Search

Semi-supervised graph anomaly detection (GAD) has recently received increasing attention, which aims to distinguish anomalous patterns from graphs under the guidance of a moderate amount of labeled data and a large volume of unlabeled data. Although these proposed semi-supervised GAD methods have achieved great success, their superior performance will be seriously degraded when the provided labels are extremely limited due to some unpredictable factors. Besides, the existing methods primarily focus on anomaly detection in static graphs, and little effort was paid to consider the continuous evolution characteristic of graphs over time (dynamic graphs). To address these challenges, we propose a novel GAD framework (EL$^{2}$-DGAD) to tackle anomaly detection problem in dynamic graphs with extremely limited labels. Specifically, a transformer-based graph encoder model is designed to more effectively preserve evolving graph structures beyond the local neighborhood. Then, we incorporate an ego-context hypersphere classification loss to classify temporal interactions according to their structure and temporal neighborhoods while ensuring the normal samples are mapped compactly against anomalous data. Finally, the above loss is further augmented with an ego-context contrasting module which utilizes unlabeled data to enhance model generalization. Extensive experiments on four datasets and three label rates demonstrate the effectiveness of the proposed method in comparison to the existing GAD methods., Comment: Accepted by 30th International Conference on Database Systems for Advanced Applications (DASFAA 2025)

This paper investigates strategic investments needed to mitigate transition risks, particularly focusing on sectors significantly impacted by the shift to a low-carbon economy. It emphasizes the importance of tailored sector-specific strategies and the role of government interventions, such as carbon taxes and subsidies, in shaping corporate behavior. In providing a multi-period framework, this paper evaluates the economic and operational trade-offs companies face under four various decarbonization scenarios: immediate, quick, slow, and no transitions. The analysis provides practical insights for both policymakers and business leaders, demonstrating how regulatory frameworks and strategic investments can be aligned to manage transition risks while optimizing long-term sustainability effectively. The findings contribute to a deeper understanding of the economic impacts of regulatory policies and offer a comprehensive framework to navigate the complexities of transitioning to a low-carbon economy.

Few-shot graph anomaly detection (GAD) has recently garnered increasing attention, which aims to discern anomalous patterns among abundant unlabeled test nodes under the guidance of a limited number of labeled training nodes. Existing few-shot GAD approaches typically adopt meta-training methods trained on richly labeled auxiliary networks to facilitate rapid adaptation to target networks that possess sparse labels. However, these proposed methods often assume that the auxiliary and target networks exist in the same data distributions-an assumption rarely holds in practical settings. This paper explores a more prevalent and complex scenario of cross-domain few-shot GAD, where the goal is to identify anomalies within sparsely labeled target graphs using auxiliary graphs from a related, yet distinct domain. The challenge here is nontrivial owing to inherent data distribution discrepancies between the source and target domains, compounded by the uncertainties of sparse labeling in the target domain. In this paper, we propose a simple and effective framework, termed CDFS-GAD, specifically designed to tackle the aforementioned challenges. CDFS-GAD first introduces a domain-adaptive graph contrastive learning module, which is aimed at enhancing cross-domain feature alignment. Then, a prompt tuning module is further designed to extract domain-specific features tailored to each domain. Moreover, a domain-adaptive hypersphere classification loss is proposed to enhance the discrimination between normal and anomalous instances under minimal supervision, utilizing domain-sensitive norms. Lastly, a self-training strategy is introduced to further refine the predicted scores, enhancing its reliability in few-shot settings. Extensive experiments on twelve real-world cross-domain data pairs demonstrate the effectiveness of the proposed CDFS-GAD framework in comparison to various existing GAD methods., Comment: Accepted by 24th IEEE International Conference on Data Mining (ICDM 2024)

This paper extends the application of ESG score assessment methodologies from large corporations to individual farmers' production, within the context of climate change. Our proposal involves the integration of crucial agricultural sustainability variables into conventional personal credit evaluation frameworks, culminating in the formulation of a holistic sustainable credit rating referred to as the Environmental, Social, Economics (ESE) score. This ESE score is integrated into theoretical joint liability models, to gain valuable insights into optimal group sizes and individual-ESE score relationships. Additionally, we adopt a mean-variance utility function for farmers to effectively capture the risk associated with anticipated profits. Through a set of simulation exercises, the paper investigates the implications of incorporating ESE scores into credit evaluation systems, offering a nuanced comprehension of the repercussions under various climatic conditions.

To assess the impact of climate change on the Canadian economy, we investigate and model the relationship between seasonal climate variables and economic growth across provinces and economic sectors. We further provide projections of climate change impacts up to the year 2050, taking into account the diverse climate change patterns and economic conditions across Canada. Our results indicate that rising Fall temperature anomalies have a notable adverse impact on Canadian economic growth. Province-wide, Saskatchewan and Manitoba are anticipated to experience the most substantial declines, whereas British Columbia and the Maritime provinces will be less impacted. Industry-wide, Mining is projected to see the greatest benefits, while Agriculture and Manufacturing are projected to have the most significant downturns. The disparities of climate change effects between provinces and industries highlight the need for governments to tailor their policies accordingly, and offer targeted assistance to regions and industries that are particularly vulnerable in the face of climate change. Targeted approaches to climate change mitigation are likely to be more effective than one-size-fits-all policies for the whole economy., Comment: 25 pages, 7 figures

The widespread confusion among investors regarding Environmental, Social, and Governance (ESG) rankings assigned by rating agencies has underscored a critical issue in sustainable investing. To address this uncertainty, our research has devised methods that not only recognize this ambiguity but also offer tailored investment strategies for different investor profiles. By developing ESG ensemble strategies and integrating ESG scores into a Reinforcement Learning (RL) model, we aim to optimize portfolios that cater to both financial returns and ESG-focused outcomes. Additionally, by proposing the Double-Mean-Variance model, we classify three types of investors based on their risk preferences. We also introduce ESG-adjusted Capital Asset Pricing Models (CAPMs) to assess the performance of these optimized portfolios. Ultimately, our comprehensive approach provides investors with tools to navigate the inherent ambiguities of ESG ratings, facilitating more informed investment decisions., Comment: 36 pages, 2 figures, presented at Fields - Institute's Mathematics for Climate Change (MfCC) Network & Waterloo Institute for Complexity and Innovation (WICI): Math for Complex Climate Challenges Workshop, Waterloo, Canada; 26th International Congress on Insurance: Mathematics and Economics, Edinburgh, UK; and the 58th Actuarial Research Conference (ARC), Des Moines, Iowa, USA

Time series anomaly detection (TSAD) plays a vital role in many industrial applications. While contrastive learning has gained momentum in the time series domain for its prowess in extracting meaningful representations from unlabeled data, its straightforward application to anomaly detection is not without hurdles. Firstly, contrastive learning typically requires negative sampling to avoid the representation collapse issue, where the encoder converges to a constant solution. However, drawing from the same dataset for dissimilar samples is ill-suited for TSAD as most samples are ``normal'' in the training dataset. Secondly, conventional contrastive learning focuses on instance discrimination, which may overlook anomalies that are detectable when compared to their temporal context. In this study, we propose a novel approach, CNT, that incorporates a window-based contrastive learning strategy fortified with learnable transformations. This dual configuration focuses on capturing temporal anomalies in local regions while simultaneously mitigating the representation collapse issue. Our theoretical analysis validates the effectiveness of CNT in circumventing constant encoder solutions. Through extensive experiments on diverse real-world industrial datasets, we show the superiority of our framework by outperforming various baselines and model variants., Comment: Accepted by 2025 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2025)

Anomalies in univariate time series often refer to abnormal values and deviations from the temporal patterns from majority of historical observations. In multivariate time series, anomalies also refer to abnormal changes in the inter-series relationship, such as correlation, over time. Existing studies have been able to model such inter-series relationships through graph neural networks. However, most works settle on learning a static graph globally or within a context window to assist a time series forecasting task or a reconstruction task, whose objective is not tailored to explicitly detect the abnormal relationship. Some other works detect anomalies based on reconstructing or forecasting a list of inter-series graphs, which inadvertently weakens their power to capture temporal patterns within the data due to the discrete nature of graphs. In this study, we propose DyGraphAD, a multivariate time series anomaly detection framework based upon a list of dynamic inter-series graphs. The core idea is to detect anomalies based on the deviation of inter-series relationships and intra-series temporal patterns from normal to anomalous states, by leveraging the evolving nature of the graphs in order to assist a graph forecasting task and a time series forecasting task simultaneously. Our numerical experiments on real-world datasets demonstrate that DyGraphAD has superior performance than baseline anomaly detection approaches.

Traditionally stationarity refers to shift invariance of the distribution of a stochastic process. In this paper, we rediscover stationarity as a path property instead of a distributional property. More precisely, we characterize a set of paths denoted as $A$, which corresponds to the notion of stationarity. On one hand, the set $A$ is shown to be large enough, so that for any stationary process, almost all of its paths are in $A$. On the other hand, we prove that any path in $A$ will behave in the optimal way under any stationarity test satisfying some mild conditions. The results provide a unified framework to understand and assess the existing time series tests for stationarity, and can potentially lead to new families of stationarity tests., Comment: 21 pages