10 November 2021 in IEEE Transactions on Knowledge and Data Engineering
Understanding in-network information diffusion is a fundamental problem in many applications and one of the primary challenges is to predict the information cascade size. Most of the existing models rely either on hypothesized point process (e.g., Poisson and Hawkes processes), or simply predict the information propagation via deep neural networks. However, they fail to simultaneously capture the underlying global and local structures of a cascade and the propagation uncertainty in the diffusion, which may result in unsatisfactory prediction performance. To address these, in this work we propose a novel probabilistic cascade prediction framework CasFlow : Hierarchical Cascade Normalizing Flows. CasFlow allows a non-linear information diffusion inference and models the information diffusion process by learning the latent representation of both the structural and temporal information. It is a pattern-agnostic model leveraging normalizing flows to learn the node-level and cascade-level latent factors in an unsupervised manner. In addition, CasFlow is capable of capturing both the cascade representation uncertainty and node infection uncertainty, while enabling hierarchical pattern learning of information diffusion. Extensive experiments conducted on real-world datasets demonstrate that CasFlow reduces the prediction error to 21.0% by only observing half an hour of cascades, compared to state-of-the-art approaches, while also enabling model interpretability.
28 February 2023 in IEEE Transactions on Knowledge and Data Engineering
Graph anomaly detection is attracting remarkable multidisciplinary research interests ranging from finance, healthcare, and social network analysis. Recent advances on graph neural networks have substantially improved the detection performance via semi-supervised representation learning. However, prior work suggests that deep graph-based methods tend to learn spurious correlations. As a result, they fail to generalize beyond training data distribution. In this article, we aim to identify structural and contextual anomaly nodes in an attributed graph. Based on our preliminary data analyses, spurious correlations can be eliminated with causal subgraph interventions. Therefore, we propose a new graph-based anomaly detection model that can learn causal relations for anomaly detection while generalizing to new environments. To handle situations with varying environments, we steer the generative model to manufacture synthetic environment features, which are exerted on realistic subgraphs to generate counterfactual subgraphs. Further, these counterfactual subgraphs help a few-shot anomaly detection model learn transferable and causal relations across different environments. The experiments on three real-world attributed graphs show that the proposed approach achieves the best performance compared to the state-of-the-art baselines and learns robust causal representations resistant to noises and spurious correlations.
13 April 2023 in IEEE Transactions on Knowledge and Data Engineering
Many deep (semi-) supervised neural network-based methods have been proposed for anomaly detection, tackling the issue of limited labeled data. They have shown good performance but still face two major challenges. First, insufficient labeled data limits their flexibility. Second, measuring the uncertainty of the prediction, especially when dealing with objects deviating largely from training data, has not been well studied. Another common reason preventing them from prevailing is that they learn a determined function to make predictions from the input. This usually makes the predicted results uncertain and lacks robustness. To address these problems, we propose a novel framework, incorporating the neural process into the semi-supervised anomaly detection paradigm and efficiently using unlabeled data and a handful of labeled data in training. Different from other methods, ours is equivalent to modeling the distribution of functions representing anomalous patterns according to the labeled data rather than learning a single determined function for anomaly detection. Our approach improves the flexibility and robustness under the condition of insufficient training data, and can measure the uncertainty of prediction results. Extensive experiments under real-world datasets demonstrate that our proposed method can significantly improve anomaly detection performance compared to several cutting-edge benchmarks.
18 March 2024 in Engineering Applications of Artificial Intelligence
10 April 2020 in IEEE Transactions on Knowledge and Data Engineering
With the rapid development of mobile technology, nowadays, people spend a large amount of time on mobile devices. The locations and contexts of users are easily accessed by mobile advertising brokers, and the brokers can send customers related location-based advertisements. In this paper, we consider an important location-based advertising problem, namely maximum utility advertisement assignment (MUAA) problem, with the estimation of the interests of customers and the contexts of the vendors, we want to maximize the overall utility of ads by determining the ads sent to each customer subject to the constraints of the capacities of customers, the distance ranges and the budgets of vendors. We prove that the MUAA problem is NP-hard and intractable. Thus, we propose one offline approach, namely the ${\sf reconciliation\ approach}$ , which has an approximation ratio of $(1-\epsilon)\cdot \theta$ . In addition, we also address the online scenario, in which customers arrive in a streaming fashion, with one novel online algorithm, namely the ${\sf online\ adaptive\ factor-aware\ approach}$ , which has a competitive ratio (compared to the optimal solution of the offline scenario) of $\frac{\ln (g)+1}{\theta }$ , $g>e$ , where $e$ is the base of the natural logarithm. Through extensive experiments, we demonstrate the efficiency and effectiveness of our proposed approaches over both real and synthetic datasets.