically designed to tackle such distribution shifts, aiming to train models to achieve satisfactory performance on Out-of-Distribution (OOD) test data. This survey provides an up-to-date and forward-looking review of deep graph learning under distribution shifts. We categorize the field into three primary scenarios: graph OOD generalization, training-time graph OOD adaptation, and test-time graph OOD adaptation. We begin by formally formulating the problems and discussing various types of distribution shifts that can affect graph learning, such as covariate shifts and concept shifts. To provide a structured understanding of the literature, we introduce a systematic taxonomy that classifies existing methods into model-centric and data-centric approaches, investigating the techniques used in each category. We also summarize commonly used datasets in this research area to facilitate further investigation. Finally, we point out promising research directions and the corresponding challenges to encourage further study in this vital domain. Additionally, we provide a continuously updated reading list at https://github.com/kaize0409/Awesome-Graph-OOD .

The superiority of graph contrastive learning (GCL) has prompted its application to anomaly detection tasks for more powerful risk warning systems. Unfortunately, existing GCL-based models tend to excessively prioritize overall detection performance while neglecting robustness to structural imbalance, which can be problematic for many real-world networks following power-law degree distributions. Particularly, GCL-based methods may fail to capture tail anomalies (abnormal nodes with low degrees). This raises concerns about the security and robustness of current anomaly detection algorithms and therefore hinders their applicability in a variety of realistic high-risk scenarios. To the best of our knowledge, research on the robustness of graph anomaly detection to structural imbalance has received little scrutiny. To address the above issues, this paper presents a novel GCL-based framework named AD-GCL. It devises the neighbor pruning strategy to filter noisy edges for head nodes and facilitate the detection of genuine tail nodes by aligning from head nodes to forged tail nodes. Moreover, AD-GCL actively explores potential neighbors to enlarge the receptive field of tail nodes through anomaly-guided neighbor completion. We further introduce intra- and inter-view consistency loss of the original and augmentation graph for enhanced representation. The performance evaluation of the whole, head, and tail nodes on multiple datasets validates the comprehensive superiority of the proposed AD-GCL in detecting both head anomalies and tail anomalies.

Federated Graph Learning (FGL) enables multiple clients to jointly train powerful graph learning models, e.g., Graph Neural Networks (GNNs), without sharing their local graph data for graph-related downstream tasks, such as graph property prediction. In the real world, however, the graph data can suffer from significant distribution shifts across clients as the clients may collect their graph data for different purposes. In particular, graph properties are usually associated with invariant label-relevant substructures (i.e., subgraphs) across clients, while label-irrelevant substructures can appear in a client-specific manner. The issue of distribution shifts of graph data hinders the efficiency of GNN training and leads to serious performance degradation in FGL. To tackle the aforementioned issue, we propose a novel FGL framework entitled FedVN that eliminates distribution shifts through client-specific graph augmentation strategies with multiple learnable Virtual Nodes (VNs). Specifically, FedVN lets the clients jointly learn a set of shared VNs while training a global GNN model. To eliminate distribution shifts, each client trains a personalized edge generator that determines how the VNs connect local graphs in a client-specific manner. Furthermore, we provide theoretical analyses indicating that FedVN can eliminate distribution shifts of graph data across clients. Comprehensive experiments on four datasets under five settings demonstrate the superiority of our proposed FedVN over nine baselines.

Spatial-temporal graphs are widely used in a variety of real-world applications. Spatial-Temporal Graph Neural Networks (STGNNs) have emerged as a powerful tool to extract meaningful insights from this data. However, in real-world applications, most nodes may not possess any available temporal data during training. For example, the pandemic dynamics of most cities on a geographical graph may not be available due to the asynchronous nature of outbreaks. Such a phenomenon disagrees with the training requirements of most existing spatial-temporal forecasting methods, which jeopardizes their effectiveness and thus blocks broader deployment. In this paper, we propose to formulate a novel problem of inductive forecasting with limited training data. In particular, given a spatial-temporal graph, we aim to learn a spatial-temporal forecasting model that can be easily generalized onto those nodes without any available temporal training data. To handle this problem, we propose a principled framework named ST-FiT. ST-FiT consists of two key learning components: temporal data augmentation and spatial graph topology learning. With such a design, ST-FiT can be used on top of any existing STGNNs to achieve superior performance on the nodes without training data. Extensive experiments verify the effectiveness of ST-FiT in multiple key perspectives.

While machine learning models have proven effective across various scenarios, it is widely acknowledged that many models are vulnerable to adversarial attacks. Recently, numerous efforts have emerged in adversarial defense. Among them, certified defense is well known for its theoretical guarantees against arbitrary adversarial perturbations on input within a certain range. However, most existing works in this line struggle to generalize their certified robustness in other data domains with distribution shifts. This issue is rooted in the difficulty of eliminating the negative impact of spurious correlations on robustness in different domains. To address this problem, in this work, we propose a novel certified defense framework GLEAN, which incorporates a causal perspective into the generalization problem in certified defense. More specifically, our framework integrates a certifiable causal factor learning component to disentangle the causal relations and spurious correlations between input and label, thereby excluding the negative effect of spurious correlations on defense. On top of that, we design a causally certified defense strategy to handle adversarial attacks on latent causal factors. In this way, our framework is not only robust against malicious noises on data in the training distribution but also can generalize its robustness across domains with distribution shifts. Extensive experiments on benchmark datasets validate the superiority of our framework in certified robustness generalization in different data domains.

Functional Magnetic Resonance Image (fMRI) is commonly employed to study human brain activity, since it offers insight into the relationship between functional fluctuations and human behavior. To enhance analysis and comprehension of brain activity, Graph Neural Networks (GNNs) have been widely applied to the analysis of functional connectivities (FC) derived from fMRI data, due to their ability to capture the synergistic interactions among brain regions. However, in the human brain, performing complex tasks typically involves the activation of certain pathways, which could be represented as paths across graphs. As such, conventional GNNs struggle to learn from these pathways due to the long-range dependencies of multiple pathways. To address these challenges, we introduce a novel framework BrainMAP to learn multiple pathways in brain networks. BrainMAP leverages sequential models to identify long-range correlations among sequentialized brain regions and incorporates an aggregation module based on Mixture of Experts (MoE) to learn from multiple pathways. Our comprehensive experiments highlight BrainMAP's superior performance. Furthermore, our framework enables explanatory analyses of crucial brain regions involved in tasks.

The development and evaluation of graph neural networks (GNNs) generally follow the independent and identically distributed (i.i.d.) assumption. Yet this assumption is often untenable in practice due to the uncontrollable data generation mechanism. In particular, when the data distribution shows a significant shift, most GNNs would fail to produce reliable predictions and may even make decisions randomly. One of the most promising solutions to improve the model generalization is to pick out causal invariant parts in the input graph. Nonetheless, we observe a significant distribution gap between the causal parts learned by existing methods and the ground-truth, leading to undesirable performance. In response to the above issues, this paper presents GPro, a model that learns graph causal invariance with progressive inference. Specifically, the complicated graph causal invariant learning is decomposed into multiple intermediate inference steps from easy to hard, and the perception of GPro is continuously strengthened through a progressive inference process to extract causal features that are stable to distribution shifts. We also enlarge the training distribution by creating counterfactual samples to enhance the capability of the GPro in capturing the causal invariant parts. Extensive experiments demonstrate that our proposed GPro outperforms the state-of-the-art methods by 4.91% on average. For datasets with more severe distribution shifts, the performance improvement can be up to 6.86%.

Although the impact of COVID-19 pandemic has largely withered away over the years, the enduring presence of face masks continues to linger within our society. Still today, they're a familiarity, a crutch to fall back upon when sickness makes its rounds. However, it is often the case that we wear masks when they are not necessary, and, more concerningly, fail to wear them when they are truly necessary. Inefficient viral tracking methods further exacerbate the issue as they often do not alert the public and healthcare officials to oncoming or currently happening outbreaks fast enough. To combat these issues, new smart masks have been developed recently, equipped with biosensors to detect respiratory viruses in the air. However, these masks have their own drawbacks, including limited detection accuracy, detection scope and beneficial population. In response, this work presents the first of its kind prototype named iMask to augment current smart masks. By connecting the smartphone of the mask wearer to the Internet, iMask improves the detection accuracy. At its core, iMask employs multi-variate time series (1) imputation algorithms to alleviate the data scarcity issue and (2) forecasting algorithms to predict future viral levels. Based on shared, imputed and forecast viral data, iMask further leverages map services to create a viral concentration map that significantly expands the beneficiaries.

Mechanistic interpretability (MI) research aims to understand large language models (LLMs) by identifying computational circuits, subgraphs of model components with associated functional interpretations, that explain specific behaviors. Current MI approaches focus on discovering task-specific circuits, which has two key limitations: (1) poor generalizability across different language tasks, and (2) high costs associated with requiring human or advanced LLM interpretation of each computational node. To address these challenges, we propose developing a “modular circuit (MC) vocabulary” consisting of task-agnostic functional units. Each unit consists of a small computational subgraph with its interpretation. This approach enables global interpretability by allowing different language tasks to share common MCs, while reducing costs by reusing established interpretations for new tasks. We establish five criteria for characterizing the MC vocabulary and present ModCirc, a novel global-level mechanistic interpretability framework for discovering MC vocabularies in LLMs. We demonstrate ModCirc’s effectiveness by showing that it can identify modular circuits that perform well on various metrics.

Fairness-aware graph learning has gained increasing attention in recent years. Nevertheless, there lacks a comprehensive benchmark to evaluate and compare different fairness-aware graph learning methods, which blocks practitioners from choosing appropriate ones for broader real-world applications. In this paper, we present an extensive benchmark on ten representative fairness-aware graph learning methods. Specifically, we design a systematic evaluation protocol and conduct experiments on seven real-world datasets to evaluate these methods from multiple perspectives, including group fairness, individual fairness, the balance between different fairness criteria, and computational efficiency. Our in-depth analysis reveals key insights into the strengths and limitations of existing methods. Additionally, we provide practical guidance for applying fairness-aware graph learning methods in applications. To the best of our knowledge, this work serves as an initial step towards comprehensively understanding representative fairness-aware graph learning methods to facilitate future advancements in this area. Open-source code can be found at: https://github.com/yushundong/Fairness-Aware-Graph-Learning-Benchmark.

Computational epidemiology is crucial in understanding and controlling infectious diseases, as highlighted by large-scale outbreaks such as COVID-19. Given the inherent uncertainty and variability of disease spread, Monte Carlo (MC) simulations are widely used to predict infection peaks, estimate reproduction numbers, and evaluate the impact of non-pharmaceutical interventions (NPIs). While effective, MC-based methods require numerous runs to achieve statistically reliable estimates and variance, which suffer from high computational costs. In this work, we present a unified theoretical framework for analyzing disease spread dynamics on both directed and undirected contact networks, and propose an algorithm, **RAPID**, that significantly improves computational efficiency. Our contributions are threefold. First, we derive an asymptotic variance lower bound for MC estimates and identify the key factors influencing estimation variance. Second, we provide a theoretical analysis of the probabilistic disease spread process using linear approximations and derive the convergence conditions under non-reinfection epidemic models. Finally, we conduct extensive experiments on six real-world datasets, demonstrating our method's effectiveness and robustness in estimating the nodes' final state distribution. Specifically, our proposed method consistently produces accurate estimates aligned with results from a large number of MC simulations, while maintaining a runtime comparable to a single MC simulation. Our code and datasets are available at https://github.com/GuanghuiMin/RAPID.

Epidemic containment has long been a crucial task in many high-stake application domains, ranging from public health to misinformation dissemination. Existing studies for epidemic containment are primarily focused on undirected networks, assuming that the infection rate is constant throughout the contact network regardless of the strength and direction of contact. However, such an assumption can be unrealistic given the asymmetric nature of the real-world infection process. To tackle the epidemic containment problem in directed networks, simply grafting the methods designed for undirected network can be problematic, as most of the existing methods rely on the orthogonality and Lipschitz continuity in the eigensystem of the underlying contact network, which do not hold for directed networks. In this work, we derive a theoretical analysis on the general epidemic threshold condition for directed networks and show that such threshold condition can be used as an optimization objective to control the spread of the disease. Based on the epidemic threshold, we propose an asymptotically greedy algorithm DINO (DIrected NetwOrk epidemic containment) to identify the most critical nodes for epidemic containment. The proposed algorithm is evaluated on real-world directed networks, and the results validate its effectiveness and efficiency. The code is available at https://github.com/YinhanHe123/DINO/.

Abnormal subgraph (AS) detection plays a significant role in ensuring the security of many high-impact domains. Unlike node anomaly detection, identifying subgraph anomalies is extremely challenging due to the exponentially large subgraph space caused by various combinations of nodes and edges. Moreover, in the absence of supervisory signals, how to quantify the abnormality of subgraphs poses another pressing challenge. Traditional methods typically rely on handcrafted subgraph anomaly measures, making it hard to handle potential unknown anomalies with limited prior knowledge. Recent deep learning-based techniques are predominantly designed to discover individual node anomalies, which could be suboptimal for AS detection due to the inconsideration of collaborative behaviors between nodes in the subgraph. In fact, existing studies have put very little effort into this task, and even dedicated performance evaluation metrics are not yet available. To address the above challenges and promote related research, in this article, we propose a end-to-end unsupervised subgraph anomaly detection framework (EndSubG), which jointly models subgraph partition and AS detection as a whole instead of treating them as two separate stages. Specifically, EndSubG uncovers potential AS boundaries that violate the Homophily assumption by modeling the edge existence probability, then achieves anomaly-aware graph embedding and subgraph partition based on the refined topology. By forming a coarsened subgraph network, EndSubG picks out subgraph anomalies by learning the "subgraph-vicinity" matching patterns. Additionally, we design an evaluation metric weighted normalized mutual information centered on AS (AS-WNMI) specifically for subgraph anomaly detection, which is a variant of vanilla NMI and quantifies detection performance from both subgraph partition and anomaly recognition. The experimental results on synthetic and real-world datasets corroborate the superiority of end-to-end unsupervised subgraph anomaly detection framework (EndSubG) in terms of area under the curve (AUC), average precision (AP), and AS-WNMI. We also provide an intuitive analysis of the detected subgraphs through visualization for better understanding.

Fairness-aware graph neural networks (GNNs) have gained a surge of attention as they can reduce the bias of predictions on any demographic group (e.g., female) in graph-based applications. Although these methods greatly improve the algorithmic fairness of GNNs, the fairness can be easily corrupted by carefully designed adversarial attacks. In this paper, we investigate the problem of adversarial attacks on fairness of GNNs and propose G-FairAttack, a general framework for attacking various types of fairness-aware GNNs in terms of fairness with an unnoticeable effect on prediction utility. In addition, we propose a fast computation technique to reduce the time complexity of G-FairAttack. The experimental study demonstrates that G-FairAttack successfully corrupts the fairness of different types of GNNs while keeping the attack unnoticeable. Our study on fairness attacks sheds light on potential vulnerabilities in fairness-aware GNNs and guides further research on the robustness of GNNs in terms of fairness.

Federated Graph Learning (FGL) aims to learn graph learning models over graph data distributed in multiple data owners, which has been applied in various applications such as social recommendation and financial fraud detection. Inherited from generic Federated Learning (FL), FGL similarly has the data heterogeneity issue where the label distribution may vary significantly for distributed graph data across clients. For instance, a client can have the majority of nodes from a class, while another client may have only a few nodes from the same class. This issue results in divergent local objectives and impairs FGL convergence for node-level tasks, especially for node classification. Moreover, FGL also encounters a unique challenge for the node classification task: the nodes from a minority class in a client are more likely to have biased neighboring information, which prevents FGL from learning expressive node embeddings with Graph Neural Networks (GNNs). To grapple with the challenge, we propose FedSpray, a novel FGL framework that learns local class-wise structure proxies in the latent space and aligns them to obtain global structure proxies in the server. Our goal is to obtain the aligned structure proxies that can serve as reliable, unbiased neighboring information for node classification. To achieve this, FedSpray trains a global feature-structure encoder and generates unbiased soft targets with structure proxies to regularize local training of GNN models in a personalized way. We conduct extensive experiments over four datasets, and experiment results validate the superiority of FedSpray compared with other baselines. Our code is available at https://github.com/xbfu/FedSpray.

Tripartite graph-based recommender systems markedly diverge from traditional models by recommending unique combinations such as user groups and item bundles. Despite their effectiveness, these systems exacerbate the long-standing cold-start problem in traditional recommender systems, because any number of user groups or item bundles can be formed among users or items. To address this issue, we introduce a Consistency and Discrepancy-based graph contrastive learning method for tripartite graph-based Recommendation (CDR). This approach leverages two novel meta-path-based metrics-consistency and discrepancy-to capture nuanced, implicit associations between the recommended objects and the recommendees. These metrics, indicative of high-order similarities, can be efficiently calculated with infinite graph convolutional networks (GCN) layers under a multi-objective optimization framework, using the limit theory of GCN. Additionally, we introduce a novel Contrastive Divergence (CD) loss, which can seamlessly integrate the consistency and discrepancy metrics into the contrastive objective as the positive and contrastive supervision signals to learn node representations, enhancing the pairwise ranking of recommended objects and proving particularly valuable in severe cold-start scenarios. Extensive experiments demonstrate the effectiveness of the proposed CDR. The code is released at https://github.com/foodfaust/CDR.

Haochen Liu, Song Wang, Chen Chen, Jundong Li. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

The problem of few-shot graph classification targets at assigning class labels for graph samples, where only limited labeled graphs are provided for each class. To solve the problem brought by label scarcity, recent studies have proposed to adopt the prevalent few-shot learning framework to achieve fast adaptations to graph classes with limited labeled graphs. In particular, these studies typically propose to accumulate meta-knowledge across a large number of meta-training tasks, and then generalize such meta-knowledge to meta-test tasks sampled from a disjoint class set. Nevertheless, existing studies generally ignore the crucial task correlations among meta-training tasks and treat them independently. In fact, such task correlations can help promote the model generalization to meta-test tasks and result in better classification performance. On the other hand, it remains challenging to capture and utilize task correlations due to the complex components and interactions in meta-training tasks. To deal with this, we propose a novel few-shot graph classification framework FAITH to capture task correlations via learning a hierarchical task structure at different granularities. We further propose a task-specific classifier to incorporate the learned task correlations into the few-shot graph classification process. Moreover, we derive FAITH+, a variant of FAITH that can improve the sampling process for the hierarchical task structure. The extensive experiments on four prevalent graph datasets further demonstrate the superiority of FAITH and FAITH+ over other state-of-the-art baselines.

Evolutionary anti-coordination games on networks capture real-world strategic situations such as traffic routing and market competition. Two key problems concerning evolutionary games are the existence of a pure Nash equilibrium (NE) and the convergence time. In this work, we study these two problems for anti-coordination games under sequential and synchronous update schemes. For each update scheme, we examine two decision modes based on whether an agent considers its own previous action (self essential) or not (self non-essential) in choosing its next action. Using a relationship between games and dynamical systems, we show that for both update schemes, finding an NE can be done efficiently under the self non-essential mode but is computationally intractable under the self essential mode. We then identify special cases for which an NE can be obtained efficiently. For convergence time, we show that the dynamics converges in a polynomial number of steps under the synchronous scheme; for the sequential scheme, the convergence time is polynomial only under the self non-essential mode. Through experiments, we empirically examine the convergence time and the equilibria for both synthetic and real-world networks.

Methicillin-resistant Staphylococcus aureus (MRSA) is a type of bacteria resistant to certain antibiotics, making it difficult to prevent MRSA infections. Among decades of efforts to conquer infectious diseases caused by MRSA, many studies have been proposed to estimate the causal effects of close contact (treatment) on MRSA infection (outcome) from observational data. In this problem, the treatment assignment mechanism plays a key role as it determines the patterns of missing counterfactuals --- the fundamental challenge of causal effect estimation. Most existing observational studies for causal effect learning assume that the treatment is assigned individually for each unit. However, on many occasions, the treatments are pairwisely assigned for units that are connected in graphs, i.e., the treatments of different units are entangled. Neglecting the entangled treatments can impede the causal effect estimation. In this paper, we study the problem of causal effect estimation with treatment entangled in a graph. Despite a few explorations for entangled treatments, this problem still remains challenging due to the following challenges: (1) the entanglement brings difficulties in modeling and leveraging the unknown treatment assignment mechanism; (2) there may exist hidden confounders which lead to confounding biases in causal effect estimation; (3) the observational data is often time-varying. To tackle these challenges, we propose a novel method NEAT, which explicitly leverages the graph structure to model the treatment assignment mechanism, and mitigates confounding biases based on the treatment assignment modeling. We also extend our method into a dynamic setting to handle time-varying observational data. Experiments on both synthetic datasets and a real-world MRSA dataset validate the effectiveness of the proposed method, and provide insights for future applications.

Federated Learning (FL) enables multiple clients to collaboratively learn a machine learning model without exchanging their own local data. In this way, the server can exploit the computational power of all clients and train the model on a larger set of data samples among all clients. Although such a mechanism is proven to be effective in various fields, existing works generally assume that each client preserves sufficient data for training. In practice, however, certain clients can only contain a limited number of samples (i.e., few-shot samples). For example, the available photo data taken by a specific user with a new mobile device is relatively rare. In this scenario, existing FL efforts typically encounter a significant performance drop on these clients. Therefore, it is urgent to develop a few-shot model that can generalize to clients with limited data under the FL scenario. In this paper, we refer to this novel problem as federated few-shot learning. Nevertheless, the problem remains challenging due to two major reasons: the global data variance among clients (i.e., the difference in data distributions among clients) and the local data insufficiency in each client (i.e., the lack of adequate local data for training). To overcome these two challenges, we propose a novel federated few-shot learning framework with two separately updated models and dedicated training strategies to reduce the adverse impact of global data variance and local data insufficiency. Extensive experiments on four prevalent datasets that cover news articles and images validate the effectiveness of our framework compared with the state-of-the-art baselines.

Few-shot node classification aims at classifying nodes with limited labeled nodes as references. Recent few-shot node classification methods typically learn from classes with abundant labeled nodes (i.e., meta-training classes) and then generalize to classes with limited labeled nodes (i.e., meta-test classes). Nevertheless, on real-world graphs, it is usually difficult to obtain abundant labeled nodes for many classes. In practice, each meta-training class can only consist of several labeled nodes, known as the extremely weak supervision problem. In few-shot node classification, with extremely limited labeled nodes for meta-training, the generalization gap between meta-training and meta-test will become larger and thus lead to suboptimal performance. To tackle this issue, we study a novel problem of few-shot node classification with extremely weak supervision and propose a principled framework X-FNC under the prevalent meta-learning framework. Specifically, our goal is to accumulate meta-knowledge across different meta-training tasks with extremely weak supervision and generalize such knowledge to meta-test tasks. To address the challenges resulting from extremely scarce labeled nodes, we propose two essential modules to obtain pseudo-labeled nodes as extra references and effectively learn from extremely limited supervision information. We further conduct extensive experiments on four node classification datasets with extremely weak supervision to validate the superiority of our framework compared to the state-of-the-art baselines.

Graph mining algorithms have been playing a significant role in myriad fields over the years. However, despite their promising performance on various graph analytical tasks, most of these algorithms lack fairness considerations. As a consequence, they could lead to discrimination towards certain populations when exploited in human-centered applications. Recently, algorithmic fairness has been extensively studied in graph-based applications. In contrast to algorithmic fairness on independent and identically distributed (i.i.d.) data, fairness in graph mining has exclusive backgrounds, taxonomies, and fulfilling techniques. In this survey, we provide a comprehensive and up-to-date introduction of existing literature under the context of fair graph mining. Specifically, we propose a novel taxonomy of fairness notions on graphs, which sheds light on their connections and differences. We further present an organized summary of existing techniques that promote fairness in graph mining. Finally, we discuss current research challenges and open questions, aiming at encouraging cross-breeding ideas and further advances.

The efficient detection of outbreaks and other cascading phenomena is a fundamental problem in a number of domains, including disease spread, social networks, and infrastructure networks. In such settings, monitoring and testing a small group of pre-selected nodes from the susceptible population (i.e., a sensor set) is often the preferred testing regime. We study the problem of selecting a sensor set that minimizes the delay in detection---we refer to this as the MinDelSS problem. Prior methods for minimizing the detection time rely on greedy algorithms using submodularity. We show that this approach can sometimes lead to a worse approximation for minimizing the detection time than desired. We also show that MinDelSS is hard to approximate within an O(n^(1-1/g))-factor for any constant g greater than or equal to 2 for a graph with n nodes. This instead motivates seeking a bicriteria approximations. We present the algorithm RoundSensor, which gives a rigorous worst case O(log(n))-factor for the detection time, while violating the budget by a factor of O(log^2(n)). Our algorithm is based on the sample average approximation technique from stochastic optimization, combined with linear programming and rounding. We evaluate our algorithm on several networks, including hospital contact networks, which validates its effectiveness in real settings.

Networked discrete dynamical systems are often used to model the spread of contagions and decision-making by agents in coordination games. Fixed points of such dynamical systems represent configurations to which the system converges. In the dissemination of undesirable contagions (such as rumors and misinformation), convergence to fixed points with a small number of affected nodes is a desirable goal. Motivated by such considerations, we formulate a novel optimization problem of finding a nontrivial fixed point of the system with the minimum number of affected nodes. We establish that, unless P = NP, there is no polynomial-time algorithm for approximating a solution to this problem to within the factor n^(1 - epsilon) for any constant epsilon > 0. To cope with this computational intractability, we identify several special cases for which the problem can be solved efficiently. Further, we introduce an integer linear program to address the problem for networks of reasonable sizes. For solving the problem on larger networks, we propose a general heuristic framework along with greedy selection methods. Extensive experimental results on real-world networks demonstrate the effectiveness of the proposed heuristics. A full version of the manuscript, source code and data are available at: https://github.com/bridgelessqiu/NMIN-FPE

Few-shot graph classification aims at predicting classes for graphs, given limited labeled graphs for each class. To tackle the bottleneck of label scarcity, recent works propose to incorporate few-shot learning frameworks for fast adaptations to graph classes with limited labeled graphs. Specifically, these works propose to accumulate meta-knowledge across diverse meta-training tasks, and then generalize such meta-knowledge to the target task with a disjoint label set. However, existing methods generally ignore task correlations among meta-training tasks while treating them independently. Nevertheless, such task correlations can advance the model generalization to the target task for better classification performance. On the other hand, it remains non-trivial to utilize task correlations due to the complex components in a large number of meta-training tasks. To deal with this, we propose a novel few-shot learning framework FAITH that captures task correlations via constructing a hierarchical task graph at different granularities. Then we further design a loss-based sampling strategy to select tasks with more correlated classes. Moreover, a task-specific classifier is proposed to utilize the learned task correlations for few-shot classification. Extensive experiments on four prevalent few-shot graph classification datasets demonstrate the superiority of FAITH over other state-of-the-art baselines.

Node classification is of great importance among various graph mining tasks. In practice, real-world graphs generally follow the long-tail distribution, where a large number of classes only consist of limited labeled nodes. Although Graph Neural Networks (GNNs) have achieved significant improvements in node classification, their performance decreases substantially in such a few-shot scenario. The main reason can be attributed to the vast generalization gap between meta-training and meta-test due to the task variance caused by different node/class distributions in meta-tasks (i.e., node-level and class-level variance). Therefore, to effectively alleviate the impact of task variance, we propose a task-adaptive node classification framework under the few-shot learning setting. Specifically, we first accumulate meta-knowledge across classes with abundant labeled nodes. Then we transfer such knowledge to the classes with limited labeled nodes via our proposed task-adaptive modules. In particular, to accommodate the different node/class distributions among meta-tasks, we propose three essential modules to perform node-level, class-level, and task-level adaptations in each meta-task, respectively. In this way, our framework can conduct adaptations to different meta-tasks and thus advance the model generalization performance on meta-test tasks. Extensive experiments on four prevalent node classification datasets demonstrate the superiority of our framework over the state-of-the-art baselines. Our code is provided at https://github.com/SongW-SW/TENT https://github.com/SongW-SW/TENT.

Graph few-shot learning is of great importance among various graph learning tasks. Under the few-shot scenario, models are often required to conduct classification given limited labeled samples. Existing graph few-shot learning methods typically leverage Graph Neural Networks (GNNs) and perform classification across a series of meta-tasks. Nevertheless, these methods generally rely on the original graph (i.e., the graph that the meta-task is sampled from) to learn node representations. Consequently, the learned representations for the same nodes are identical in all meta-tasks. Since the class sets are different across meta-tasks, node representations should be task-specific to promote classification performance. Therefore, to adaptively learn node representations across meta-tasks, we propose a novel framework that learns a task-specific structure for each meta-task. To handle the variety of nodes across meta-tasks, we extract relevant nodes and learn task-specific structures based on node influence and mutual information. In this way, we can learn node representations with the task-specific structure tailored for each meta-task. We further conduct extensive experiments on five node classification datasets under both single- and multiple-graph settings to validate the superiority of our framework over the state-of-the-art baselines.

Online travel platforms (OTPs), e.g., booking.com and Ctrip.com, deliver travel experiences to online users by providing travel-related products. One key problem facing OTPs is to predict users' future travel destination, which has many important applications, e.g., proactively recommending users flight tickets or hotels in the destination city. Although much progress has been made for the next POI recommendation, they are largely sub-optimal for travel destination prediction on OTPs, due to the unique characteristics exhibited from users' travel behaviors such as offline spatial-temporal periodicity and online multi-interest exploration. In this paper, we propose an online-offline periodicity-aware information gain network, OOPIN, for travel destination prediction on OTPs. The key components of the model are (1) an offline mobility pattern extractor, which extracts spatial-temporal periodicity along with the sequential dependencies from the visited city sequence; and (2) an online multi-interests exploration module that discovers destinations that the user might be interested in but not yet visited from their online interaction data.Comprehensive experiments on real-world OTP demonstrate the superior performance of the proposed model for travel destination prediction compared with state-of-the-art methods.

Knowledge graphs (KGs) are of great importance in various artificial intelligence systems, such as question answering, relation extraction, and recommendation. Nevertheless, most real-world KGs are highly incomplete, with many missing relations between entities. To discover new triples (i.e., head entity, relation, tail entity), many KG completion algorithms have been proposed in recent years. However, a vast majority of existing studies often require a large number of training triples for each relation, which contradicts the fact that the frequency distribution of relations in KGs often follows a long tail distribution, meaning a majority of relations have only very few triples. Meanwhile, since most existing large-scale KGs are constructed automatically by extracting information from crowd-sourcing data using heuristic algorithms, plenty of errors could be inevitably incorporated due to the lack of human verification, which greatly reduces the performance for KG completion. To tackle the aforementioned issues, in this paper, we study a novel problem of error-aware few-shot KG completion and present a principled KG completion framework REFORM. Specifically, we formulate the problem under the few-shot learning framework, and our goal is to accumulate meta-knowledge across different meta-tasks and generalize the accumulated knowledge to the meta-test task for error-aware few-shot KG completion. To address the associated challenges resulting from insufficient training samples and inevitable errors, we propose three essential modules neighbor encoder, cross-relation aggregation, and error mitigation in each meta-task. Extensive experiments on three widely used KG datasets demonstrate the superiority of the proposed framework REFORM over competitive baseline methods.

Feature selection is a prevalent data preprocessing paradigm for various learning tasks. Due to the expensive cost of acquiring supervision information, unsupervised feature selection sparks great interests recently. However, existing unsupervised feature selection algorithms do not have fairness considerations and suffer from a high risk of amplifying discrimination by selecting features that are over associated with protected attributes such as gender, race, and ethnicity. In this paper, we make an initial investigation of the fairness-aware unsupervised feature selection problem and develop a principled framework, which leverages kernel alignment to find a subset of high-quality features that can best preserve the information in the original feature space while being minimally correlated with protected attributes. Specifically, different from the mainstream in-processing debiasing methods, our proposed framework can be regarded as a model-agnostic debiasing strategy that eliminates biases and discrimination before downstream learning algorithms are involved. Experimental results on real-world datasets demonstrate that our framework achieves a good trade-off between feature utility and promoting feature fairness.

One fundamental problem in causal inference is to learn the individual treatment effects (ITE) -- assessing the causal effects of a certain treatment (e.g., prescription of medicine) on an important outcome (e.g., cure of a disease) for each data instance, but the effectiveness of most existing methods is often limited due to the existence of hidden confounders. Recent studies have shown that the auxiliary relational information among data can be utilized to mitigate the confounding bias. However, these works assume that the observational data and the relations among them are static, while in reality, both of them will continuously evolve over time and we refer such data as time-evolving networked observational data.

The connectivity of networks has been widely studied in many high-impact applications, ranging from immunization, critical infrastructure analysis, social network mining, to bioinformatic system studies. Regardless of the end application domains, connectivity minimization has always been a fundamental task to effectively control the functioning of the underlying system. The combinatorial nature of the connectivity minimization problem imposes an exponential computational complexity to find the optimal solution, which is intractable in large systems. To tackle the computational barrier, greedy algorithm is extensively used to ensure a near-optimal solution by exploiting the diminishing returns property of the problem. Despite the empirical success, the theoretical and algorithmic challenges of the problems still remain wide open. On the theoretical side, the intrinsic hardness and the approximability of the general connectivity minimization problem are still unknown except for a few special cases. On the algorithmic side, existing algorithms are hard to balance between the optimization quality and computational efficiency. In this article, we address the two challenges by (1) proving that the general connectivity minimization problem is NP-hard and is the best approximation ratio for any polynomial algorithms, and (2) proposing the algorithm CONTAIN and its variant CONTAIN + that can well balance optimization effectiveness and computational efficiency for eigen-function based connectivity minimization problems in large networks.

Network connectivity optimization, which aims to manipulate network connectivity by changing its underlying topology, is a fundamental task behind a wealth of high-impact data mining applications, ranging from immunization, critical infrastructure construction, social collaboration mining, bioinformatics analysis, to intelligent transportation system design. To tackle its exponential computation complexity, greedy algorithms have been extensively used for network connectivity optimization by exploiting its diminishing returns property. Despite the empirical success, two key challenges largely remain open. First, on the theoretic side, the hardness, as well as the approximability of the general network connectivity optimization problem are still nascent except for a few special instances. Second, on the algorithmic side, current algorithms are often hard to balance between the optimization quality and the computational efficiency. In this paper, we systematically address these two challenges for the network connectivity optimization problem. First, we reveal some fundamental limits by proving that, for a wide range of network connectivity optimization problems, (1) they are NP-hard and (2) (1-1/e) is the optimal approximation ratio for any polynomial algorithms. Second, we propose an effective, scalable and general algorithm (CONTAIN) to carefully balance the optimization quality and the computational efficiency.

Network embedding has gained more attentions in recent years. It has been shown that the learned low-dimensional node vector representations could advance a myriad of graph mining tasks such as node classification, community detection, and link prediction. A vast majority of the existing efforts are overwhelmingly devoted to single-layered networks or homogeneous networks with a single type of nodes and node interactions. However, in many real-world applications, a variety of networks could be abstracted and presented in a multilayered fashion. Typical multi-layered networks include critical infrastructure systems, collaboration platforms, social recommender systems, to name a few. Despite the widespread use of multi-layered networks, it remains a daunting task to learn vector representations of different types of nodes due to the bewildering combination of both within-layer connections and cross-layer network dependencies. In this paper, we study a novel problem of multi-layered network embedding. In particular, we propose a principled framework – MANE to model both within-layer connections and cross-layer network dependencies simultaneously in a unified optimization framework for embedding representation learning. Experiments on real-world multi-layered networks corroborate the effectiveness of the proposed framework.

Networks are ubiquitous in many high impact domains. Among the various aspects of network studies, connectivity is the one that plays important role in many applications (e.g., information dissemination, robustness analysis, community detection, etc.). The diversified applications have spurred numerous connectivity measures. Accordingly, ad-hoc connectivity optimization methods are designed for each measure, making it hard to model and control the connectivity of the network in a uniformed framework. On the other hand, it is often impossible to maintain an accurate structure of the network due to network dynamics and noise in real applications, which would affect the accuracy of connectivity measures and the effectiveness of corresponding connectivity optimization methods. In this work, we aim to address the challenges on network connectivity by (1)unifying a wide range of classic network connectivity measures into one uniform model; (2)proposing effective approaches to infer connectivity measures and network structures from dynamic and incomplete input data, and (3) providing a general framework to optimize the connectivity measures in the network.

It is a grand challenge to reveal the causal effects of DNA variants in complex phenotypes. Although statistical techniques can establish correlations between genotypes and phenotypes in Genome-Wide Association Studies (GWAS), they often fail when the variant is rare. The emerging Network-based Association Studies aim to address this shortcoming in statistical analysis, but are mainly applied to coding variations. Increasing evidences suggest that non-coding variants play critical roles in the etiology of complex diseases. However, few computational tools are available to study the effect of rare non-coding variants on phenotypes. Here we have developed a multiscale modeling variant-to-function-to-network framework VariFunNet to address these challenges. VariFunNet first predict the functional variations of molecular interactions, which result from the non-coding variants. Then we incorporate the genes associated with the functional variation into a tissue-specific gene network, and identify subnetworks that transmit the functional variation to molecular phenotypes. Finally, we quantify the functional implication of the subnetwork, and prioritize the association of the non-coding variants with the phenotype. We have applied VariFunNet to investigating the causal effect of rare non-coding variants on Alzheimer's disease (AD). Among top 21 ranked causal non-coding variants, 16 of them are directly supported by existing evidences. The remaining 5 novel variants dysregulate multiple downstream biological processes, all of which are associated with the pathology of AD. Furthermore, we propose potential new drug targets that may modulate diverse pathways responsible for AD. These findings may shed new light on discovering new biomarkers and therapies for the prevention, diagnosis, and treatment of AD. Our results suggest that multiscale modeling is a potentially powerful approach to studying causal genotype-phenotype associations.

The increasingly connected world has catalyzed the fusion of networks from different domains, which facilitates the emergence of a new network model-multi-layered networks. Examples of such kind of network systems include critical infrastructure networks, biological systems, organization-level collaborations, cross-platform e-commerce, and so forth. One crucial structure that distances multi-layered network from other network models is its cross-layer dependency, which describes the associations between the nodes from different layers. Needless to say, the cross-layer dependency in the network plays an essential role in many data mining applications like system robustness analysis and complex network control. However, it remains a daunting task to know the exact dependency relationships due to noise, limited accessibility, and so forth. In this article, we tackle the cross-layer dependency inference problem by modeling it as a collective collaborative filtering problem. Based on this idea, we propose an effective algorithm Fascinate that can reveal unobserved dependencies with linear complexity. Moreover, we derive Fascinate-ZERO, an online variant of Fascinate that can respond to a newly added node timely by checking its neighborhood dependencies. We perform extensive evaluations on real datasets to substantiate the superiority of our proposed approaches.

Networks are prevalent in many high impact domains. Moreover, cross-domain interactions are frequently observed in many applications, which naturally form the dependencies between different networks. Such kind of highly coupled network systems are referred to as multi-layered networks, and have been used to characterize various complex systems, including critical infrastructure networks, cyber-physical systems, collaboration platforms, biological systems, and many more. Different from single-layered networks where the functionality of their nodes is mainly affected by within-layer connections, multi-layered networks are more vulnerable to disturbance as the impact can be amplified through cross-layer dependencies, leading to the cascade failure to the entire system. To manipulate the connectivity in multi-layered networks, some recent methods have been proposed based on two-layered networks with specific types of connectivity measures. In this paper, we address the above challenges in multiple dimensions. First, we propose a family of connectivity measures (SUBLINE) that unifies a wide range of classic network connectivity measures. Third, we reveal that the connectivity measures in the SUBLINE family enjoy diminishing returns property, which guarantees a near-optimal solution with linear complexity for the connectivity optimization problem. Finally, we evaluate our proposed algorithm on real data sets to demonstrate its effectiveness and efficiency.

Multi-layered networks have recently emerged as a new network model, which naturally finds itself in many high-impact application domains, ranging from critical inter-dependent infrastructure networks, biological systems, organization-level collaborations, to cross-platform e-commerce, etc. Cross-layer dependency, which describes the dependencies or the associations between nodes across different layers/networks, often plays a central role in many data mining tasks on such multi-layered networks. Yet, it remains a daunting task to accurately know the cross-layer dependency a prior. In this paper, we address the problem of inferring the missing cross-layer dependencies on multi-layered networks. The key idea behind our method is to view it as a collective collaborative filtering problem. By formulating the problem into a regularized optimization model, we propose an effective algorithm to find the local optima with linear complexity. Furthermore, we derive an online algorithm to accommodate newly arrived nodes, whose complexity is just linear wrt the size of the neighborhood of the new node. We perform extensive empirical evaluations to demonstrate the effectiveness and the efficiency of the proposed methods.

Large graphs are prevalent in many applications and enable a variety of information dissemination processes, e.g., meme, virus, and influence propagation. How can we optimize the underlying graph structure to affect the outcome of such dissemination processes in a desired way (e.g., stop a virus propagation, facilitate the propagation of a piece of good idea, etc)? Existing research suggests that the leading eigenvalue of the underlying graph is the key metric in determining the so-called epidemic threshold for a variety of dissemination models. In this paper, we study the problem of how to optimally place a set of edges (e.g., edge deletion and edge addition) to optimize the leading eigenvalue of the underlying graph, so that we can guide the dissemination process in a desired way. We propose effective, scalable algorithms for edge deletion and edge addition, respectively. In addition, we reveal the intrinsic relationship between edge deletion and node deletion problems. Experimental results validate the effectiveness and efficiency of the proposed algorithms.

Given a large graph, like a computer communication network, which k nodes should we immunize (or monitor, or remove), to make it as robust as possible against a computer virus attack? This problem, referred to as the node immunization problem, is the core building block in many high-impact applications, ranging from public health, cybersecurity to viral marketing. A central component in node immunization is to find the best k bridges of a given graph. In this setting, we typically want to determine the relative importance of a node (or a set of nodes) within the graph, for example, how valuable (as a bridge) a person or a group of persons is in a social network. First of all, we propose a novel `bridging' score Dλ, inspired by immunology, and we show that its results agree with intuition for several realistic settings. Since the straightforward way to compute Dλ is computationally intractable, we then focus on the computational issues and propose a surprisingly efficient way (O(nk2+ m)) to estimate it. Experimental results on real graphs show that (1) the proposed `bridging' score gives mining results consistent with intuition; and (2) the proposed fast solution is up to seven orders of magnitude faster than straightforward alternatives.

Networks appear naturally in many high-impact real-world applications. In an increasingly connected and coupled world, the networks arising from many application domains are often collected from different channels, forming the so-called multi-layered networks, such as cyber-physical systems, organization-level collaboration platforms, critical infrastructure networks and many more. Compared with single-layered networks, multi-layered networks are more vulnerable as even a small disturbance on one supporting layer/network might cause a ripple effect to all the dependent layers, leading to a catastrophic/cascading failure of the entire system. The state-of-the-art has been largely focusing on modeling and manipulating the cascading effect of two-layered interdependent network systems for some specific type of network connectivity measure. This paper generalizes the challenge to multiple dimensions. First, we propose a new data model for multi-layered networks MULAN, which admits an arbitrary number of layers with a much more flexible dependency structure among different layers, beyond the current pair-wise dependency. Second, we unify a wide range of classic network connectivity measures SUBLINE. Third, we show that for any connectivity measure in the SUBLINE family, it enjoys the diminishing returns property which in turn lends itself to a family of provable near-optimal control algorithms with linear complexity. Finally, we conduct extensive empirical evaluations on real network data, to validate the effectiveness of the proposed algorithms.

Many important graph parameters can be expressed as eigen-functions of its adjacency matrix. Examples include epidemic threshold, graph robustness, etc. It is often of key importance to accurately monitor these parameters. For example, knowing that Ebola virus has already been brought to the US continent, to avoid the virus from spreading away, it is important to know which emerging connections among related people would cause great reduction on the epidemic threshold of the network. However, most, if not all, of the existing algorithms computing these measures assume that the input graph is static, despite the fact that almost all real graphs are evolving over time. In this paper, we propose two online algorithms to track the eigen-functions of a dynamic graph with linear complexity wrt the number of nodes and number of changed edges in the graph. The key idea is to leverage matrix perturbation theory to efficiently update the top eigen-pairs of the underlying graph without recomputing them from scratch at each time stamp. Experiment results demonstrate that our methods can reach up to 20× speedup with precision more than 80% for fairly long period of time.

In peer-to-peer streaming system, multicasting tree is essential to application performance and network transmission resource usage. Currently, available multicasting tree construction strategy optimize for source to client delay, load balance, etc. But network resource occupation of these strategy is not carefully studied. In this paper, network resource usage of application is analyzed. Then, metrics of network resource usage is proposed. Accordingly, Transmission Resource Saving Tree(TRST) is proposed. In order to make our experimental reliable, transmission delay and jitter are sampled from PlanetLab. Contrast experiments is carried out. According to the results, our proposed strategy consumes less network resources to serve the same set of peers.