Linlin Yu, Xujiang Zhao, Dong Li, Yanchi Liu, Wei Cheng, Zhengzhang Chen, Chen Zhao, Feng Chen, Haifeng Chen. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Offline Reinforcement Learning (RL) has emerged as a promising paradigm to overcome the limitations of conventional RL methods that depend on extensive and often unsafe online interactions with the environment. By learning policies exclusively from pre-collected datasets, Offline RL aligns with the growing emphasis on data efficiency and safety in machine learning. However, existing off-policy RL algorithms encounter substantial difficulties when trained purely on offline data, primarily due to distributional shift between the training dataset and the learned policy. This issue becomes more pronounced with high-dimensional function approximation, leading to degraded performance and poor generalization. This survey provides a comprehensive overview of recent advances in Offline RL, with a particular focus on the challenges of distribution shift, generalization, and out-of-distribution (OOD) actions. We review the evolution of this field, discuss data limitations, and analyze the historical and theoretical foundations of distributional shift in Offline RL. Furthermore, we categorize existing approaches into four major groups including Q-value restriction methods, uncertainty-based Q-restriction methods, policy constraint methods, and uncertainty-based policy constraint methods, highlighting their core principles and practical implications. We also summarize common benchmarks such as D4RL, discuss dataset enhancement strategies, and examine evaluation metrics and computational efficiency. Through this analysis, the survey offers a unified perspective on current solutions and identifies open challenges, providing valuable guidance for advancing robust, generalizable, and trustworthy Offline RL in domains such as robotics, healthcare, and autonomous systems.

Accurate quantification of both aleatoric and epistemic uncertainties is essential when deploying Graph Neural Networks (GNNs) in high-stakes applications such as drug discovery and financial fraud detection, where reliable predictions are critical. Although Evidential Deep Learning (EDL) efficiently quantifies uncertainty using a Dirichlet distribution over predictive probabilities, existing EDL-based GNN (EGNN) models require modifications to the network architecture and retraining, failing to take advantage of pre-trained models. We propose a plug-and-play framework for uncertainty quantification in GNNs that works with pre-trained models without the need for retraining. Our Evidential Probing Network (EPN) uses a lightweight Multi-Layer-Perceptron (MLP) head to extract evidence from learned representations, allowing efficient integration with various GNN architectures. We further introduce evidence-based regularization techniques, referred to as EPN-reg, to enhance the estimation of epistemic uncertainty with theoretical justifications. Extensive experiments demonstrate that the proposed EPN-reg achieves state-of-the-art performance in accurate and efficient uncertainty quantification, making it suitable for real-world deployment.

Recent advancements in natural language processing, driven by Large Language Models (LLMs), have significantly improved text comprehension, enabling these models to handle complex tasks with greater efficiency. A key feature of LLMs is their ability to engage in contextual learning, which allows them to understand and apply instructions given in natural language to new scenarios without requiring additional training. This capability is particularly valuable in social media, where LLMs can be crucial in addressing challenges in explainable sexism detection. We hypothesize that by leveraging contextual learning capabilities, LLMs can provide clear, explainable insights into why certain content is flagged as problematic, thus enhancing transparency in the sexism detection process. To this end, we propose a Reinforcement Learning from Human Feedback (RLHF) based fine-tuning framework for sexism detection. We studied two well-known LLMs, Mistral-7B and LLaMA-3-8B, in zero-shot, supervised fine-tuning, and RLHF scenarios to conclude the superior ability of LLMs in sexism detection. The experimental results reported in this work, based on three tasks of Explainable Detection of Online Sexism (EDOS), highlight the importance of RLHF for building explainable systems in online discourse. Furthermore, we found that the LLaMA-3-8B model achieves the best results using the RLHF approach, scoring 0.8681 on Task A (binary sexism detection), 0.6829 on Task B (category classification of sexism), and 0.4722 on Task C (fine-grained sexism vectors) test sets.

In real-world applications, data-driven classifiers often grapple with a three-pronged challenge: data arrives in a continuous stream, most data in the wild are often unlabeled, and there is a critical need to maintain fairness in predictions across different sub-groups. Existing methods falter when addressing all these three factors concurrently. This work tackles this challenge by addressing a novel paradigm: Fairness-Aware Active Online Learning. We introduce a simple yet effective approach - FACTION, which actively selects the most crucial data points for labeling, going beyond traditional methods by considering both model uncertainty (epistemic uncertainty) and a newly introduced fairness notion derived from this very uncertainty. Additionally, FACTION leverages a system adept at identifying out-of-distribution samples within online learning environ-ments. Extensive evaluations on real-world datasets, coupled with theoretical analysis, demonstrate FACTION's effectiveness in handling this complex challenge. Our model demonstrably outperforms relevant baselines adapted for this new setting.

Federated Learning (FL) offers a promising approach for collaborative model training in healthcare while preserving data privacy. However, existing FL methods often fall short in addressing two critical challenges: client-level fairness and compounded uncertainty from data heterogeneity and privacy-preserving mechanisms. We propose fair-LDP, a fairness-aware Local Differential Privacy framework that promotes fairness and privacy via uncertainty-guided aggregation in federated healthcare AI. fair-LDP leverages evidential neural networks (ENNs) to quantify predictive uncertainty and introduces a novel strategy that uses uncertainty-driven local differential privacy to guide fairness-aware updates while preserving data privacy. This ensures equitable performance across clients with varying data quality while mitigating the influence of unreliable or outlier updates. fair-LDP incorporates an adaptive mechanism that adjusts each client's privacy budget based on model performance, balancing fairness, privacy, and accuracy. We evaluate fair-LDP on real-world healthcare datasets under both IID and non-IID settings. Our experimental results show that it consistently outperforms state-of-the-art fairness-aware and privacy-preserving FL baselines, with no added computational overhead, while maintaining privacy guarantees comparable to homomorphic encryption and secure multiparty computation. By integrating uncertainty modeling, fairness-aware aggregation, and adaptive local differential privacy, fair-LDP provides a practical and principled solution for responsible, equitable, and privacy-preserving federated learning in healthcare.

The fusion of raw sensor data to create a Bird's Eye View (BEV) representation is critical for autonomous vehicle planning and control. Despite the growing interest in using deep learning models for BEV semantic segmentation, anticipating segmentation errors and enhancing the explainability of these models remain underexplored. This paper introduces a comprehensive benchmark for predictive uncertainty quantification in BEV segmentation, evaluating multiple uncertainty quantification methods across three popular datasets with three representative network architectures. Our study focuses on the effectiveness of quantified uncertainty in detecting misclassified and out-of-distribution (OOD) pixels while also improving model calibration. Through empirical analysis, we uncover challenges in existing uncertainty quantification methods and demonstrate the potential of evidential deep learning techniques, which capture both aleatoric and epistemic uncertainty. To address these challenges, we propose a novel loss function, Uncertainty-Focal-Cross-Entropy (UFCE), specifically designed for highly imbalanced data, along with a simple uncertainty-scaling regularization term that improves both uncertainty quantification and model calibration for BEV segmentation.

As computers increasingly make decisions about who gets a loan, a job, or even bail, the expansion of AI algorithms has provoked public concern about ethical issues, and the need to understand what constitutes AI algorithms and how they make decisions becomes ever more pressing. For example, an increasing number of high-profile news reports that widely-used algorithms have unfairly discriminated against some groups of people (e.g., by gender and race) in parole decisions and other major life events. Focusing more attention on ethical bias in learning algorithms is key to unlocking the potential of automated decision systems while ensuring fairness and accountability so that everyone can advance equally in society. Ethical AI has become increasingly important and it has been attracting attention from academia and industry, due to its increased popularity in real-world applications with fairness concerns. It also places fundamental importance on ethical considerations in determining legitimate and illegitimate uses of AI. Organizations that apply ethical AI have clearly stated well-defined review processes to ensure adherence to legal guidelines. Therefore, the wave of research at the intersection of ethical AI in data mining and machine learning has also influenced other fields of science, including computer vision, natural language processing, reinforcement learning, and social science.

Uncertainty reasoning and quantification play a critical role in decision making across various domains, prompting increased attention from both academia and industry. As real-world applications become more complex and data-driven, effectively handling uncertainty becomes paramount for accurate and reliable decision making. This workshop focuses on the critical topics of uncertainty reasoning and quantification in decision making. It provides a platform for experts and researchers from diverse backgrounds to exchange ideas on cutting-edge techniques and challenges in this field. The interdisciplinary nature of uncertainty reasoning and quantification, spanning artificial intelligence, machine learning, statistics, risk analysis, and decision science, will be explored. The workshop aims to address the need for robust and interpretable methods for modeling and quantifying uncertainty, fostering reasoning decision-making in various domains. Participants will have the opportunity to share research findings and practical experiences, promoting collaboration and advancing decision-making practices under uncertainty.

Large Language Models (LLMs) offer promising capabilities for tackling complex reasoning tasks, including optimization problems. However, existing methods either rely on prompt engineering, which leads to poor generalization across problem types, or require costly supervised training. We introduce SolverLLM, a training-free framework that leverages test-time scaling to solve diverse optimization problems. Rather than solving directly, SolverLLM generates mathematical formulations and translates them into solver-ready code, guided by a novel Monte Carlo Tree Search (MCTS) strategy. To enhance the search process, we modify classical MCTS with (1) dynamic expansion for adaptive formulation generation, (2) prompt backpropagation to guide exploration via outcome-driven feedback, and (3) uncertainty backpropagation to incorporate reward reliability into decision-making. Experiments on six standard benchmark datasets demonstrate that SolverLLM outperforms both prompt-based and learning-based baselines, achieving strong generalization without additional training.

Generalizing to out-of-distribution data while ensuring model fairness presents a significant challenge in meta-learning. This problem aims to find fairness-aware, invariant classifier parameters trained on data from related training domains that experience distribution shifts in non-sensitive features and varying dependencies between model predictions and sensitive attributes. Such parameters enable classifiers to generalize effectively to unknown, distinct test domains. Existing state-of-the-art methods either focus on domain generalization without considering fairness or exclusively model domain shifts at varying fairness levels. In this paper, we introduce Fairness-Enhanced Meta-Learning for Domain Generalization (FEED), a novel framework that disentangles latent data representations into content, style, and sensitive vectors. This disentanglement approach promotes robust model generalization across diverse domains while rigorously upholding fairness constraints. Unlike conventional methods that concentrate on domain invariance or sensitivity to distributional shifts, our model embeds a fairnessaware invariance criterion within the meta-learning process, ensuring consistently fair learned parameters across domains with varied characteristics. Extensive experiments on multiple benchmarks validate our framework’s effectiveness, demonstrating not only superior accuracy and fairness maintenance but also substantial improvements over state-of-the-art methods in domain generalization tasks.

Real-world machine learning applications often face simultaneous covariate and semantic shifts, challenging traditional domain generalization and out-of-distribution (OOD) detection methods. We introduce Meta-learned Across Domain Out-of-distribution Detection (MADOD), a novel framework designed to address both shifts concurrently. MADOD leverages meta-learning and G-invariance to enhance model generalizability and OOD detection in unseen domains. Our key innovation lies in task construction: we randomly designate in-distribution classes as pseudo-OODs within each meta-learning task, simulating OOD scenarios using existing data. This approach, combined with energy-based regularization, enables the learning of robust, domain-invariant features while calibrating decision boundaries for effective OOD detection. Operating in a test domain-agnostic setting, MADOD eliminates the need for adaptation during inference, making it suitable for scenarios where test data is unavailable. Extensive experiments on real-world and synthetic datasets demonstrate MADOD’s superior performance in semantic OOD detection across unseen domains, achieving an AUPR improvement of 8.48% to 20.81%, while maintaining competitive in-distribution classification accuracy, representing a significant advancement in handling both covariate and semantic shifts.

Open-set domain generalization addresses a real-world challenge: training a model to generalize across unseen domains (domain generalization) while also detecting samples from unknown classes not encountered during training (open-set recognition). However, most existing approaches tackle these issues separately, limiting their practical applicability. To overcome this limitation, we propose a unified framework for open-set domain generalization by introducing Feature-space Semantic Invariance (FSI). FSI maintains semantic consistency across different domains within the feature space, enabling more accurate detection of OOD instances in unseen domains. Additionally, we adapt a generative model to produce synthetic data with novel domain styles or class labels, enhancing model robustness. Initial experiments show that our method improves AUROC by 9.1% to 18.9% on ColoredMNIST, while also significantly increasing in-distribution classification accuracy.

The Competitive Influence Maximization (CIM) problem involves entities competing to maximize influence in online social networks (OSNs). While Deep Reinforcement Learning (DRL) methods have shown promise, most assume binary user opinions and overlook behavioral factors. We introduce DRIM, a novel DRL-based CIM framework using Subjective Logic (SL) to incorporate user preferences and uncertainty, optimizing seed selection to spread true information while countering false information. DRIM’s Uncertainty-based Opinion Model (UOM) provides a realistic representation of user opinions. Results demonstrate that UOM maintains over 80% true influence against advanced misinformation, and DRIM outperforms state-of-the-art methods by up to 45% in influence and 77% in speed. DRIM also excels in limited-resource scenarios, networks with 10% invisibility, and when users are inclined to doubt true information.

Diffusion probabilistic models (DPMs) have become the state-of-the-art in high-quality image generation. However, DPMs have an arbitrary noisy latent space with no interpretable or controllable semantics. Although there has been significant research effort to improve image sample quality, there is little work on representation-controlled generation using diffusion models. Specifically, causal modeling and controllable counterfactual generation using DPMs is an underexplored area. In this work, we propose CausalDiffAE, a diffusion-based causal representation learning framework to enable counterfactual generation according to a specified causal model. Our key idea is to use an encoder to extract high-level semantically meaningful causal variables from high-dimensional data and model stochastic variation using reverse diffusion. We propose a causal encoding mechanism that maps high-dimensional data to causally related latent factors and parameterize the causal mechanisms among latent factors using neural networks. To enforce the disentanglement of causal variables, we formulate a variational objective and leverage auxiliary label information in a prior to regularize the latent space. We propose a DDIM-based counterfactual generation procedure subject to do-interventions. Finally, to address the limited label supervision scenario, we also study the application of CausalDiffAE when a part of the training data is unlabeled, which also enables granular control over the strength of interventions in generating counterfactuals during inference. We empirically show that CausalDiffAE learns a disentangled latent space and is capable of generating high-quality counterfactual images.

Text summarization, a key natural language generation (NLG) task, is vital in various domains.However, the high cost of inaccurate summaries in risk-critical applications, particularly those involving human-in-the-loop decision-making, raises concerns about the reliability of uncertainty estimation on text summarization (UE-TS) evaluation methods.This concern stems from the dependency of uncertainty model metrics on diverse and potentially conflicting NLG metrics.To address this issue, we introduce a comprehensive UE-TS benchmark incorporating 31 NLG metrics across four dimensions.The benchmark evaluates the uncertainty estimation capabilities of two large language models and one pre-trained language model on three datasets, with humanannotation analysis incorporated where applicable.We also assess the performance of 14 common uncertainty estimation methods within this benchmark.Our findings emphasize the importance of considering multiple uncorrelated NLG metrics and diverse uncertainty estimation methods to ensure reliable and efficient evaluation of UE-TS techniques.Our code and data are available here.

Deep neural networks (DNNs) have been shown to perform well on exclusive, multi-class classification tasks. However, when different classes have similar visual features, it becomes challenging for human annotators to differentiate them. When an image is ambiguous, such as a blurry one where an annotator can't distinguish between a husky and a wolf, it may be labeled with both classes: {husky, wolf}. This scenario necessitates the use of composite set labels. In this paper, we propose a novel framework called Hyper-Evidential Neural Network (HENN) that explicitly models predictive uncertainty caused by composite set labels in training data in the context of the belief theory called Subjective Logic (SL). By placing a Grouped Dirichlet distribution on the class probabilities, we treat predictions of a neural network as parameters of hyper-subjective opinions and learn the network that collects both single and composite evidence leading to these hyper-opinions by a deterministic DNN from data. We introduce a new uncertainty type called vagueness originally designed for hyper-opinions in SL to quantify composite classification uncertainty for DNNs. Our experiments prove that HENN outperforms its state-of-the-art counterparts based on four image datasets. The code and datasets are available at: https://shorturl.at/dhoqx.

Hyperspectral imaging (HSI) technology captures spectral information across a broad wavelength range, providing richer pixel features compared to traditional color images with only three channels. Although pixel classification in HSI has been extensively studied, especially using graph convolution neural networks (GCNs), quantifying epistemic and aleatoric uncertainties associated with the HSI classification (HSIC) results remains an unexplored area. These two uncertainties are effective for out-of-distribution (OOD) and misclassification detection, respectively. In this paper, we adapt two advanced uncertainty quantification models, evidential GCNs (EGCN) and graph posterior networks (GPN), designed for node classifications in graphs, into the realm of HSIC. We first reveal theoretically that a popular uncertainty cross-entropy (UCE) loss function is insufficient to produce good epistemic uncertainty when learning EGCNs. To mitigate the limitations, we propose two regularization terms. One leverages the inherent property of HSI data where each feature vector is a linear combination of the spectra signatures of the confounding materials, while the other is the total variation (TV) regularization to enforce the spatial smoothness of the evidence with edge-preserving. We demonstrate the effectiveness of the proposed regularization terms on both EGCN and GPN on three real-world HSIC datasets for OOD and misclassification detection tasks. The code is available at GitHub.

Accompanying the successes of learning-based defensive software vulnerability analyses is the lack of large and quality sets of labeled vulnerable program samples, which impedes further advancement of those defenses. Existing automated sample generation approaches have shown potentials yet still fall short of practical expectations due to the high noise in the generated samples. This paper proposes VGX, a new technique aimed for large-scale generation of high-quality vulnerability datasets. Given a normal program, VGX identifies the code contexts in which vulnerabilities can be injected, using a customized Transformer featured with a new value-flow-based position encoding and pre-trained against new objectives particularly for learning code structure and context. Then, VGX materializes vulnerability-injection code editing in the identified contexts using patterns of such edits obtained from both historical fixes and human knowledge about real-world vulnerabilities.

The endeavor to preserve the generalization of a fair and invariant classifier across domains, especially in the presence of distribution shifts, becomes a significant and intricate challenge in machine learning. In response to this challenge, numerous effective algorithms have been developed with a focus on addressing the problem of fairness-aware domain generalization. These algorithms are designed to navigate various types of distribution shifts, with a particular emphasis on covariate and dependence shifts. In this context, covariate shift pertains to changes in the marginal distribution of input features, while dependence shift involves alterations in the joint distribution of the label variable and sensitive attributes. In this paper, we introduce a simple but effective approach that aims to learn a fair and invariant classifier by simultaneously addressing both covariate and dependence shifts across domains. We assert the existence of an underlying transformation model can transform data from one domain to another, while preserving the semantics related to non-sensitive attributes and classes. By augmenting various synthetic data domains through the model, we learn a fair and invariant classifier in source domains. This classifier can then be generalized to unknown target domains, maintaining both model prediction and fairness concerns. Extensive empirical studies on four benchmark datasets demonstrate that our approach surpasses state-of-the-art methods.

Ethical AI has become increasingly important, and it has been attracting attention from academia and industry, due to its increased popularity in real-world applications with fairness concerns. It also places fundamental importance on ethical considerations in determining legitimate and illegitimate uses of AI. Organizations that apply ethical AI have clearly stated well-defined review processes to ensure adherence to legal guidelines. Therefore, the wave of research at the intersection of ethical AI in data mining and machine learning has also influenced other fields of science, including computer vision, natural language processing, reinforcement learning, and social science. Despite these successes, ethical AI still faces many challenges, such as a lack of interpretable and explainable methods for fairness-aware deep learning models, etc. Consequently, there is an urgent need to bring experts and researchers together at prestigious venues to discuss ethical AI, which has been rarely seen in previous KDD conferences. This workshop will provide a premium platform for both research and industry from different backgrounds to exchange ideas on opportunities, challenges, and cutting-edge techniques in ethical AI.

Uncertainty reasoning and quantification play a critical role in decision making across various domains, prompting increased attention from both academia and industry. As real-world applications become more complex and data-driven, effectively handling uncertainty becomes paramount for accurate and reliable decision making. This workshop focuses on the critical topics of uncertainty reasoning and quantification in decision making. It provides a platform for experts and researchers from diverse backgrounds to exchange ideas on cutting-edge techniques and challenges in this field. The interdisciplinary nature of uncertainty reasoning and quantification, spanning artificial intelligence, machine learning, statistics, risk analysis, and decision science, will be explored. The workshop aims to address the need for robust and interpretable methods for modeling and quantifying uncertainty, fostering reasoning decision-making in various domains. Participants will have the opportunity to share research findings and practical experiences, promoting collaboration and advancing decision-making practices under uncertainty.

The fairness-aware online learning framework has emerged as a potent tool within the context of continuous lifelong learning. In this scenario, the learner’s objective is to progressively acquire new tasks as they arrive over time, while also guaranteeing statistical parity among various protected sub-populations, such as race and gender when it comes to the newly introduced tasks. A significant limitation of current approaches lies in their heavy reliance on the i.i.d (independent and identically distributed) assumption concerning data, leading to a static regret analysis of the framework. Nevertheless, it’s crucial to note that achieving low static regret does not necessarily translate to strong performance in dynamic environments characterized by tasks sampled from diverse distributions. In this article, to tackle the fairness-aware online learning challenge in evolving settings, we introduce a unique regret measure, FairSAR, by incorporating long-term fairness constraints into a strongly adapted loss regret framework. Moreover, to determine an optimal model parameter at each time step, we introduce an innovative adaptive fairness-aware online meta-learning algorithm, referred to as FairSAOML. This algorithm possesses the ability to adjust to dynamic environments by effectively managing bias control and model accuracy. The problem is framed as a bi-level convex-concave optimization, considering both the model’s primal and dual parameters, which pertain to its accuracy and fairness attributes, respectively. Theoretical analysis yields sub-linear upper bounds for both loss regret and the cumulative violation of fairness constraints. Our experimental evaluation of various real-world datasets in dynamic environments demonstrates that our proposed FairSAOML algorithm consistently outperforms alternative approaches rooted in the most advanced prior online learning methods.

Early event detection aims to detect events even before the event is complete. However, most of the existing methods focus on an event with a single label but fail to be applied to cases with multiple labels. Another non-negligible issue for early event detection is a prediction with overconfidence due to the high vacuity uncertainty that exists in the early time series. It results in an over-confidence estimation and hence unreliable predictions. To this end, technically, we propose a novel framework, Multi-Label Temporal Evidential Neural Network (MTENN), for multi-label uncertainty estimation in temporal data. MTENN is able to quality predictive uncertainty due to the lack of evidence for multi-label classifications at each time stamp based on belief/evidence theory. In addition, we introduce a novel uncertainty estimation head (weighted binomial comultiplication (WBC)) to quantify the fused uncertainty of a sub-sequence for early event detection. We validate the performance of our approach with state-of-the-art techniques on real-world audio datasets.

Building new, powerful data-driven defenses against prevalent software vulnerabilities needs sizable, quality vulnerability datasets, so does large-scale benchmarking of existing defense solutions. Automatic data generation would promisingly meet the need, yet there is little work aimed to generate much-needed quality vulnerable samples. Meanwhile, existing similar and adaptable techniques suffer critical limitations for that purpose. In this paper, we present VULGEN, the first injection-based vulnerability-generation technique that is not limited to a particular class of vulnerabilities. VULGEN combines the strengths of deterministic (pattern-based) and probabilistic (deep-learning/DL-based) program transformation approaches while mutually overcoming respective weaknesses. This is achieved through close collaborations between pattern mining/application and DL-based injection localization, which separates the concerns with how and where to inject. By leveraging large, pretrained programming language modeling and only learning locations, VULGEN mitigates its own needs for quality vulnerability data (for training the localization model). Extensive evaluations show that VULGEN significantly outperforms a state-of-the-art (SOTA) pattern-based peer technique as well as both Transformer- and GNN-based approaches in terms of the percentages of generated samples that are vulnerable and those also exactly matching the ground truth (by 38.0-430.1% and 16.3-158.2%, respectively). The VULGEN-generated samples led to substantial performance improvements for two SOTA DL-based vulnerability detectors (by up to 31.8% higher in F1), close to those brought by the ground-truth real-world samples and much higher than those by the same numbers of existing synthetic samples.

Intent mining is critical for controlling the spread of false information across online social networks (OSNs). To this end, we develop deep reinforcement learning (DRL) agents guided by a delayed reward based on intent prediction using a classifier of long short-term memory (LSTM). Additionally, we incorporate an uncertainty-aware function that leverages subjective opinions derived from Subjective Logic (SL). Through evaluation using an annotated fake news tweet dataset, our results demonstrate that our intent classification framework surpasses competing methods in terms of intent accuracy. Our intent mining solutions using DRL algorithms can support effective and efficient intervention strategies for fake news spreading on OSNs.

Ethical AI has become increasingly important, and it has been attracting attention from academia and industry, due to its increased popularity in real-world applications with fairness concerns. It also places fundamental importance on ethical considerations in determining legitimate and illegitimate uses of AI. Organizations that apply ethical AI have clearly stated well-defined review processes to ensure adherence to legal guidelines. Therefore, the wave of research at the intersection of ethical AI in data mining and machine learning has also influenced other fields of science, including computer vision, natural language processing, reinforcement learning, and social science. Despite these successes, ethical AI still faces many challenges, such as a lack of interpretable and explainable methods for fairness-aware deep learning models, etc. Consequently, there is an urgent need to bring experts and researchers together at prestigious venues to discuss ethical AI, which has been rarely seen in previous KDD conferences. This workshop will provide a premium platform for both research and industry from different backgrounds to exchange ideas on opportunities, challenges, and cutting-edge techniques in ethical AI.

In the problem of online learning for changing environments, data are sequentially received one after another over time, and their distribution assumptions may vary frequently. Although existing methods demonstrate the effectiveness of their learning algorithms by providing a tight bound on either dynamic regret or adaptive regret, most of them completely ignore learning with model fairness, defined as the statistical parity across different sub-population (e.g., race and gender). Another drawback is that when adapting to a new environment, an online learner needs to update model parameters with a global change, which is costly and inefficient. Inspired by the sparse mechanism shift hypothesis [22], we claim that changing environments in online learning can be attributed to partial changes in learned parameters that are specific to environments and the rest remain invariant to changing environments. To this end, in this paper, we propose a novel algorithm under the assumption that data collected at each time can be disentangled with two representations, an environment-invariant semantic factor and an environment-specific variation factor. The semantic factor is further used for fair prediction under a group fairness constraint. To evaluate the sequence of model parameters generated by the learner, a novel regret is proposed in which it takes a mixed form of dynamic and static regret metrics followed by a fairness-aware long-term constraint. The detailed analysis provides theoretical guarantees for loss regret and violation of cumulative fairness constraints. Empirical evaluations on real-world datasets demonstrate our proposed method sequentially outperforms baseline methods in model accuracy and fairness.

Uncertainty reasoning and quantification play a critical role in decision making across various domains, prompting increased attention from both academia and industry. As real-world applications become more complex and data-driven, effectively handling uncertainty becomes paramount for accurate and reliable decision making. This workshop focuses on the critical topics of uncertainty reasoning and quantification in decision making. It provides a platform for experts and researchers from diverse backgrounds to exchange ideas on cutting-edge techniques and challenges in this field. The interdisciplinary nature of uncertainty reasoning and quantification, spanning artificial intelligence, machine learning, statistics, risk analysis, and decision science, will be explored. The workshop aims to address the need for robust and interpretable methods for modeling and quantifying uncertainty, fostering reasoning decision-making in various domains. Participants will have the opportunity to share research findings and practical experiences, promoting collaboration and advancing decision-making practices under uncertainty.

Deep neural networks have achieved significant success in the last decades, but they are not well-calibrated and often produce unreliable predictions. A large number of literature relies on uncertainty quantification to evaluate the reliability of a learning model, which is particularly important for applications of out-of-distribution (OOD) detection and misclassification detection. We are interested in uncertainty quantification for interdependent node-level classification. We start our analysis based on graph posterior networks (GPNs) that optimize the uncertainty cross-entropy (UCE)-based loss function. We describe the theoretical limitations of the widely-used UCE loss. To alleviate the identified drawbacks, we propose a distance-based regularization that encourages clustered OOD nodes to remain clustered in the latent space. We conduct extensive comparison experiments on eight standard datasets and demonstrate that the proposed regularization outperforms the state-of-the-art in both OOD detection and misclassification detection.

Model-Agnostic Meta-Learning (MAML), a popular gradient-based meta-learning framework, assumes that the contribution of each task or instance to the meta-learner is equal.Hence, it fails to address the domain shift between base and novel classes in few-shot learning. In this work, we propose a novel robust meta-learning algorithm, NESTEDMAML, which learns to assign weights to training tasks or instances. We con-sider weights as hyper-parameters and iteratively optimize them using a small set of validation tasks set in a nested bi-level optimization approach (in contrast to the standard bi-level optimization in MAML). We then applyNESTED-MAMLin the meta-training stage, which involves (1) several tasks sampled from a distribution different from the meta-test task distribution, or (2) some data samples with noisy labels.Extensive experiments on synthetic and real-world datasets demonstrate that NESTEDMAML efficiently mitigates the effects of ”unwanted” tasks or instances, leading to significant improvement over the state-of-the-art robust meta-learning methods.

We propose a new approach, the calibrated nonparametric scan statistic (CNSS), for more accurate detection of anomalous patterns in large-scale, real-world graphs. Scan statistics identify connected subgraphs that are interesting or unexpected through maximization of a likelihood ratio statistic; in particular, nonparametric scan statistics (NPSSs) identify subgraphs with a higher than expected proportion of individually significant nodes. However, we show that recently proposed NPSS methods are miscalibrated, failing to account for the maximization of the statistic over the multiplicity of subgraphs. This results in both reduced detection power for subtle signals, and low precision of the detected subgraph even for stronger signals. Thus we develop a new statistical approach to recalibrate NPSSs, correctly adjusting for multiple hypothesis testing and taking the underlying graph structure into account. While the recalibration, based on randomization testing, is computationally expensive, we propose both an efficient (approximate) algorithm and new, closed-form lower bounds (on the expected maximum proportion of significant nodes for subgraphs of a given size, under the null hypothesis of no anomalous patterns). These advances, along with the integration of recent core-tree decomposition methods, enable CNSS to scale to large real-world graphs, with substantial improvement in the accuracy of detected subgraphs. Extensive experiments on both semi-synthetic and real-world datasets are demonstrated to validate the effectiveness of our proposed methods, in comparison with state-of-the-art counterparts.

The goal of causal representation learning is to map low-level observations to high-level causal concepts to learn interpretable and robust representations for various downstream tasks. Latent variable models such as the variational autoencoder (VAE) are frequently leveraged to learn disentangled representations. However, there are often complex non-linear causal relationships underlying the observed data that cannot be captured through disentangled representations or linear dependence assumptions. Further, an independent conditional prior assumption can make learning causal dependencies in the latent space more challenging. We propose a framework, coined SCM-VAE, which uses apriori causal knowledge, a structural causal prior, and a non-linear additive noise structural causal model (SCM) to learn independent causal mechanisms and identifiable causal representations. We conduct theoretical analysis and perform experiments on synthetic and real-world datasets to show the improved quality of learned causal representations and robustness under interventions.

Adversarial machine learning has been extensively studied from perspectives of attack settings and defense strategies. However, existing adversarial training models fail to be adaptive and robust against new attacks during test time. In this paper, we propose a novel adversarially adaptive defense (AAD) framework based on adaptive training such that the trained prediction and detection models adapt at test time to new attacks. Our AAD structures the training data into groups and each group represents one attack scenario. Different from empirical risk minimization that trains a single robust model or learns an invariant feature space, our AAD learns a context vector from features of each batch during training and incorporates the learned context vector into both prediction and detection models. Thus, AAD can adapt at test time to new adversarial attacks. We formulate our problem by optimizing a joint loss from prediction, detection, and regularization via a multi-task learning framework. We conduct comprehensive empirical evaluations with popular adversarial attacks and defense strategies on two real-world datasets under different attack settings. Empirical results show that AAD achieves both high prediction and detection accuracy and significantly outperforms baselines.

Sound Event Early Detection (SEED) is an essential task in recognizing the acoustic environments and soundscapes. However, most of the existing methods focus on the offline sound event detection, which suffers from the over-confidence issue of early-stage event detection and usually yield unreliable results. To solve the problem, we propose a novel Polyphonic Evidential Neural Network (PENet) to model the evidential uncertainty of the class probability with Beta distribution. Specifically, we use a Beta distribution to model the distribution of class probabilities, and the evidential uncertainty enriches uncertainty representation with evidence information, which plays a central role in reliable prediction. To further improve the event detection performance, we design the backtrack inference method that utilizes both the forward and backward audio features of an ongoing event. Experiments on the DESED database show that the proposed method can simultaneously improve 13.0% and 3.8% in time delay and detection F1 score compared to the state-of-the-art methods.

Recent semi-supervised learning algorithms have demonstrated greater success with higher overall performance due to the use of better-unlabeled data representations. Nonetheless, recent research suggests that the performance of the SSL algorithm can be degraded when the unlabeled set contains out-of-distribution examples (OODs). This work addresses the following research question: How do out-of-distribution (OOD) data adversely affect semi-supervised learning algorithms? To answer this question, we investigate the critical causes of OOD’s negative effect on SSL algorithms. In particular, we found that 1) certain kinds of OOD data instances that are close to the decision boundary have a more significant impact on performance than those that are further away, and 2) Batch Normalization (BN), a popular module, may degrade rather than improve performance when the unlabeled set contains OODs. To address these challenges, we developed a unified weighted robust SSL framework that can be easily extended to many existing SSL algorithms and improve their robustness against OODs. Having identified the limitations of low-order approximations in bi-level optimization, we developed an efficient bi-level optimization algorithm that could accommodate high-order approximations of the objective and could scale to a large number of inner optimization steps to learn a massive number of weight parameters. Furthermore, we conduct a theoretical analysis of the impact of faraway OODs in the BN step and propose a weighted batch normalization (WBN) procedure that uses the weights estimated by the bi-level optimization problem in the BN step. Additionally, we discuss the connection between our approach and low-order approximation techniques. Our extensive experiments on synthetic and real-world datasets demonstrate that our proposed approach significantly enhances the robustness of four representative SSL algorithms against OODs compared to four state-of-the-art robust SSL strategies.

Few-shot classification (FSC) requires training models using a few (typically one to five) data points per class. Meta-learning has proven to be able to learn a parametrized model for FSC by training on various other classification tasks. In this work, we propose PLATINUM (semi-suPervised modeL Agnostic meTa learnIng usiNg sUbmodular Mutual information ), a novel semi-supervised model agnostic meta learning framework that uses the submodular mutual in- formation (SMI) functions to boost the perfor- mance of FSC. PLATINUM leverages unlabeled data in the inner and outer loop using SMI func- tions during meta-training and obtains richer meta- learned parameterizations. We study the per- formance of PLATINUM in two scenarios - 1) where the unlabeled data points belong to the same set of classes as the labeled set of a cer- tain episode, and 2) where there exist out-of- distribution classes that do not belong to the la- beled set. We evaluate our method on various settings on the miniImageNet, tieredImageNet and CIFAR-FS datasets. Our experiments show that PLATINUM outperforms MAML and semi- supervised approaches like pseduo-labeling for semi-supervised FSC, especially for small ratio of labeled to unlabeled samples.

The problem of algorithmic recourse has been explored for supervised machine learning models, to provide more interpretable, transparent and robust outcomes from decision support systems. An unexplored area is that of algorithmic recourse for anomaly detection, specifically for tabular data with only discrete feature values. Here the problem is to present a set of counterfactuals that are deemed normal by the underlying anomaly detection model so that applications can utilize this information for explanation purposes or to recommend countermeasures. We present an approach-Context preserving Algorithmic Recourse for Anomalies in Tabular data(CARAT), that is effective, scalable, and agnostic to the underlying anomaly detection model. CARAT uses a transformer based encoder-decoder model to explain an anomaly by finding features with low likelihood. Subsequently semantically coherent counterfactuals are generated by modifying the highlighted features, using the overall context of features in the anomalous instance(s). Extensive experiments help demonstrate the efficacy of CARAT.

Ethical AI has become increasingly important and it has been attracting attention from academia and industry, due to its increased popularity in real-world applications with fairness concerns. It also places fundamental importance on ethical considerations in determining legitimate and illegitimate uses of AI. Organizations that apply ethical AI have clearly stated well-defined review processes to ensure adherence to legal guidelines. Therefore, the wave of research at the intersection of ethical AI in data mining and machine learning has also influenced other fields of science, including computer vision, natural language processing, reinforcement learning, and social science. Despite these successes, ethical AI still faces many challenges. Consequently, there is an urgent need to bring experts and researchers together at prestigious venues to discuss ethical AI, which has been rarely seen in previous KDD conferences. This workshop will provide a premium platform for both research and industry from different backgrounds to exchange ideas on opportunities, challenges, and cutting-edge techniques in ethical AI.

The fairness-aware online learning framework has arisen as a powerful tool for the continual lifelong learning setting. The goal for the learner is to sequentially learn new tasks where they come one after another over time and the learner ensures the statistic parity of the new coming task across different protected sub-populations (e.g. race and gender). A major drawback of existing methods is that they make heavy use of the i.i.d assumption for data and hence provide static regret analysis for the framework. However, low static regret cannot imply a good performance in changing environments where tasks are sampled from heterogeneous distributions. To address the fairness-aware online learning problem in changing environments, in this paper, we first construct a novel regret metric FairSAR by adding long-term fairness constraints onto a strongly adapted loss regret. Furthermore, to determine a good model parameter at each round, we propose a novel adaptive fairness-aware online meta-learning algorithm, namely FairSAOML, which is able to adapt to changing environments in both bias control and model precision. The problem is formulated in the form of a bi-level convex-concave optimization with respect to the model's primal and dual parameters that are associated with the model's accuracy and fairness, respectively. The theoretic analysis provides sub-linear upper bounds for both loss regret and violation of cumulative fairness constraints. Our experimental evaluation on different real-world datasets with settings of changing environments suggests that the proposed FairSAOML significantly outperforms alternatives based on the best prior online learning approaches.

The availability of large-scale, realistic vulnerability datasets is essential both for benchmarking existing techniques and for developing effective new data-driven approaches for software security. Yet such datasets are critically lacking. A promising solution is to generate such datasets by injecting vulnerabilities into real-world programs, which are richly available. Thus, in this paper, we explore the feasibility of vulnerability injection through neural code editing. With a synthetic dataset and a real-world one, we investigate the potential and gaps of three state-of-the-art neural code editors for vulnerability injection. We find that the studied editors have critical limitations on the real-world dataset, where the best accuracy is only 10.03%, versus 79.40% on the synthetic dataset. While the graph-based editors are more effective (successfully injecting vulnerabilities in up to 34.93% of real-world testing samples) than the sequence-based one (0 success), they still suffer from complex code structures and fall short for long edits due to their insufficient designs of the preprocessing and deep learning (DL) models. We reveal the promise of neural code editing for generating realistic vulnerable samples, as they help boost the effectiveness of DL-based vulnerability detectors by up to 49.51% in terms of F1 score. We also provide insights into the gaps in current editors (e.g., they are good at deleting but not at replacing code) and actionable suggestions for addressing them (e.g., designing effective editing primitives).

The forecasting of significant societal events such as civil unrest and economic crisis is an interesting and challenging problem which requires both timeliness, precision, and comprehensiveness. Significant societal events are influenced and indicated jointly by multiple aspects of a society, including its economics, politics, and culture. Traditional forecasting methods based on a single data source find it hard to cover all these aspects comprehensively, thus limiting model performance. Multi-source event forecasting has proven promising but still suffers from several challenges, including (1) geographical hierarchies in multi-source data features, (2) hierarchical missing values, (3) characterization of structured feature sparsity, and (4) difficulty in model’s online update with incomplete multiple sources. This article proposes a novel feature learning model that concurrently addresses all the above challenges. Specifically, given multi-source data from different geographical levels, we design a new forecasting model by characterizing the lower-level features’ dependence on higher-level features. To handle the correlations amidst structured feature sets and deal with missing values among the coupled features, we propose a novel feature learning model based on an N th-order strong hierarchy and fused-overlapping group Lasso. An efficient algorithm is developed to optimize model parameters and ensure global optima. More importantly, to enable the model update in real time, the online learning algorithm is formulated and active set techniques are leveraged to resolve the crucial challenge when new patterns of missing features appear in real time. Extensive experiments on 10 datasets in different domains demonstrate the effectiveness and efficiency of the proposed models.

Traditional deep neural networks (NNs) have significantly contributed to the state-of-the-art performance in the task of classification under various application domains. However, NNs have not considered inherent uncertainty in data associated with the class probabilities where misclassification under uncertainty may easily introduce high risk in decision making in real-world contexts (e.g., misclassification of objects in roads leads to serious accidents). Unlike Bayesian NN that indirectly infer uncertainty through weight uncertainties, evidential NNs (ENNs) have been recently proposed to explicitly model the uncertainty of class probabilities and use them for classification tasks. An ENN offers the formulation of the predictions of NNs as subjective opinions and learns the function by collecting an amount of evidence that can form the subjective opinions by a deterministic NN from data. However, the ENN is trained as a black box without explicitly considering inherent uncertainty in data with their different root causes, such as vacuity (i.e., uncertainty due to a lack of evidence) or dissonance (i.e., uncertainty due to conflicting evidence). By considering the multidimensional uncertainty, we proposed a novel uncertainty-aware evidential NN called WGAN-ENN (WENN) for solving an out-of-distribution (OOD) detection problem. We took a hybrid approach that combines Wasserstein Generative Adversarial Network (WGAN) with ENNs to jointly train a model with prior knowledge of a certain class, which has high vacuity for OOD samples. Via extensive empirical experiments based on both synthetic and real-world datasets, we demonstrated that the estimation of uncertainty by WENN can significantly help distinguish OOD samples from boundary samples. WENN outperformed in OOD detection when compared with other competitive counterparts.

Multiple Instance Learning (MIL) provides a promising solution to many real-world problems, where labels are only available at the bag level but missing for instances due to a high labeling cost. As a powerful Bayesian non-parametric model, Gaussian Processes (GP) have been extended from classical supervised learning to MIL settings, aiming to identify the most likely positive (or least negative) instance from a positive (or negative) bag using only the bag-level labels. However, solely focusing on a single instance in a bag makes the model less robust to outliers or multi-modal scenarios, where a single bag contains a diverse set of positive instances. We propose a general GP mixture framework that simultaneously considers multiple instances through a latent mixture model. By adding a top-k constraint, the framework is equivalent to choosing the top-k most positive instances, making it more robust to outliers and multimodal scenarios. We further introduce a Distributionally Robust Optimization (DRO) constraint that removes the limitation of specifying a fix k value. To ensure the prediction power over high-dimensional data (e.g., videos and images) that are common in MIL, we augment the GP kernel with fixed basis functions by using a deep neural network to learn adaptive basis functions so that the covariance structure of high-dimensional data can be accurately captured. Experiments are conducted on highly challenging real-world video anomaly detection tasks to demonstrate the effectiveness of the proposed model.

Recent multilingual pre-trained language models have achieved remarkable zero-shot performance, where the model is only finetuned on one source language and directly evaluated on target languages.In this work, we propose a self-learning framework that further utilizes unlabeled data of target languages, combined with uncertainty estimation in the process to select high-quality silver labels.Three different uncertainties are adapted and analyzed specifically for the cross lingual transfer: Language Heteroscedastic/Homoscedastic Uncertainty (LEU/LOU), Evidential Uncertainty (EVI).We evaluate our framework with uncertainties on two cross-lingual tasks including Named Entity Recognition (NER) and Natural Language Inference (NLI) covering 40 languages in total, which outperforms the baselines significantly by 10 F1 on average for NER and 2.5 accuracy score for NLI.

In contrast to offline working fashions, two research paradigms are devised for online learning: (1) Online Meta-Learning (OML)[6, 20, 26] learns good priors over model parameters (or learning to learn) in a sequential setting where tasks are revealed one after another. Although it provides a sub-linear regret bound, such techniques completely ignore the importance of learning with fairness which is a significant hallmark of human intelligence. (2) Online Fairness-Aware Learning [1, 8, 21]. This setting captures many classification problems for which fairness is a concern. But it aims to attain zero-shot generalization without any task-specific adaptation. This therefore limits the capability of a model to adapt onto newly arrived data. To overcome such issues and bridge the gap, in this paper for the first time we proposed a novel online meta-learning algorithm, namely FFML, which is under the setting of unfairness prevention. The key part of FFML is to learn good priors of an online fair classification model's primal and dual parameters that are associated with the model's accuracy and fairness, respectively. The problem is formulated in the form of a bi-level convex-concave optimization. The theoretic analysis provides sub-linear upper bounds O(log T)for loss regret and O(√log T)violation of cumulative fairness constraints. Our experiments demonstrate the versatility of FFML by applying it to classification on three real-world datasets and show substantial improvements over the best prior work on the tradeoff between fairness and classification accuracy.

Semi-supervised learning (SSL) algorithms have had great success in recent years in limited labeled data regimes. However, the current state-of-the-art SSL algorithms are computationally expensive and entail significant compute time and energy requirements. This can prove to be a huge limitation for many smaller companies and academic groups. Our main insight is that training on a subset of unlabeled data instead of entire unlabeled data enables the current SSL algorithms to converge faster, significantly reducing computational costs. In this work, we propose RETRIEVE, a coreset selection framework for efficient and robust semi-supervised learning. RETRIEVE selects the coreset by solving a mixed discrete-continuous bi-level optimization problem such that the selected coreset minimizes the labeled set loss. We use a one-step gradient approximation and show that the discrete optimization problem is approximately submodular, enabling simple greedy algorithms to obtain the coreset. We empirically demonstrate on several real-world datasets that existing SSL algorithms like VAT, Mean-Teacher, FixMatch, when used with RETRIEVE, achieve a) faster training times, b) better performance when unlabeled data consists of Out-of-Distribution (OOD) data and imbalance. More specifically, we show that with minimal accuracy degradation, RETRIEVE achieves a speedup of around $3\times$ in the traditional SSL setting and achieves a speedup of $5\times$ compared to state-of-the-art (SOTA) robust SSL algorithms in the case of imbalance and OOD data. RETRIEVE is available as a part of the CORDS toolkit: https://github.com/decile-team/cords.

A burst event on a social graph is usually framed as an anomalous and unexpected pattern that is characterized as a compact or correlated subset of affected vertices, which is a subgraph. Subgraph detection becomes a serious problem when social graphs involve multiple attributes (i.e., multivariate graph). Most existing methods are not capable of handling the feature selection and subgraph detection problems simultaneously on the multivariate graph. In this article, we propose multivariate anomalous subgraph scanning (MASS), a generic model that detects anomalous events on the multivariate social graph. First, we reformulate the traditional nonparametric statistics as a new statistical objective function that simultaneously measures the significance of a vertices subset and an attributes subset to generate an indicator of ongoing or upcoming events. Then, we reformulate the objective function as the difference between two bisubmodular functions and approximate it with a bisubmodular objective function, which can be optimized in linear time, with an analysis of its theoretical properties. We demonstrate the performance of our proposed method using two burst event detection and prediction tasks from the real world.

Mobile devices have been an integral part of our everyday lives. Users’ increasing interaction with mobile devices brings in significant concerns on various types of potential privacy leakage, among which location privacy draws the most attention. Specifically, mobile users’ trajectories constructed by location data may be captured by adversaries to infer sensitive information. In previous studies, differential privacy has been utilized to protect published trajectory data with rigorous privacy guarantee. Strong protection provided by differential privacy distorts the original locations or trajectories using stochastic noise to avoid privacy leakage. In this article, we propose a novel location inference attack framework, iTracker, which simultaneously recovers multiple trajectories from differentially private trajectory data using the structured sparsity model. Compared with the traditional recovery methods based on single trajectory prediction, iTracker, which takes advantage of the correlation among trajectories discovered by the structured sparsity model, is more effective in recovering multiple private trajectories simultaneously. iTracker successfully attacks the existing privacy protection mechanisms based on differential privacy. We theoretically demonstrate the near-linear runtime of iTracker, and the experimental results using two real-world datasets show that iTracker outperforms existing recovery algorithms in recovering multiple trajectories.

Using unreliable information sources generating conflicting evidence may lead to a large uncertainty, which significantly hurts the decision making process. Recently, many approaches have been taken to integrate conflicting data from multiple sources and/or fusing conflicting opinions from different entities. To explicitly deal with uncertainty, a belief model called Subjective Logic (SL), as a variant of Dumpster-Shafer Theory, has been proposed to represent subjective opinions and to merge multiple opinions by offering a rich volume of fusing operators, which have been used to solve many opinion inference problems in trust networks. However, the operators of SL are known to be lack of scalability in inferring unknown opinions from large network data as a result of the sequential procedures of merging multiple opinions. In addition, SL does not consider deriving opinions in the presence of conflicting evidence. In this work, we propose a hybrid inference method that combines SL and Probabilistic Soft Logic (PSL), namely, Collective Subjective Plus, CSL + , which is resistible to highly conflicting evidence or a lack of evidence. PSL can reason a belief in a collective manner to deal with large-scale network data, allowing high scalability based on relationships between opinions. However, PSL does not consider an uncertainty dimension in a subjective opinion. To take benefits from both SL and PSL, we proposed a hybrid approach called CSL + for achieving high scalability and high prediction accuracy for unknown opinions with uncertainty derived from a lack of evidence and/or conflicting evidence. Through the extensive experiments on four semi-synthetic and two real-world datasets, we showed that the CSL + outperforms the state-of-the-art belief model (i.e., SL), probabilistic inference models (i.e., PSL, CSL), and deep learning model (i.e., GCN-VAE-opinion) in terms of prediction accuracy, computational complexity, and real running time.

The problem of learning to generalize on unseen classes during the training step, also known as few-shot classification, has attracted considerable attention. Initialization based methods, such as the gradient-based model agnostic meta-learning (MAML) [1], tackle the few-shot learning problem by “learning to fine-tune”. The goal of these approaches is to learn proper model initialization, so that the classifiers for new classes can be learned from a few labeled examples with a small number of gradient update steps. Few shot meta-learning is well-known with its fast-adapted capability and accuracy generalization onto unseen tasks [2]. Learning fairly with unbiased outcomes is another significant hallmark of human intelligence, which is rarely touched in few-shot meta-learning. In this work, we propose a Primal-Dual Fair Meta-learning framework, namely PDFM, which learns to train fair machine learning models using only a few examples based on data from related tasks. The key idea is to learn a good initialization of a fair model's primal and dual parameters so that it can adapt to a new fair learning task via a few gradient update steps. Instead of manually tuning the dual parameters as hyperparameters via a grid search, PDFM optimizes the initialization of the primal and dual parameters jointly for fair meta-learning via a subgradient primal-dual approach. We further instantiate an example of bias controlling using decision boundary covariance (DBC) [3] as the fairness constraint for each task, and demonstrate the versatility of our proposed approach by applying it to classification on a variety of three realworld datasets. Our experiments show substantial improvements over the best prior work for this setting. Our code and datasets are available at https://github.com/charliezhaoyinpeng/PDFM.git.

We present a novel multi-source uncertainty prediction approach that enables deep learning (DL) models to be actively trained with much less labeled data. By leveraging the second-order uncertainty representation provided by subjective logic (SL), we conduct evidence-based theoretical analysis and formally decompose the predicted entropy over multiple classes into two distinct sources of uncertainty: vacuity and dissonance, caused by lack of evidence and conflict of strong evidence, respectively. The evidence based entropy decomposition provides deeper insights on the nature of uncertainty, which can help effectively explore a large and high-dimensional unlabeled data space. We develop a novel loss function that augments DL based evidence prediction with uncertainty anchor sample identification. The accurately estimated multiple sources of uncertainty are systematically integrated and dynamically balanced using a data sampling function for label-efficient active deep learning (ADL). Experiments conducted over both synthetic and real data and comparison with competitive AL methods demonstrate the effectiveness of the proposed ADL model.

Thanks to graph neural networks (GNNs), semi-supervised node classification has shown the state-of-the-art performance in graph data. However, GNNs have not considered different types of uncertainties associated with class probabilities to minimize risk of increasing misclassification under uncertainty in real life. In this work, we propose a multi-source uncertainty framework using a GNN that reflects various types of predictive uncertainties in both deep learning and belief/evidence theory domains for node classification predictions. By collecting evidence from the given labels of training nodes, the Graph-based Kernel Dirichlet distribution Estimation (GKDE) method is designed for accurately predicting node-level Dirichlet distributions and detecting out-of-distribution (OOD) nodes. We validated the outperformance of our proposed model compared to the state-of-the-art counterparts in terms of misclassification detection and OOD detection based on six real network datasets. We found that dissonance-based detection yielded the best results on misclassification detection while vacuity-based detection was the best for OOD detection. To clarify the reasons behind the results, we provided the theoretical proof that explains the relationships between different types of uncertainties considered in this work.

The motives and means of explicit state censorship have been well studied, both quantitatively and qualitatively. Self-censorship by media outlets, however, has not received nearly as much attention, mostly because it is difficult to systematically detect. We develop a novel approach to identify news media self-censorship by using social media as a sensor. We develop a hypothesis testing framework to identify and evaluate censored clusters of keywords and a near-linear-time algorithm (called GraphDPD) to identify the highest scoring clusters as indicators of censorship. We evaluate the accuracy of our framework, versus other state-of-the-art algorithms, using both semi-synthetic and real-world data from Mexico and Venezuela during Year 2014. These tests demonstrate the capacity of our framework to identify self-censorship, and provide an indicator of broader media freedom. The results of this study lay the foundation for detection, study, and policy-response to self-censorship.

Forecasting spatial societal events in social media is significant and challenging. Most existing methods consider the frequencies of keywords or n-grams to be features, but have not explored the exponentially large space of the conjunctions of those features, such as keyword co-occurrence in messages, which can serve as crucial precursor rules. Due to the inherent exponential complexity of ensemble rule learning, existing work typically adopts greedy/heuristic strategies. This means that they cannot guarantee the solution's optimality, which would require a considerably more sophisticated model for spatial event forecasting, while still suffering from major challenges: 1) Exponentially-dimensional feature learning with distant supervision, 2) Numerical values of conjunctive features, and 3) Spatially heterogeneous conjunction patterns. To concurrently address all these challenges with a theoretical guarantee, we propose a novel spatial event forecasting model which learns numerical conjunctive features efficiently. Specifically, to consider their magnitude, traditional Boolean rules are innovatively generalized to deal with numerical conjunctive features with amenable computational properties. To handle the geographical similarity and heterogeneity in numerical conjunctive feature learning, we propose a new model that implements through a new bi-space hierarchical sparsity regularization for locations and features. Moreover, we propose a new algorithm to optimize the model parameters and prove that it enjoys theoretical guarantees for both the error bounds and time efficiency. Extensive experiments on multiple datasets demonstrate the effectiveness and efficiency of the proposed method.

Inference of unknown opinions with uncertain, adversarial (e.g., incorrect or conflicting) evidence in large datasets is not a trivial task. Without proper handling, it can easily mislead decision making in data mining tasks. In this work, we propose a highly scalable opinion inference probabilistic model, namely Adversarial Collective Opinion Inference (Adv-COI), which provides a solution to infer unknown opinions with high scalability and robustness under the presence of uncertain, adversarial evidence by enhancing Collective Subjective Logic (CSL) which is developed by combining SL and Probabilistic Soft Logic (PSL). The key idea behind the Adv-COI is to learn a model of robust ways against uncertain, adversarial evidence which is formulated as a min-max problem. We validate the out-performance of the Adv-COI compared to baseline models and its competitive counterparts under possible adversarial attacks on the logic-rule based structured data and white and black box adversarial attacks under both clean and perturbed semi-synthetic and real-world datasets in three real world applications. The results show that the Adv-COI generates the lowest mean absolute error in the expected truth probability while producing the lowest running time among all.

We propose a generalized optimization framework for detecting anomalous patterns (subgraphs that are interesting or unexpected) in interdependent networks, such as multi-layer networks, temporal networks, networks of networks, and many others. We frame the problem as a non-convex optimization that has a general nonlinear score function and a set of block-structured and non-convex constraints. We develop an effective, efficient, and parallelizable projection-based algorithm, namely Graph Block-structured Gradient Projection (GBGP), to solve the problem. It is proved that our algorithm 1) runs in nearly-linear time on the network size, and 2) enjoys a theoretical approximation guarantee. Moreover, we demonstrate how our framework can be applied to two very practical applications, and we conduct comprehensive experiments to show the effectiveness and efficiency of our proposed algorithm.

In this work, we develop a novel fairness learning approach for multi-task regression models based on a biased training dataset, using a popular rank-based non-parametric independence test, i.e., Mann Whitney U statistic, for measuring the dependency between target variable and protected variables. To solve this learning problem efficiently, we first reformulate the problem as a new non-convex optimization problem, in which a non-convex constraint is defined based on group-wise ranking functions of individual objects. We then develop an efficient model-training algorithm based on the framework of non-convex alternating direction method of multipliers (NC-ADMM), in which one of the main challenges is to implement an efficient projection oracle to the preceding non-convex set defined based on ranking functions. Through the extensive experiments on both synthetic and real-world datasets, we validated the out-performance of our new approach against several state-of-the-art competitive methods on several popular metrics relevant to fairness learning.

Stochastic optimization algorithms update models with cheap per-iteration costs sequentially, which makes them amenable for large-scale data analysis. Such algorithms have been widely studied for structured sparse models where the sparsity information is very specific, e.g., convex sparsity-inducing norms or $\ell^0$-norm. However, these norms cannot be directly applied to the problem of complex (non-convex) graph-structured sparsity models, which have important application in disease outbreak and social networks, etc. In this paper, we propose a stochastic gradient-based method for solving graph-structured sparsity constraint problems, not restricted to the least square loss. We prove that our algorithm enjoys a linear convergence up to a constant error, which is competitive with the counterparts in the batch learning setting. We conduct extensive experiments to show the efficiency and effectiveness of the proposed algorithms.

Spatio-temporal societal event forecasting, which has traditionally been prohibitively challenging, is now becoming possible and experiencing rapid growth thanks to the big data from Open Source Indicators (OSI) such as social media, news sources, blogs, economic indicators, and other meta-data sources. Spatio-temporal societal event forecasting and their precursor discovery benefit the society by providing insight into events such as political crises, humanitarian crises, mass violence, riots, mass migrations, disease outbreaks, economic instability, resource shortages, natural disasters, and others. In contrast to traditional event detection that identifies ongoing events, event forecasting focuses on predicting future events yet to happen. Also different from traditional spatio-temporal predictions on numerical indices, spatio-temporal event forecasting needs to leverage the heterogeneous information from OSI to discover the predictive indicators and mappings to future societal events. While studying large scale societal events, policy makers and practitioners aim to identify precursors to such events to help understand causative attributes and ensure accountability. The resulting problems typically require the predictive modeling techniques that can jointly handle semantic, temporal, and spatial information, and require a design of efficient and interpretable algorithms that scale to high-dimensional large real-world datasets.

Online learning algorithms update models via one sample per iteration, thus efficient to process large-scale datasets and useful to detect malicious events for social benefits, such as disease outbreak and traffic congestion on the fly. However, existing algorithms for graph-structured models focused on the offline setting and the least square loss, incapable for online setting, while methods designed for online setting cannot be directly applied to the problem of complex (usually non-convex) graph-structured sparsity model. To address these limitations, in this paper we propose a new algorithm for graph-structured sparsity constraint problems under online setting, which we call GraphDA. The key part in GraphDA is to project both averaging gradient (in dual space) and primal variables (in primal space) onto lower dimensional subspaces, thus capturing the graph-structured sparsity effectively. Furthermore, the objective functions assumed here are generally convex so as to handle different losses for online learning settings. To the best of our knowledge, GraphDA is the first online learning algorithm for graph-structure constrained optimization problems. To validate our method, we conduct extensive experiments on both benchmark graph and real-world graph datasets. Our experiment results show that, compared to other baseline methods, GraphDA not only improves classification performance, but also successfully captures graph-structured features more effectively, hence stronger interpretability.

One fundamental task in network analysis is detecting “hotspots” or “anomalies” in the network; that is, detecting subgraphs where there is significantly more activity than one would expect given historical data or some baseline process. Scan statistics is one popular approach used for anomalous subgraph detection. This methodology involves maximizing a score function over all connected subgraphs, which is a challenging computational problem. A number of heuristics have been proposed for these problems, but they do not provide any quality guarantees. Here, we propose a framework for designing algorithms for optimizing a large class of scan statistics for networks, subject to connectivity constraints. Our algorithms run in time that scales linearly on the size of the graph and depends on a parameter we call the “effective solution size,” while providing rigorous approximation guarantees. In contrast, most prior methods have super-linear running times in terms of graph size. Extensive empirical evidence demonstrates the effectiveness and efficiency of our proposed algorithms in comparison with state-of-the-art methods. Our approach improves on the performance relative to all prior methods, giving up to over 25% increase in the score. Further, our algorithms scale to networks with up to a million nodes, which is 1--2 orders of magnitude larger than all prior applications.

The area of anomaly detection has recently been expanded in the graph-based data. Anomalous vertices are often exhibited as a connected subgraph. Few works, however, have focused on connected anomalous subgraph detection because of the challenge of optimizing graph functionals under connectivity constraints. We employ Non-Parametric Graph Scan (NPGS) statistics for detecting anomalies within graph-based data. Based on the NPGS statistics, we proposed an efficient approximate approach to the connected anomalous subgraph detection problem that provides provable guarantees on performance and quality. In particular, we first decompose the problem into a sequence of subproblems, each of which can be reduced to a Budget Price-Collecting Steiner Tree (BPCST) problem, and then develop efficient exact and approximate algorithms for a special category of graphs in which the anomalous subgraphs can be reformulated in a fixed tree topology. Our method has a wide variety of applications, such as disease outbreak detection, road traffic congestion detection, and event detection in social media, because the NPGS statistics is free of distribution assumptions and can be applied to heterogeneous graph data.

Subjective Logic (SL) is one of well-known belief models that can explicitly deal with uncertain opinions and infer unknown opinions based on a rich set of operators of fusing multiple opinions. Due to high simplicity and applicability, SL has been substantially applied in a variety of decision making in the area of cybersecurity, opinion models, trust models, and/or social network analysis. However, SL and its variants have exposed limitations in predicting uncertain opinions in real-world dynamic network data mainly in three-fold: (1) a lack of scalability to deal with a large-scale network; (2) limited capability to handle heterogeneous topological and temporal dependencies among node-level opinions; and (3) a high sensitivity with conflicting evidence that may generate counterintuitive opinions derived from the evidence. In this work, we proposed a novel deep learning (DL)-based dynamic opinion inference model while node-level opinions are still formalized based on SL meaning that an opinion has a dimension of uncertainty in addition to belief and disbelief in a binomial opinion (i.e., agree or disagree). The proposed DL-based dynamic opinion inference model overcomes the above three limitations by considering the following: (1) state-of-the-art DL techniques, such as the Graph Convolutional Network (GCN) and the Gated Recurrent Units (GRU), for modeling the topological and temporal heterogeneous dependency information of a given dynamic network; (2) modeling conflicting opinions based on robust statistics; and (3) a highly scalable inference algorithm to predict dynamic, uncertain opinions in a linear computation time. We validated the outperformance of our proposed DL-based algorithm (i.e., GCN-GRU-opinion model) via extensive comparative performance analysis based on a real-world dataset.

In this work, we study different types of uncertainty in subjective opinions based on the internal belief mass distribution and the base rate distribution. Subjective opinions which are used as arguments in subjective logic (SL) expand the traditional belief functions by including base rate distributions. Fundamental uncertainty characteristics of a given opinion depend on its `singularity', `vagueness', `vacuity', `dissonance', `consonance' and `monosonance'. We define those concepts in the formalism of SL and show how these characteristics can be manifested in the three different opinion classes which are binomial, multinomial, and hyper-opinions. We clarify the relationships between the uncertainty characteristics and discuss how they influence decision making in SL.

For node level graph encoding, a recent important state-of-art method is the graph convolutional networks (GCN), which nicely integrate local vertex features and graph topology in the spectral domain. However, current studies suffer from several drawbacks: (1) graph CNNs rely on Chebyshev polynomial approximation which results in oscillatory approximation at jump discontinuities; (2) Increasing the order of Chebyshev polynomial can reduce the oscillations issue, but also incurs unaffordable computational cost; (3) Chebyshev polynomials require degree Ω(poly(1/ε)) to approximate a jump signal such as |x|, while rational function only needs O(poly log(1/ε)). However, it is non-trivial to apply rational approximation without increasing computational complexity due to the denominator. In this paper, the superiority of rational approximation is exploited for graph signal recovering. RatioanlNet is proposed to integrate rational function and neural networks. We show that the rational function of eigenvalues can be rewritten as a function of graph Laplacian, which can avoid multiplication by the eigenvector matrix. Focusing on the analysis of approximation on graph convolution operation, a graph signal regression task is formulated. Under graph signal regression task, its time complexity can be significantly reduced by graph Fourier transform. To overcome the local minimum problem of neural networks model, a relaxed Remez algorithm is utilized to initialize the weight parameters. Convergence rate of RatioanlNet and polynomial based methods on a jump signal is analyzed for a theoretical guarantee. The extensive experimental results demonstrated that our approach could effectively characterize the jump discontinuities, outperforming competing methods by a substantial margin on both synthetic and real-world graphs.

Subjective Logic (SL) is one of well-known belief models that can explicitly deal with uncertain opinions and infer unknown opinions based on a rich set of operators of fusing multiple opinions. Due to high simplicity and applicability, SL has been popularly applied in a variety of decision making in the area of cybersecurity, opinion models, and/or trust / social network analysis. However, SL has been facing an issue of scalability to deal with a large-scale network data. In addition, SL has shown a bounded prediction accuracy due to its inherent parametric nature by treating heterogeneous data and network structure homogeneously based on the assumption of a Bayesian network. In this work, we take one step further to deal with uncertain opinions for unknown opinion inference. We propose a deep learning (DL)-based opinion inference model while node-level opinions are still formalized based on SL. The proposed DL-based opinion inference model handles node-level opinions explicitly in a large-scale network using graph convoluational network (GCN) and variational autoencoder (VAE) techniques. We adopted the GCN and VAE due to their powerful learning capabilities in dealing with a large-scale network data without parametric fusion operators and/or Bayesian network assumption. This work is the first that leverages the merits of both DL (i.e., GCN and VAE) and a belief model (i.e., SL) where each node level opinion is modeled by the formalism of SL while GCN and VAE are used to achieve non-parametric learning with low complexity. By mapping the node-level opinions modeled by the GCN to their equivalent Beta PDFs (probability density functions), we develop a network-driven VAE to maximize prediction accuracy of unknown opinions while significantly reducing algorithmic complexity. We validate our proposed DL-based algorithm using real-world datasets via extensive simulation experiments for comparative performance analysis.

Evolving anomalous subgraphs detection in dynamic networks is an important and challenging problem that has arisen in multiple applications and is NP-hard in general. The evolving characteristic makes most existing methods incapable to tackle this problem effectively and efficiently, as it involves huge search spaces and continuous changes of evolving connected subgraphs, especially when the data are free of distributions. This paper presents a generic efficient framework, namely dynamic evolving anomalous subgraphs scanning (dGraphScan), to address this problem. We generalize traditional nonparametric scan statistics, and propose a large class of scan statistic functions for measuring the significance of evolving subgraphs in dynamic networks. Furthermore, we make a number of computational studies to optimize this large class of nonparametric scan statistic functions. Specifically, we first decompose each scan statistic function as a sequence of subproblems with provable guarantees, and then propose efficient approximation algorithms for tackling each subproblem, while analyzing their theoretical properties and providing rigorous approximation guarantees. Extensive experiments on three real-world datasets demonstrate that our general framework performs superior over state-of-the-art methods.

Detecting “hotspots” and “anomalies” is a recurring problem with a wide range of applications, such as social network analysis, epidemiology, finance, and biosurveillance, among others. Networks are a common abstraction in these applications for representing complex relationships. Typically, these networks are dynamic-, i.e., they evolve over time. A number of methods have been proposed for anomaly detection in such dynamic network data sets, which are primarily based on changes in network properties. We provide a survey of the various formulations of anomaly detection in dynamic networks with a focus on “window-based” methods. Window-based methods first define a time window of past network snapshots to model normal behavior and then mark a snapshot as anomalous if it has significantly different patterns from those observed in the time window. We describe two classes of techniques: 1) generalizations of Steiner connectivity; and 2) dense subgraph mining. Both have been used extensively in window-based graph anomaly detection. We summarize the key problem formulations that have been studied using these approaches, and we describe details of some of the main techniques.

Road traffic speed prediction is a challenging problem in intelligent transportation system (ITS) and has gained increasing attentions. Existing works are mainly based on raw speed sensing data obtained from infrastructure sensors or probe vehicles, which, however, are limited by expensive cost of sensor deployment and maintenance. With sparse speed observations, traditional methods based only on speed sensing data are insufficient, especially when emergencies like traffic accidents occur. To address the issue, this paper aims to improve the road traffic speed prediction by fusing traditional speed sensing data with new-type “sensing” data from cross domain sources, such as tweet sensors from social media and trajectory sensors from map and traffic service platforms. Jointly modeling information from different datasets brings many challenges, including location uncertainty of low-resolution data, language ambiguity of traffic description in texts, and heterogeneity of cross-domain data. In response to these challenges, we present a unified probabilistic framework, called Topic-Enhanced Gaussian Process Aggregation Model (TEGPAM), consisting of three components, i.e., location disaggregation model, traffic topic model, and traffic speed Gaussian Process model, which integrate new-type data with traditional data. Experiments on real world data from two large cities validate the effectiveness and efficiency of our model.

Adverse weather conditions have a significant impact on the safety, mobility, and efficiency of highway networks. Annually, 24 percent of all crashes, more than 7,400 roadway fatalities, and over 673,000 crash related injuries were caused by adverse weather conditions between 1995 and 2005 [1]. In addition, weather contributed to 23 percent of all non-reoccurring delay and approximately 544 million vehicle hours of delay each year [2]. Nearly 2.3 billion dollars each year are spent by transportation agencies for winter maintenance that contribute to close to 20 percent of most DOTs yearly budgets [2]. These safety and mobility factors make it important to develop new and more effective methods to address road conditions during adverse weather conditions. This paper develops techniques for efficiently detecting rapid weather change events and analyzing their impacts on the traffic flow characteristics of a highway network. It is composed of three components, including 1) detection of rapid weather change events in a highway network using the streaming weather information from a sensor network of weather stations; 2) detection of rapid traffic change events on the traffic flow characteristics (e.g., travel time) of the highway network; and 3) analysis of correlations between the detected weather and traffic change events in space and time. The proposed approach was applied to a weather dataset provided by New York State Mesonet and a traffic flow dataset the National Performance Management Research Data Set (NPMRDS) provided by NYSDOT. The empirical results provide potential evidence about the significant impacts of rapid weather change events on traffic flow characteristics of the Interstate 90 (I-90) Highway in the state of New York. The limitations of the proposed approach and the empirical study are also discussed.

Subjective Logic (SL), as one of the state-of-the-art belief models, has been proposed to model an opinion that explicitly deals with its uncertainty. SL offers a variety of operators to update opinions consisting of belief, disbelief, and uncertainty. However, SL operators lack scalability to derive opinions from a large-scale network data due to the sequential procedures of combining two opinions, instead of collective procedures dealing with multiple opinions concurrently. In addition, SL's performance in predicting unknown opinions has been validated only when the uncertainty mass is sufficiently low. To enhance scalability and prediction accuracy of unknown opinions in SL, we take a hybrid approach by combining SL with Probabilistic Soft Logic (PSL). PSL provides collective reasoning with high scalability based on relationships between opinions but does not deal with uncertainty. By taking the merits of both SL and PSL, we propose a probabilistic logic algorithm, called Collective Subjective Logic (CSL) that provides high scalability and high prediction accuracy while dealing with uncertain opinions. Our proposed CSL is generic to deal with uncertain opinions with both high scalability and high prediction accuracy of unknown opinions over a large-scale network dataset. Through the extensive simulation experiments, we validated the outperformance of CSL compared against SL and PSL in terms of prediction accuracy of unknown opinions and algorithmic complexity using Epinions and two road traffic datasets.

Detection of interesting (e.g., coherent or anomalous) clusters has been studied extensively on plain or univariate networks, with various applications. Recently, algorithms have been extended to networks with multiple attributes for each node in the real-world. In a multi-attributed network, often, a cluster of nodes is only interesting for a subset (subspace) of attributes, andthis type of clusters is called subspace clusters. However, in the current literature, few methods are capable of detecting subspace clusters, which involves concurrent feature selection and network cluster detection. These relevant methods are mostly heuristic-driven and customized for specific application scenarios. In this work, we present a generic and theoretical framework for detection of interesting subspace clusters in large multi-attributed networks. Specifically, we propose a subspace graph-structured matching pursuit algorithm, namely, SG-Pursuit, to address a broad class of such problems for different scorefunctions (e.g., coherence or anomalous functions) and topology constraints (e.g., connected subgraphs and dense subgraphs). We prove that our algorithm 1) runs in nearly-linear time on the network size and the total number of attributes and 2) enjoys rigorous guarantees (geometrical convergence rate and tight error bound) analogous to those of the state-of-the-art algorithms for sparse feature selection problems and subgraph detection problems. As a case study, we specialize SG-Pursuit to optimizea number of well-known score functions for two typical tasks, including detection of coherent dense and anomalous connected subspace clusters in real-world networks. Empirical evidence demonstrates that our proposed generic algorithm SG-Pursuit is superior over state-of-the-art methods that are designed specifically for these two tasks.

For a detection problem, a user often has some prior knowledge about the structure-specific subgraphs of interest, but few traditional approaches are capable of employing this knowledge. The main technical challenge is that few approaches can efficiently model the space of connected subgraphs that are isomorphic to a query graph. We present a novel, efficient approach for optimizing a generic nonlinear cost function subject to a query-specific structural constraint. Our approach enjoys strong theoretical guarantees on the convergence of a nearly optimal solution and a low time complexity. For the case study, we specialize the nonlinear function to several well-known graph scan statistics for anomalous subgraph discovery. Empirical evidence demonstrates that our method is superior to state-of-the-art methods in several real-world anomaly detection tasks.

While automatic online software anomaly detection is crucial for ensuring the quality of production software, current techniques are mostly inefficient and ineffective. For online software, its inputs are usually provided by the users at runtime and the validity of the outputs cannot be automatically verified without a predefined oracle. Furthermore, some online anomalous behavior may be caused by the anomalies in the execution context, rather than by any code defect, which are even more difficult to detect. Existing approaches tackle this problem by identifying certain properties observed from the executions of the software during a training process and using them to monitor online software behavior. However, they may require a large execution overhead for monitoring the properties, which limits the applicability of these approaches for online monitoring. We present a methodology that applies effective algorithms to select a close to optimal set of anomaly-revealing properties, which enables online anomaly detection with minimal execution overhead. Our empirical results show that an average of 76.5% of anomalies were detected by using at most 5.5% of execution overhead.

Scan statistics is a popular approach used for detecting “hotspots” and “anomalies” in spatio-temporal and network data. This methodology involves maximizing a score function over all connected subgraphs, which is NP-hard in general. A number of heuristics have been proposed for these problems, but they do not provide any quality guarantees. In this paper, we develop a framework for designing algorithms for optimizing a large class of scan statistics for networks, subject to connectivity constraints. Our algorithms run in time that scales linearly on the size of the graph and depends on a parameter we call the “effective solution size”, while providing rigorous approximation guarantees. In contrast, most prior methods have super-linear running times in terms of graph size. Extensive empirical evidence demonstrates the effectiveness and efficiency of our proposed algorithms in comparison with state-of-the-art methods. Our approach improves on the performance relative to all prior methods, giving up to over 25% increase in the score. Further, our algorithms scale to networks with up to a million nodes, which is 1–2 orders of magnitude larger than all prior applications.

Event detection in online social media has primarily focused on identifying abnormal spikes, or bursts, in activity. However, disruptive events such as socio-economic disasters, civil unrest, and even power outages, often involve abnormal troughs or lack of activity, leading to absenteeism. We present the first study, to our knowledge, that models absenteeism and uses detected absenteeism instances as a basis for event detection in location-based social networks such as Twitter. The proposed framework addresses the challenges of (i) early detection of absenteeism, (ii) identifying the locus of the absenteeism, and (iii) identifying groups or communities underlying the absenteeism. Our approach uses the formalism of graph wavelets to represent the spatiotemporal structure of user activity in a location-based social network. This formalism facilitates multiscale analysis, enabling us to detect anomalous behavior at different graph resolutions, which in turn allows the identification of event locations and underlying groups. The effectiveness of our approach is evaluated using Twitter activity related to civil unrest events in Latin America.

Anomalous subgraph detection has been successfully applied to event detection in social media. However, the subgraph detection problembecomes challenging when the social media network incorporates abundant attributes, which leads to a multivariate network. The multivariate characteristic makes most existing methods incapable to tackle this problem effectively and efficiently, as it involves joint feature selection and subgraph detection that has not been well addressed in the current literature, especially, in the dynamic multivariate networks in which attributes evolve over time.

Summary For the many application domains concerning entities and their connections, often their data can be formally represented as graphs and an important problem is detecting an anomalous subgraph within it. Numerous methods have been proposed to speed‐up anomalous subgraph detection; however, each incurs non‐trivial costs on detection accuracy. In this paper, we formulate the anomalous subgraph detection problem as the maximization of a non‐parametric scan statistic and then approximate it to a submodular maximization problem. We propose two parallel algorithms: non‐coordination anomalous subgraph detection (NCASD) and under‐coordination anomalous subgraph detection (UCASD)for the anomalous subgraph detection. To the best of our knowledge, this paper is the first to solve this problem in parallel. NCASD emphasizes speed at the expense of approximation guarantees, while UCASD achieves a higher approximation factor through additional coordination controls and reduced parallelism. The experiments demonstrate the effectiveness and efficiency of our proposed approaches in a real‐world application domain (water pollution detection), comparing them with five other state‐of‐the‐art methods. Copyright © 2016 John Wiley & Sons, Ltd.

Social media has been utilized as a significant surrogate for spatial societal event forecasting. The accuracy and discernibility of a spatial event forecasting model are two key concerns, as they determine how accurate and how detailed the model's predictions will be. Existing research focuses almost exclusively on the accuracy alone, seldom considering the accuracy and discernibility simultaneously because this would require a considerably more sophisticated model while suffering from several challenges, namely: 1) the precise formulation of the tradeoff between accuracy and discernibility; 2) the scarcity of social media data with a high spatial resolution; and 3) the characterization of spatial correlation and heterogeneity. This paper proposes a novel feature learning framework that concurrently addresses all the above challenges by formulating prediction tasks for different locations with different spatial resolutions, allowing the heterogeneous relationships among the tasks to be characterized. This characterization is then integrated into our new models based on multitask learning, with parameters optimized by our proposed algorithm based on the alternative direction method of multipliers (ADMM) and dynamic programming. Extensive experimental evaluations performed on several data sets from different domains demonstrated the effectiveness of our proposed approach.

With the ever increasing volume of geo-referenced datasets, there is a real need for better statistical estimation and prediction techniques for spatial analysis. Most existing approaches focus on predicting multivariate Gaussian spatial processes, but as the data may consist of non-Gaussian (or mixed type) variables, this creates two challenges: (1) how to accurately capture the dependencies among different data types, both Gaussian and non-Gaussian; and (2) how to efficiently predict multivariate non-Gaussian spatial processes. In this article, we propose a generic approach for predicting multiple response variables of mixed types. The proposed approach accurately captures cross-spatial dependencies among response variables and reduces the computational burden by projecting the spatial process to a lower dimensional space with knot-based techniques. Efficient approximations are provided to estimate posterior marginals of latent variables for the predictive process, and extensive experimental evaluations based on both simulation and real-life datasets are provided to demonstrate the effectiveness and efficiency of this new approach.

Spatial event forecasting from social media is potentially extremely useful but suffers from critical challenges, such as the dynamic patterns of features (keywords) and geographic heterogeneity (e.g., spatial correlations, imbalanced samples, and different populations in different locations). Most existing approaches (e.g., LASSO regression, dynamic query expansion, and burst detection) address some, but not all, of these challenges. Here, we propose a novel multi-task learning framework that aims to concurrently address all the challenges involved. Specifically, given a collection of locations (e.g., cities), forecasting models are built for all the locations simultaneously by extracting and utilizing appropriate shared information that effectively increases the sample size for each location, thus improving the forecasting performance. The new model combines both static features derived from a predefined vocabulary by domain experts and dynamic features generated from dynamic query expansion in a multi-task feature learning framework. Different strategies to balance homogeneity and diversity between static and dynamic terms are also investigated. And, efficient algorithms based on Iterative Group Hard Thresholding are developed to achieve efficient and effective model training and prediction. Extensive experimental evaluations on Twitter data from civil unrest and influenza outbreak datasets demonstrate the effectiveness and efficiency of our proposed approach.

The analysis of interactions between social media and traditional news streams is becoming increasingly relevant for a variety of applications, including: understanding the underlying factors that drive the evolution of data sources, tracking the triggers behind events, and discovering emerging trends.Researchers have explored such interactions by examining volume changes or information diffusions,however, most of them ignore the semantical and topical relationships between news and social media data.Our work is the first attempt to study how news influences social media, or inversely, based on topical knowledge.We propose a hierarchical Bayesian model that jointly models the news and social media topics and their interactions.We show that our proposed model can capture distinct topics for individual datasets as well as discover the topic influences among multiple datasets.By applying our model to large sets of news and tweets, we demonstrate its significant improvement over baseline methods and explore its power in the discovery of interesting patterns for real world cases.

Non-parametric graph scan (NPGS) statistics are used to detect anomalous connected subgraphs on graphs, and have a wide variety of applications, such as disease outbreak detection, road traffic congestion detection, and event detection in social media. In contrast to traditional parametric scan statistics (e.g., the Kulldorff statistic), NPGS statistics are free of distributional assumptions and can be applied to heterogeneous graph data. In this paper, we make a number of contributions to the computational study of NPGS statistics. First, we present a novel reformulation of the problem as a sequence of Budget Price-Collecting Steiner Tree (B-PCST) sub-problems. Second, we show that this reformulated problem is NP-hard for a large class of nonparametric statistic functions. Third, we further develop efficient exact and approximate algorithms for a special category of graphs in which the anomalous subgraphs can be reformulated in a fixed tree topology. Finally, using extensive experiments we demonstrate the performance of our proposed algorithms in two real-world application domains (water pollution detection in water sensor networks and spatial event detection in social media networks) and contrast against state-of-the-art connected subgraph detection methods.

Spatial event detection is an important and challenging problem. Unlike traditional event detection that focuses on the timing of global urgent event, the task of spatial event detection is to detect the spatial regions (e.g. clusters of neighboring cities) where urgent events occur. In this paper, we focus on the problem of spatial event detection using textual information in social media. We observe that, when a spatial event occurs, the topics relevant to the event are often discussed more coherently in cities near the event location than those far away. In order to capture this pattern, we propose a new method called Graph Topic Scan Statistic (Graph-TSS) that corresponds to a generalized log-likelihood ratio test based on topic modeling. We first demonstrate that the detection of spatial event regions under Graph-TSS is NP-hard due to a reduction from classical node-weighted prize-collecting Steiner tree problem (NW-PCST). We then design an efficient algorithm that approximately maximizes the graph topic scan statistic over spatial regions of arbitrary form. As a case study, we consider three applications using Twitter data, including Argentina civil unrest event detection, Chile earthquake detection, and United States influenza disease outbreak detection. Empirical evidence demonstrates that the proposed Graph-TSS performs superior over state-of-the-art methods on both running time and accuracy.

Social media has become a significant surrogate forspatial event forecasting. The accuracy and discernibility of aspatial event forecasting model are two key concerns, whichrespectively determine how accurate and how detailed themodel's predictions could be. Existing work pays most attentionon the accuracy alone, seldom considering the accuracyand discernibility simultaneously, because this would requiresa considerably more sophisticated model while still sufferingfrom several challenges: 1) the precise formulation of thetrade-off between accuracy and discernibility, 2) the scarcityof social media data with a high spatial resolution, and 3)the characterization of spatial correlation and heterogeneity. This paper proposes a novel feature learning model thatconcurrently addresses all the above challenges by formulatingprediction tasks for different locations with different spatialresolutions, allowing the heterogeneous relationships amongthe tasks to be characterized. This characterization is thenintegrated into our new model based on multitask learning, whose parameters are optimized by our proposed algorithmbased on the Alternative Direction Method of Multipliers(ADMM). Extensive experimental evaluations on 11 datasetsfrom different domains demonstrated the effectiveness of ourproposed approach.

Structured sparse optimization is an important and challenging problem for analyzing high-dimensional data in a variety of applications such as bioinformatics, medical imaging, social networks, and astronomy. Although a number of structured sparsity models have been explored, such as trees, groups, clusters, and paths, connected subgraphs have been rarely explored in the current literature. One of the main technical challenges is that there is no structured sparsity-inducing norm that can directly model the space of connected subgraphs, and there is no exact implementation of a projection oracle for connected subgraphs due to its NP-hardness. In this paper, we explore efficient approximate projection oracles for connected subgraphs, and propose two new efficient algorithms, namely, Graph-IHT and Graph-GHTP, to optimize a generic nonlinear objective function subject to connectivity constraint on the support of the variables. Our proposed algorithms enjoy strong guarantees analogous to several current methods for sparsity-constrained optimization, such as Projected Gradient Descent (PGD), Approximate Model Iterative Hard Thresholding (AM-IHT), and Gradient Hard Thresholding Pursuit (GHTP) with respect to convergence rate and approximation accuracy. We apply our proposed algorithms to optimize several well-known graph scan statistics in several applications of connected subgraph detection as a case study, and the experimental results demonstrate that our proposed algorithms outperform state-of-the-art methods.

Forecasting significant societal events is an interesting and challenging problem as it taking into consideration multiple aspects of a society, including its economics, politics, and culture. Traditional forecasting methods based on a single data source find it hard to cover all these aspects comprehensively, thus limiting model performance. Multi source event forecasting has proven promising but still suffers from several challenges, including 1) geographical hierarchies in multi-source data features, 2) missing values, and 3) characterization of structured feature sparsity. This paper proposes a novel feature learning model that concurrently addresses all the above challenges. Specifically, given multi-source data from different geographical levels, we design a new forecasting model by characterizing the lower-level features' dependence on higher-level features. To handle the correlations amidst structured feature sets and deal with missing values among the coupled features, we propose a novel feature learning model based on an $N$th-order strong hierarchy and fused-overlapping group Lasso. An efficient algorithm is developed to optimize model parameters and ensure global optima. Extensive experiments on 10 datasets in different domains demonstrate the effectiveness and efficiency of the proposed model.

Anomaly detection in mixed-type data is an important problem that has not been well addressed in the machine learning field. Existing approaches focus on computational efficiency and their correlation modeling between mixed-type attributes is heuristically driven, lacking a statistical foundation. In this paper, we propose MIxed-Type Robust dEtection (MITRE), a robust error buffering approach for anomaly detection in mixed-type datasets. Because of its non-Gaussian design, the problem is analytically intractable. Two novel Bayesian inference approaches are utilized to solve the intractable inferences: Integrated-nested Laplace Approximation (INLA), and Expectation Propagation (EP) with Variational Expectation-Maximization (EM). A set of algorithmic optimizations is implemented to improve the computational efficiency. A comprehensive suite of experiments was conducted on both synthetic and real world data to test the effectiveness and efficiency of MITRE.

Twitter has become a popular social sensor. It is socially significant to surveil the tweet content under crucial themes such as "disease" and "civil unrest". However, this creates two challenges: 1) how to characterize the theme pattern, given Twitter's heterogeneity, dynamics, and unstructured language; and 2) how to model the theme consistently across multiple Twitter functions such as hashtags, replying, and friendships. In this paper, we propose a dynamic query expansion (DQE) model for theme tracking in Twitter. Specifically, DQE characterizes the theme consistency among heterogeneous entities (e.g., terms, tweets, and users) through semantic and social relationships, including co-occurrence, replying, authorship, and friendship. The proposed new optimization algorithm estimates the weight of each relationship by minimizing the Kullback-Leibler divergence. To demonstrate the effectiveness and scalability of DQE, we conducted extensive experiments to track the theme "civil unrest" across 8 Latin American countries.

Infectious disease epidemics such as influenza and Ebola pose a serious threat to global public health. It is crucial to characterize the disease and the evolution of the ongoing epidemic efficiently and accurately. Computational epidemiology can model the disease progress and underlying contact network, but suffers from the lack of real-time and fine-grained surveillance data. Social media, on the other hand, provides timely and detailed disease surveillance, but is insensible to the underlying contact network and disease model. This paper proposes a novel semi-supervised deep learning framework that integrates the strengths of computational epidemiology and social media mining techniques. Specifically, this framework learns the social media users' health states and intervention actions in real time, which are regularized by the underlying disease model and contact network. Conversely, the learned knowledge from social media can be fed into computational epidemic model to improve the efficiency and accuracy of disease diffusion modeling. We propose an online optimization algorithm to substantialize the above interactive learning process iteratively to achieve a consistent stage of the integration. The extensive experimental results demonstrated that our approach can effectively characterize the spatio-temporal disease diffusion, outperforming competing methods by a substantial margin on multiple metrics.

Spatial event forecasting from social media is an important problem but encounters critical challenges, such as dynamic patterns of features (keywords) and geographic heterogeneity (e.g., spatial correlations, imbalanced samples, and different populations in different locations). Most existing approaches (e.g., LASSO regression, dynamic query expansion, and burst detection) are designed to address some of these challenges, but not all of them. This paper proposes a novel multi-task learning framework which aims to concurrently address all the challenges. Specifically, given a collection of locations (e.g., cities), we propose to build forecasting models for all locations simultaneously by extracting and utilizing appropriate shared information that effectively increases the sample size for each location, thus improving the forecasting performance. We combine both static features derived from a predefined vocabulary by domain experts and dynamic features generated from dynamic query expansion in a multi-task feature learning framework; we investigate different strategies to balance homogeneity and diversity between static and dynamic terms. Efficient algorithms based on Iterative Group Hard Thresholding are developed to achieve efficient and effective model training and prediction. Extensive experimental evaluations on Twitter data from four different countries in Latin America demonstrated the effectiveness of our proposed approach.

Event forecasting in Twitter is an important and challenging problem. Most existing approaches focus on forecasting temporal events (such as elections and sports) and do not consider spatial features and their underlying correlations. In this paper, we propose a generative model for spatiotemporal event forecasting in Twitter. Our model characterizes the underlying development of future events by jointly modeling the structural contexts and spatiotemporal burstiness. An effective inference algorithm is developed to train the model parameters. Utilizing the trained model, the alignment likelihood of tweet sequences is calculated by dynamic programming. Extensive experimental evaluations on two different domains demonstrated the effectiveness of our proposed approach.

Real-time road traffic congestion monitoring is an important and challenging problem. Most existing monitoring approaches require the deployment of infrastructure sensors or large-scale probe vehicles. Their installation is often expensive and temporal-spatial coverage is limited. Probe vehicle data are oftentimes noisy on urban arterials, and therefore insufficient to provide accurate congestion estimation. This paper presents a novel social-media based approach to traffic congestion monitoring, in which pedestrians, drivers, and passengers a retreated as human sensors and their posted tweets in Twitter as observations of nearby ongoing traffic conditions. There are three technical challenges for road traffic monitoring based on Twitter, namely: 1) language ambiguity in the usage of traffic related terms, 2) uncertainty and low resolution of geographic location mentions, and 3) interactions between traffic-related events such as accidents and congestion. We propose a topic modeling based language model to address the first challenge and a collaborative inference model based on probabilistic soft logic (PSL) to address the second and third challenges. We present a unified statistical framework that combines those two models based on hinge loss Markov random fields (HLMRFs). In order to address the computational challenges incurred by the non-analytical integral of latent variables (factors) and the MAP estimation of a large number of location-dependent traffic congestion variables, we propose a fast approximate inference algorithm based on maximization expectation (ME) and the alternating directed method of multipliers (ADMM). Extensive evaluations over a variety of metrics on real world Twitter and INRIX probe speed datasets in two U.S. Major cities demonstrate the efficiency and effectiveness of our proposed approach.

Event detection in social media is an important but challenging problem. Most existing approaches are based on burst detection, topic modeling, or clustering techniques, which cannot naturally model the implicit heterogeneous network structure in social media. As a result, only limited information, such as terms and geographic locations, can be used. This paper presents Non-Parametric Heterogeneous Graph Scan (NPHGS), a new approach that considers the entire heterogeneous network for event detection: we first model the network as a "sensor" network, in which each node senses its "neighborhood environment" and reports an empirical p-value measuring its current level of anomalousness for each time interval (e.g., hour or day). Then, we efficiently maximize a nonparametric scan statistic over connected subgraphs to identify the most anomalous network clusters. Finally, the event represented by each cluster is summarized with information such as type of event, geographical locations, time, and participants. As a case study, we consider two applications using Twitter data, civil unrest event detection and rare disease outbreak detection, and present empirical evaluations illustrating the effectiveness and efficiency of our proposed approach.

Modeling the movement of information within social media outlets, like Twitter, is key to understanding to how ideas spread but quantifying such movement runs into several difficulties. Two specific areas that elude a clear characterization are (i) the intrinsic random nature of individuals to potentially adopt and subsequently broadcast a Twitter topic, and (ii) the dissemination of information via non-Twitter sources, such as news outlets and word of mouth, and its impact on Twitter propagation. These distinct yet inter-connected areas must be incorporated to generate a comprehensive model of information diffusion. We propose a bispace model to capture propagation in the union of (exclusively) Twitter and non-Twitter environments. To quantify the stochastic nature of Twitter topic propagation, we combine principles of geometric Brownian motion and traditional network graph theory. We apply Poisson process functions to model information diffusion outside of the Twitter mentions network. We discuss techniques to unify the two sub-models to accurately model information dissemination. We demonstrate the novel application of these techniques on real Twitter datasets related to mass protest adoption in social communities.

We describe the design, implementation, and evaluation of EMBERS, an automated, 24x7 continuous system for forecasting civil unrest across 10 countries of Latin America using open source indicators such as tweets, news sources, blogs, economic indicators, and other data sources. Unlike retrospective studies, EMBERS has been making forecasts into the future since Nov 2012 which have been (and continue to be) evaluated by an independent T&E team (MITRE). Of note, EMBERS has successfully forecast the June 2013 protests in Brazil and Feb 2014 violent protests in Venezuela. We outline the system architecture of EMBERS, individual models that leverage specific data sources, and a fusion and suppression engine that supports trading off specific evaluation criteria. EMBERS also provides an audit trail interface that enables the investigation of why specific predictions were made along with the data utilized for forecasting. Through numerous evaluations, we demonstrate the superiority of EMBERS over baserate methods and its capability to forecast significant societal happenings.

Passive monitoring by distributed wireless sniffers has been used to strategically capture the network traffic, as the basis of automatic network diagnosis. However, the traditional monitoring techniques fall short in cognitive radio networks (CRNs) due to the much larger number of channels to be monitored and the secondary users' channel availability uncertainty imposed by primary user activities. To better serve CRNs, we propose a systematic passive monitoring framework, i.e., SpecMonitor, for traffic collection using a limited number of sniffers in Wi-Fi-like CRNs. We jointly consider primary user activity and secondary user channel access pattern to optimize the traffic capturing strategy. In particular, we exploit a nonparametric density estimation method to learn and predict secondary users' access pattern in an online fashion, which rapidly adapts to the users' dynamic behaviors and supports accurate estimation of merged access patterns from multiple users. We also design near-optimal monitoring algorithms that maximize two levels of quality-of-monitoring goals based on the predicted channel access patterns. The simulations and experiments show that SpecMonitor outperforms the existing schemes significantly.

Anomaly detection for mixed-type data is an important problem that has not been well addressed in the machine learning field. There are two challenging issues for mixed-type datasets, namely modeling mutual correlations between mixed-type attributes and capturing large variations due to anomalies. This paper presents BuffDetect, a robust error buffering approach for anomaly detection in mixed-type datasets. A new variant of the generalized linear model is proposed to model the dependency between mixed-type attributes. The model incorporates an error buffering component based on Student-t distribution to absorb the variations caused by anomalies. However, because of the non- Gaussian design, the problem becomes analytically intractable. We propose a novel Bayesian inference approach, which integrates Laplace approximation and several computational optimizations, and is able to efficiently approximate the posterior of high dimensional latent variables by iteratively updating the latent variables in groups. Extensive experimental evaluations based on 13 benchmark datasets demonstrate the effectiveness and efficiency of BuffDetect.

Geo-social information can be utilized for user benefits in many applications. Social interaction in vehicular ad hoc networks (VANETs) is an important source for this type of information. In this paper, we first propose and describe a general architecture of the social VANET system (S-VANET) that supports social interaction through vehicular networks. Then, we present a new carpooling recommendation system that works as S-VANET application. The main objective is to recommend individuals to join their friends during trips or travels. The proposed recommendation system uses check-in history and home location to model users, and utilizes Fast Fourier transform to represent user check-ins and find the similarity between users. The system uses hierarchical clustering with weighted center of mass method to estimate the user home location.

Passive monitoring by distributed wireless sniffers has been used to strategically capture the network traffic, as the basis of automatic network diagnosis. However, the traditional monitoring techniques fall short in cognitive radio networks (CRNs) due to the much larger number of channels to be monitored, and the secondary users' channel availability uncertainty imposed by primary user activities. To better serve CRNs, we propose a systematic passive monitoring framework for traffic collection using a limited number of sniffers in WiFi like CRNs. We jointly consider primary user activity and secondary user channel access pattern to optimize the traffic capturing strategy. In particular, we exploit a non-parametric density estimation method to learn and predict secondary users' access pattern in an online fashion, which rapidly adapts to the users' dynamic behaviors and supports accurate estimation of merged access patterns from multiple users. We also design near-optimal monitoring algorithms that maximize two levels of quality-of-monitoring goals respectively, based on the predicted channel access patterns. The simulations and experiments show that our proposed framework outperforms the existing schemes significantly.

Social microblogs such as Twitter and Weibo are experiencing an explosive growth with billions of global users sharing their daily observations and thoughts. Beyond public interests (e.g., sports, music), microblogs can provide highly detailed information for those interested in public health, homeland security, and financial analysis. However, the language used in Twitter is heavily informal, ungrammatical, and dynamic. Existing data mining algorithms require extensive manually labeling to build and maintain a supervised system. This paper presents STED, a semi-supervised system that helps users to automatically detect and interactively visualize events of a targeted type from twitter, such as crimes, civil unrests, and disease outbreaks. Our model first applies transfer learning and label propagation to automatically generate labeled data, then learns a customized text classifier based on mini-clustering, and finally applies fast spatial scan statistics to estimate the locations of events. We demonstrate STED's usage and benefits using twitter data collected from Latin America countries, and show how our system helps to detect and track example events such as civil unrests and crimes.

Energy crisis and climate change have caused a global concern and motivated efforts to reduce energy consumption. Studies have shown that providing appliance-level consumption information can help users conserve a significant amount of energy. Existing methods focus on learning parallel signal signatures, but the inherent relationships between the signatures have not been well explored. This paper presents the Hierarchical Probabilistic Model for Energy Disaggregation (HPMED). We derive the discriminative features from low sample rate power readings to characterise device functional modes. The HPMED model bridges the discriminative features, working states, and aggregated consumption. To address the analytical intractable problem, an efficient algorithm is proposed to approximately infer the latent states for disaggregation task. Extensive experiments on a real-world dataset demonstrated the effectiveness of the proposed approach.

This paper describes an efficient and effective design of Robust Spatio-Temporal Prediction based on Student's t distribution, namely, St-RSTP, to provide estimations based on observations over spatio-temporal neighbors. The proposed St-RSTP is more resilient to outliers or other small departures from model assumptions than its ancestor, the Spatio-Temporal Random Effects (STRE) model. STRE is a state-of-the-art statistical model with linear order complexity for large scale processing. However, it assumes Gaussian observations, which has the well-known limitation of non-robustness. In our StRSTP design, the measurement error follows Student's t distribution, instead of a traditional Gaussian distribution. This design reduces the influence of outliers, improves prediction quality, and keeps the problem analytically intractable. We propose a novel approximate inference approach, which approximates the model into the form that separates the high dimensional latent variables into groups, and then estimates the posterior distributions of different groups of variables separately in the framework of Expectation Propagation. As a good property, our approximate approach degeneralizes to the standard STRE based prediction, when the degree of freedom of the Student's t distribution is set to infinite. Extensive experimental evaluations based on both simulation and real-life data sets demonstrated the robustness and the efficiency of our Student-t prediction model. The proposed approach provides critical functionality for stochastic processes on spatio-temporal data.

Spatial kriging is a widely used predictive model for spatial datasets. In spatial kriging model, the observations are assumed to be Gaussian for computational convenience. However, its predictive accuracy could be significantly compromised if the observations are contaminated by outliers. This deficiency can be systematically addressed by increasing the robustness of spatial kriging model using heavy tailed distributions, such as the Huber, Laplace, and Student's t distributions. This paper presents a novel Robust and Reduced Rank Spatial Kriging Model (R3-SKM), which is resilient to the influences of outliers and allows for fast spatial inference. Furthermore, three effective and efficient algorithms are proposed based on R3-SKM framework that can perform robust parameter estimation, spatial prediction, and spatial outlier detection with a linear-order time complexity. Extensive experiments on both simulated and real data sets demonstrated the robustness and efficiency of our proposed techniques.

As the issue of freshwater shortage is increasing daily, it's critical to take effective measures for water conservation. Based on previous studies, device level consumption could lead to significant conservation of freshwater. However, current smart meter deployments only produce low sample rate aggregated data. In this paper, we examine the task of separating whole-home water consumption into its component appliances. A key challenge is to address the unique features of low sample rate data. To this end, we propose Sparse Coding with Featured Discriminative Dictionary (SCFDD) by incorporating inherent shape and activation features to capture the discriminative characteristics of devices. In addition, extensive experiments were performed to validate the effectiveness of SCFDD.

Spatial Categorical Outlier Detection (SCOD) has attracted considerable attentions from the areas of spatial data mining and geological analysis. When encountering an SCOD problem, some researchers introduce to utilize Spatial Numerical Outlier Detection measures by mapping categorical attributes to continuous ones. However, such approaches fail to capture the special properties of spatial categorical data, which is prone to incur the masking and swamping issues. In this paper, we model spatial dependencies between spatial categorical observations and propose a Pair Correlation Function(PCF) based method to detect SCOs. First, a new metric, named Pair Correlation Ratio(PCR), is estimated for each pair of categorical combinations based on their co-occurrence frequency at different spatial distances. Then discrete PCRs are fitted in a continuous function of distances. The outlier score is computed using the average PCRs between referenced object and its spatial neighbors. Observations with the lowest PCRs are labeled as potential SCOs. Extensive experiments demonstrated that PCF based method outperformed existing approaches.

In this paper we describe the multi-resolution water consumption prediction based on the SmarterWater system. This prediction service provides household consumption projection and regional demand forecasting for both short-term and med-term. Water consumption prediction, together with the other functions in the SmarterWater service, has been deployed to Dubuque, IA. Consumption behavior change after accessing the service has been observed.

Activity analysis disaggregates utility consumption from smart meters into specific usage that associates with human activities. It can not only help residents better manage their consumption for sustainable lifestyle, but also allow utility managers to devise conservation programs. Existing research efforts on disaggregating consumption focus on analyzing consumption features with high sample rates (mainly between 1 Hz ~ 1MHz). However, many smart meter deployments support sample rates at most 1/900 Hz, which challenges activity analysis with occurrences of parallel activities, difficulty of aligning events, and lack of consumption features. We propose a novel statistical framework for disaggregation on coarse granular smart meter readings by modeling fixture characteristics, household behavior, and activity correlations. This framework has been implemented into two approaches for different application scenarios, and has been deployed to serve over 300 pilot households in Dubuque, IA. Interesting activity-level consumption patterns have been identified, and the evaluation on both real and synthetic datasets has shown high accuracy on discovering washer and shower.

Regional human behavior change refers to the scenarios that people in a certain area exhibit significant behavior deviation from their neighbors and their own past. This regional pattern usually reveals underlying changes of living environment, such as regional development, immigration, disease breakout; or uncovers demographic information from special events, for instance, start/end of school holidays, or religious holidays. Statistically significant behavior changes contain both temporal and spatial characteristics. In this paper, we propose local spatial scan statistic to identify regional behavior changes. To accelerate local search, spatial index is modified to provide data-driven clusters and scalable data access. Base on the restricted spatial index, we provide both exact and approximated approaches to compute local spatial scan. Simulation analysis and case studies on water bills of 15K households validated the efficiency and effectiveness of these approaches on identifying regional behavior changes.

A spatial outlier is a spatially referenced object whose non-spatial attributes are very different from those of its spatial neighbors. Spatial outlier detection has been an important part of spatial data mining and attracted attention in the past decades. Numerous SOD (Spatial Outlier Detection) approaches have been proposed. However, in these techniques, there exist the problems of masking and swamping. That is, some spatial outliers can escape the identification, and normal objects can be erroneously identified as outliers. In this paper, two Random walk based approaches, RW-BP (Random Walk on Bipartite Graph) and RW-EC (Random Walk on Exhaustive Combination), are proposed to detect spatial outliers. First, two different weighed graphs, a BP (Bipartite graph) and an EC (Exhaustive Combination), are modeled based on the spatial and/or non-spatial attributes of the spatial objects. Then, random walk techniques are utilized on the graphs to compute the relevance scores between the spatial objects. Using the analysis results, the outlier scores are computed for each object and the top k objects are recognized as outliers. Experiments conducted on the synthetic and real datasets demonstrated the effectiveness of the proposed approaches.

Local based approach is a major category of methods for spatial outlier detection (SOD). Currently, there is a lack of systematic analysis on the statistical properties of this framework. For example, most methods assume identical and independent normal distributions (i.i.d. normal) for the calculated local differences, but no justifications for this critical assumption have been presented. The methods' detection performance on geostatistic data with linear or nonlinear trend is also not well studied. In addition, there is a lack of theoretical connections and empirical comparisons between local and global based SOD approaches. This paper discusses all these fundamental issues under the proposed Generalized Local Statistical (GLS) framework. Furthermore, robust estimation and outlier detection methods are designed for the new GLS model. Extensive simulations demonstrated that the SOD method based on the GLS model significantly outperformed all existing approaches when the spatial data exhibits a linear or nonlinear trend.

Probability density function estimation is a fundamental component in several stream mining tasks such as outlier detection and classification. The nonparametric adaptive kernel density estimate (AKDE) provides a robust and asymptotically consistent estimate for an arbitrary distribution. However, its extensive computational requirements make it difficult to apply this technique to the stream environment. This paper tackles the issue of developing efficient and asymptotically consistent AKDE over data streams while heeding the stringent constraints imposed by the stream environment. We propose the concept of local regions to effectively synopsize local density features, design a suite of algorithms to maintain the AKDE under a time-based sliding window, and analyze the estimates' asymptotic consistency and computational costs. In addition, extensive experiments were conducted with real-world and synthetic data sets to demonstrate the effectiveness and efficiency of our approach.

This work proposes high-performance critical visualization techniques for exploring real-time and historical traffic loop-detector data. Until recently, it has been difficult to discover trends, identify patterns, or locate abnormalities within the massive collection of traffic data. Many of the current visualization techniques do not scale to large data sets and are not practical for interactive visualization. We have developed an effective visualization system, Highway Operation Monitoring and Evaluation System (HOMES), for observing the summarization of spatiotemporal patterns and trends in traffic data. HOMES is designed for browsing the spatial-temporal dimension hierarchy via integrated roll-up and drill-down operations. The identified traffic patterns and rules can assist decision-making for transportation managers, establish traffic models for researchers and planners, and allow travelers to select commuting routes.

Locally linear classification by pairwise coupling addresses a nonlinear classification problem by three basic phases: decompose the classes of complex concepts into linearly separable subclasses, learn a linear classifier for each pair, and combine pairwise classifiers into a single classifier. A number of methods have been proposed in this framework. However, these methods have two major deficiencies: 1) lack of systematic evaluation of this framework; 2) naive application of clustering algorithms to generate subclasses. This paper proves the equivalence between three popular combination schemas under general settings, defines several global criterion functions for measuring the goodness of subclasses, and presents a supervised greedy clustering algorithm to optimize the proposed criterion functions. Extensive experiments were conducted to validate the effectiveness of the proposed techniques.

A bridging rule in this paper has its antecedent and action from different conceptual clusters. We first design two algorithms for mining bridging rules between clusters in a database, and then propose two non-linear metrics for measuring the interestingness of bridging rules. Bridging rules can be distinct from association rules (or frequent itemsets). This is because (1) bridging rules can be generated by infrequent itemsets that are pruned in association rule mining; and (2) bridging rules are measured by the importance that includes the distance between two conceptual clusters, whereas frequent itemsets are measured by only the support.