Network tomography is a crucial problem in network monitoring, where the observable path performance metric values are used to infer the unobserved ones, making it essential for tasks such as route selection, fault diagnosis, and traffic control. However, most existing methods either assume complete knowledge of network topology and metric formulas—an unrealistic expectation in many real-world scenarios with limited observability—or rely entirely on black-box end-to-end models. To tackle this, in this paper, we argue that a good network tomography requires synergizing the knowledge from both data and appropriate inductive bias from (partial) prior knowledge. To see this, we propose Deep Network Tomography (DeepNT), a novel framework that leverages a path-centric graph neural network to predict path performance metrics without relying on predefined hand-crafted metrics, assumptions, or the real network topology. The path-centric graph neural network learns the path embedding by inferring and aggregating the embeddings of the sequence of nodes that compose this path. Training path-centric graph neural networks requires learning the neural netowrk parameters and network topology under discrete constraints induced by the observed path performance metrics, which motivates us to design a learning objective that imposes connectivity and sparsity constraints on topology and path performance triangle inequality on path performance. Extensive experiments on real-world and synthetic datasets demonstrate the superiority of DeepNT in predicting performance metrics and inferring graph topology compared to state-of-the-art methods.

In the big data era, spatial-network data has become increasingly important and popular in many real-world objects, ranging from micro-scale (e.g., molecule structures), to middle-scale (e.g., biological neural networks), to macro-scale (e.g., mobility networks). Spatial networks consist of nodes and edges that are embedded in a geometric space. Although, it is critical to model and understand the generative process of spatial networks, this task remains largely under-explored due to the significant difficulty in automatically modeling and distinguishing the dependency and relevance among various spatial and network semantic factors. In addition, containing both spatial and network information makes the modeling of spatial networks bear large time and memory cost, especially for large graphs. To address the aforementioned challenges, we first propose a novel objective for joint spatial-network disentangled representation learning from the perspective of information bottleneck as well as a novel progressive optimization algorithm to optimize the intractable objective. Based on this, a Spatial-Network Disentangled Variational Autoencoder (SND-VAE) is proposed to discover the independent and dependent latent factors of spatial and networks. To reduce the time complexity, an efficient version SND-VAE-light is proposed, which is based on a novel Efficient Spatial-Network Message Passing Neural Network (ES-MPNN). Qualitative and quantitative experiments on both synthetic and real-world datasets with various scales of graph size demonstrate the superiority of the proposed model over the state-of-the-arts by up to 66.9% for graph generation and 37.3% for interpretability. In addition, the ES-MPNN is also proved to reduce the time complexity of the encoder in the generative model from cubic to linear growth (The implementation of this work can be found at https://github.com/xguo7/SND-VAE ).

Deep learning has shown remarkable success in the field of clustering recently. However, how to transfer a trained clustering model on a source domain to a target domain by leveraging the acquired knowledge to guide the clustering process remains challenging. Existing deep clustering methods often lack generalizability to new domains because they typically learn a group of fixed cluster centroids, which may not be optimal for the new domain distributions. In this paper, we propose a novel transferable deep clustering model that can automatically adapt the cluster centroids according to the distribution of data samples. Rather than learning a fixed set of centroids, our approach introduces a novel attention-based module that can adapt the centroids by measuring their relationship with samples. In addition, we theoretically show that our model is strictly more powerful than some classical clustering algorithms such as k-means or Gaussian Mixture Model (GMM). Experimental results on both synthetic and real-world datasets demonstrate the effectiveness and efficiency of our proposed transfer learning framework, which significantly improves the performance on target domain and reduces the computational cost.

Text-Attributed Graphs (TAGs) enhance graph structures with natural language descriptions, enabling detailed representation of data and their relationships across a broad spectrum of real-world scenarios. Despite the potential for deeper insights, existing TAG representation learning primarily omit the semantic relationship among node texts, and mostly relies on supervised methods, necessitating extensive labeled data and limiting applicability across diverse contexts. This paper introduces a new self-supervised learning framework, Text-Attributed-Graph Multi-View Alignment (TAGA), which overcomes these constraints by integrating TAGs' structural and semantic dimensions. TAGA constructs two complementary views: Text-of-Graph view, which organizes node texts into structured documents based on graph topology, and the Graph-of-Text view, which converts textual nodes and connections into graph data. By aligning representations from both views, TAGA captures joint textual and structural information. In addition, a novel structure-preserving random walk algorithm is proposed for efficient training on large-sized TAGs. Our framework demonstrates strong performance in zero-shot and few-shot scenarios across eight real-world datasets.

In a multi-stage recommendation system, reranking plays a crucial role in modeling intra-list correlations among items. A key challenge lies in exploring optimal sequences within the combinatorial space of permutations. Recent research follows a two-stage (generator-evaluator) paradigm, where a generator produces multiple feasible sequences, and an evaluator selects the best one. In practice, the generator is typically implemented as an autoregressive model. However, these two-stage methods face two main challenges. First, the separation of the generator and evaluator hinders end-to-end training. Second, autoregressive generators suffer from inference efficiency. In this work, we propose a Unified Generative Efficient Reranking Framework (GReF) to address the two primary challenges. Specifically, we introduce Gen-Reranker, an autoregressive generator featuring a bidirectional encoder and a dynamic autoregressive decoder to generate causal reranking sequences. Subsequently, we pre-train Gen-Reranker on the item exposure order for high-quality parameter initialization. To eliminate the need for the evaluator while integrating sequence-level evaluation during training for end-to-end optimization, we propose post-training the model through Rerank-DPO. Moreover, for efficient autoregressive inference, we introduce ordered multi-token prediction (OMTP), which trains Gen-Reranker to simultaneously generate multiple future items while preserving their order, ensuring practical deployment in real-time recommender systems. Extensive offline experiments demonstrate that GReF outperforms state-of-the-art reranking methods while achieving latency that is nearly comparable to non-autoregressive models. Additionally, GReF has also been deployed in a real-world video app Kuaishou with over 300 million daily active users, significantly improving online recommendation quality.

Deep generative models like VAEs and diffusion models have advanced various generation tasks by leveraging latent variables to learn data distributions and generate high-quality samples. Despite the field of explainable AI making strides in interpreting machine learning models, understanding latent variables in generative models remains challenging. This paper introduces LatentExplainer, a framework for automatically generating semantically meaningful explanations of latent variables in deep generative models. LatentExplainer tackles three main challenges: inferring the meaning of latent variables, aligning explanations with inductive biases, and handling varying degrees of explainability. Our approach perturbs latent variables, interprets changes in generated data, and uses multimodal large language models (MLLMs) to produce human-understandable explanations. We evaluate our proposed method on several real-world and synthetic datasets, and the results demonstrate superior performance in generating high-quality explanations for latent variables. The results highlight the effectiveness of incorporating inductive biases and uncertainty quantification, significantly enhancing model interpretability.

Explainable AI (XAI) has gained significant attention for providing insights into the decision-making processes of deep learning models, particularly for image classification tasks through saliency-based visual explanations. Despite their success, key challenges persist due to the scarcity of annotated datasets and the absence of standardized evaluation protocols. In this paper, we introduce Saliency-Bench, a novel benchmark designed to evaluate visual explanations generated by saliency methods across multiple datasets. We curated, constructed, and annotated eight datasets, each covering diverse tasks such as scene classification, cancer diagnosis, object classification, and action classification, with corresponding ground-truth explanation annotations. The benchmark includes a standardized and unified evaluation pipeline for assessing faithfulness and alignment of the visual explanation, providing a holistic visual explanation performance assessment. We benchmark these eight datasets with widely used saliency methods on different image classifier architectures to evaluate explanation quality. Additionally, we developed an user-friendly toolkit for automating the evaluation pipeline, from data accessing, and data loading, to result evaluation. The benchmark is available at https://github.com/XAIdataset/XAIdataset.github.io.

Network interdiction problems, arising in critical applications from military strategy to disease control, involve a complex attacker-defender dynamic: one player optimizes a network-based objective, while the other strategically modifies the network to impede that objective. The inherent bi-level optimization and combinatorial nature of these problems pose a significant computational challenge, often rendering traditional exact solvers impractical and hindering the development of effective heuristics. While Graph Neural Networks (GNNs) have demonstrated promise in solving single-level combinatorial optimization problems on graphs, their direct application to bi-level interdiction problems remains limited. In this paper, we bridge this gap by introducing a novel approach that leverages the power of GNNs to learn Mixed-Integer Linear Programming (MILP) formulations of network interdiction problems. By representing the problem in this structured mathematical form, we empower a multipartite GNN with the representational capacity to effectively capture the complex interplay between the two players. This approach aligns the neural network with the underlying mathematical structure of interdiction problems, leading to improved performance. Through extensive experiments on two network interdiction tasks, we demonstrate the superiority of our proposed method over both baseline GNN models and traditional exact solvers, showcasing its potential for real-world applications.

This paper presents a novel Chemist-AI Alignment framework for generating novel structures of quaternary ammonium compounds (QACs), a crucial class of antimicrobial agents.The framework uniquely integrates AI-driven small molecule generation with iterative feedback from chemist experts, leveraging both rapid assessments and comprehensive wet-lab validations to optimize for biological potency and synthetic feasibility.Central to the framework is a hierarchical generative model that captures the QAC hierarchical topology.Extensive experiments highlight the efficacy of the framework in identifying promising QAC candidates, many

Despite the recent success of Graph Neural Networks (GNNs), it remains challenging to train GNNs on large-scale graphs due to neighbor explosions. As a remedy, distributed computing becomes a promising solution by leveraging abundant computing resources (e.g., GPU). However, the node dependency of graph data increases the difficulty of achieving high concurrency in distributed GNN training, which suffers from the massive communication overhead. To address it, Historical value approximation is deemed a promising class of distributed training techniques. It utilizes an offline memory to cache historical information (e.g., node embedding) as an affordable approximation of the exact value and achieves high concurrency. However, such benefits come at the cost of involving dated training information, leading to staleness, imprecision, and convergence issues. To overcome these challenges, this paper proposes SAT (Staleness-Alleviated Training), a novel and scalable distributed GNN training framework that reduces the embedding staleness adaptively. The key idea of SAT is to model the GNN’s embedding evolution as a temporal graph and build a model upon it to predict future embedding, which effectively alleviates the staleness of the cached historical embedding. We propose an online algorithm to train the embedding predictor and the distributed GNN alternatively and further provide a convergence analysis. Empirically, we demonstrate that SAT can effectively reduce embedding staleness and thus achieve better performance and convergence speed on multiple large-scale graph datasets. Code available at https://github.com/Ziyang-Yu/SAT.

Research question answering requires accurate retrieval and contextual understanding of scientific literature. However, current Retrieval-Augmented Generation (RAG) methods often struggle to balance complex document relationships with precise information retrieval. In this paper, we introduce Contextualized Graph Retrieval-Augmented Generation (CG-RAG), a novel framework that integrates sparse and dense retrieval signals within graph structures to enhance retrieval efficiency and subsequently improve generation quality for research question answering. First, we propose a contextual graph representation for citation graphs, effectively capturing both explicit and implicit connections within and across documents. Next, we introduce Lexical-Semantic Graph Retrieval (LeSeGR), which seamlessly integrates sparse and dense retrieval signals with graph encoding. It bridges the gap between lexical precision and semantic understanding in citation graph retrieval, demonstrating generalizability to existing graph retrieval and hybrid retrieval methods. Finally, we present a context-aware generation strategy that utilizes the retrieved graph-structured information to generate precise and contextually enriched responses using large language models (LLMs). Extensive experiments on research question answering benchmarks across multiple domains demonstrate that our CG-RAG framework significantly outperforms RAG methods combined with various state-of-the-art retrieval approaches, delivering superior retrieval accuracy and generation quality.

In recent years, Graph Neural Networks (GNNs) have attracted considerable attention. However, the rapid emergence of diverse GNN models, each grounded in different theoretical foundations, complicates the model selection process, as these models are not easily understood within a unified framework. Initial GNNs were constructed using spectral theory, while others were developed based on spatial theory. This theoretical divergence makes direct comparisons difficult. Furthermore, the variety of models within each theoretical domain further complicates their evaluation. In this tutorial, we explore state-of-the-art GNNs and present a comprehensive framework that bridges the spatial and spectral domains, clarifying their interrelationship. This framework deepens our understanding of GNN operations. The tutorial delves into key paradigms, such as spatial and spectral methods, through a synthesis of spectral graph theory and approximation theory. We conduct an in-depth analysis of recent research advancements, addressing emerging issues like over-smoothing, using well-established GNN models to illustrate the universality of our framework.

Text-Attributed Graphs (TAGs) are graphs of connected textual documents. Graph models can efficiently learn TAGs, but their training heavily relies on human-annotated labels, which are scarce or even unavailable in many applications. Large language models (LLMs) have recently demonstrated remarkable capabilities in few-shot and zero-shot TAG learning, but they suffer from scalability, cost, and privacy issues. Therefore, in this work, we focus on synergizing LLMs and graph models with their complementary strengths by distilling the power of LLMs into a local graph model on TAG learning. To address the inherent gaps between LLMs (generative models for texts) and graph models (discriminative models for graphs), we propose first to let LLMs teach an interpreter with rich rationale and then let a student model mimic the interpreter's reasoning without LLMs' rationale. We convert LLM's textual rationales to multi-level graph rationales to train the interpreter model and align the student model with the interpreter model based on the features of TAGs. Extensive experiments validate the efficacy of our proposed framework.

Semantic trajectories, which enrich spatial-temporal data with textual information such as trip purposes or location activities, are key for identifying outlier behaviors critical to healthcare, social security, and urban planning. Traditional outlier detection relies on heuristic rules, which requires domain knowledge and limits its ability to identify unseen outliers. Besides, there lacks a comprehensive approach that can jointly consider multi-modal data across spatial, temporal, and textual dimensions. Addressing the need for a domain-agnostic model, we propose the Transferable Outlier Detection for Human Semantic Trajectories (TOD4Traj) framework. TOD4Traj first introduces a modality feature unification module to align diverse data feature representations, enabling the integration of multi-modal information and enhancing transferability across different datasets. A contrastive learning module is further proposed for identifying regular mobility patterns both temporally and across populations, allowing for a joint detection of outliers based on individual consistency and group majority patterns. Our experimental results have shown TOD4Traj's superior performance over existing models, demonstrating its effectiveness and adaptability in detecting human trajectory outliers across various datasets.

Zero-shot link prediction (ZSLP) on knowledge graphs aims at automatically identifying relations between given entities. Existing methods primarily employ auxiliary information to predict tail entity given head entity and its relation, yet face challenges due to the occasional unavailability of such detailed information and the inherent simplicity of predicting tail entities based on semantic similarities. Even though Large Language Models (LLMs) offer a promising solution to predict unobserved relations between the head and tail entity in a zero-shot manner, their performance is still restricted due to the inability to leverage all the (exponentially many) paths' information between two entities, which are critical in collectively indicating their relation types. To address this, in this work, we introduce a Condensed Transition Graph Framework for Zero-Shot Link Prediction (CTLP), which encodes all the paths' information in linear time complexity to predict unseen relations between entities, attaining both efficiency and information preservation. Specifically, we design a condensed transition graph encoder with theoretical guarantees on its coverage, expressiveness, and efficiency. It is learned by a transition graph contrastive learning strategy. Subsequently, we design a soft instruction tuning to learn and map the all-path embedding to the input of LLMs. Experimental results show that our proposed CTLP method achieves state-of-the-art performance on three standard ZSLP datasets.11The code is available here: https://github.com/ToneLi/Graph_LLM_link_predcition

Over the last decades, a rapidly growing volume of spatiotemporal data has been collected from smartphones and GPS, terrestrial, seaborne, airborne, and spaceborne sensors, as well as computational simulations. Meanwhile, advances in deep learning technologies, especially the recent breakthroughs of generative AI and foundation models such as Large Language Models (LLMs) and Large Vision Models (LVMs), have achieved tremendous success in natural language processing and computer vision applications. There is growing anticipation of the same level of accomplishment of AI on spatiotemporal data in tackling grand societal challenges, such as national water resource management, monitoring coastal hazards, energy and food security, as well as mitigation and adaptation to climate change. When deep learning, especially emerging foundation models, intersects spatiotemporal data in scientific domains, it opens up new opportunities and challenges. The workshop aims to bring together academic researchers in both AI and scientific domains, government program managers, leaders from non-profit organizations, as well as industry executives to brainstorm and debate on the emerging opportunities and novel challenges of deep learning (foundation models) for spatiotemporal data inspired by real-world scientific applications.

Source localization aims to locate information diffusion sources only given the diffusion observation, which has attracted extensive attention in the past few years. Existing methods are mostly tailored for single networks and may not be generalized to handle more complex networks like cross-networks. Cross-network is defined as two interconnected networks, where one network's functionality depends on the other. Source localization on cross-networks entails locating diffusion sources on the source network by only giving the diffused observation in the target network. The task is challenging due to challenges including: 1) diffusion sources distribution modeling; 2) jointly considering both static and dynamic node features; and 3) heterogeneous diffusion patterns learning. In this work, we propose a novel method, namely CNSL, to handle the three primary challenges. Specifically, we propose to learn the distribution of diffusion sources through Bayesian inference and leverage disentangled encoders to learn static and dynamic node features separately. The learning objective is coupled with the cross-network information propagation estimation model to make the inference of diffusion sources considering the overall diffusion process. Additionally, we also provide two novel cross-network datasets collected by ourselves. Extensive experiments are conducted on both datasets to demonstrate the effectiveness of CNSL in handling the source localization on cross-networks.

Time series domain adaptation stands as a pivotal and intricate challenge with diverse applications, including but not limited to human activity recognition, sleep stage classification, and machine fault diagnosis. Despite the numerous domain adaptation techniques proposed to tackle this complex problem, they primarily focus on domain adaptation from a single source domain. Yet, it is more crucial to investigate domain adaptation from multiple domains due to the potential for greater improvements. To address this, three important challenges need to be overcome: 1). The lack of exploration to utilize domain-specific information for domain adaptation, 2). The difficulty to learn domain-specific information that changes over time, and 3). The difficulty to evaluate learned domain-specific information. In order to tackle these challenges simultaneously, in this paper, we introduce PrOmpt-based domaiN Discrimination (POND), the first framework to utilize prompts for time series domain adaptation. Specifically, to address Challenge 1, we extend the idea of prompt tuning to time series analysis and learn prompts to capture common and domain-specific information from all source domains. To handle Challenge 2, we introduce a conditional module for each source domain to generate prompts from time series input data. For Challenge 3, we propose two criteria to select good prompts, which are used to choose the most suitable source domain for domain adaptation. The efficacy and robustness of our proposed POND model are extensively validated through experiments across 50 scenarios encompassing four datasets. Experimental results demonstrate that our proposed POND model outperforms all state-of-the-art comparison methods by up to 66% on the F1-score.

Multi-source spatial point data prediction is crucial in fields like environmental monitoring and natural resource management, where integrating data from various sensors is the key to achieving a holistic environmental understanding. Existing models in this area often fall short due to their domain-specific nature and lack a strategy for integrating information from various sources in the absence of ground truth labels. Key challenges include evaluating the quality of different data sources and modeling spatial relationships among them effectively. Addressing these issues, we introduce an innovative multi-source spatial point data prediction framework that adeptly aligns information from varied sources without relying on ground truth labels. A unique aspect of our method is the 'fidelity score,' a quantitative measure for evaluating the reliability of each data source. Furthermore, we develop a geo-location-aware graph neural network tailored to accurately depict spatial relationships between data points. Our framework has been rigorously tested on two real-world datasets and one synthetic dataset. The results consistently demonstrate its superior performance over existing state-of-the-art methods.

Polygon representation learning is essential for diverse applications, encompassing tasks such as shape coding, building pattern classification, and geographic question answering. While recent years have seen considerable advancements in this field, much of the focus has been on single polygons, overlooking the intricate inner- and inter-polygonal relationships inherent in multipolygons. To address this gap, our study introduces a comprehensive framework specifically designed for learning representations of polygonal geometries, particularly multipolygons. Central to our approach is the incorporation of a heterogeneous visibility graph, which seamlessly integrates both inner- and inter-polygonal relationships. To enhance computational efficiency and minimize graph redundancy, we implement a heterogeneous spanning tree sampling method. Additionally, we devise a rotation-translation invariant geometric representation, ensuring broader applicability across diverse scenarios. Finally, we introduce Multipolygon-GNN, a novel model tailored to leverage the spatial and semantic heterogeneity inherent in the visibility graph. Experiments on five real-world and synthetic datasets demonstrate its ability to capture informative representations for polygonal geometries.

Geometric trees are characterized by their tree-structured layout and spatially constrained nodes and edges, which significantly impacts their topological attributes. This inherent hierarchical structure plays a crucial role in domains such as neuron morphology and river geomorphology, but traditional graph representation methods often overlook these specific characteristics of tree structures. To address this, we introduce a new representation learning framework tailored for geometric trees. It first features a unique message passing neural network, which is both provably geometrical structure-recoverable and rotation-translation invariant. To address the data label scarcity issue, our approach also includes two innovative training targets that reflect the hierarchical ordering and geometric structure of these geometric trees. This enables fully self-supervised learning without explicit labels. We validate our method's effectiveness on eight real-world datasets, demonstrating its capability to represent geometric trees.

Explanation supervision aims to enhance deep learning models by integrating additional signals to guide the generation of model explanations, showcasing notable improvements in both the predictability and explainability of the model. However, the application of explanation supervision to higher-dimensional data, such as 3D medical images, remains an under-explored domain. Challenges associated with supervising visual explanations in the presence of an additional dimension include: 1) spatial correlation changed, 2) lack of direct 3D annotations, and 3) uncertainty varies across different parts of the explanation. To address these challenges, we propose a Dynamic Uncertainty-aware Explanation supervision (DUE) framework for 3D explanation supervision that ensures uncertainty-aware explanation guidance when dealing with sparsely annotated 3D data with diffusion-based 3D interpolation. Our proposed framework is validated through comprehensive experiments on diverse real-world medical imaging datasets. The results demonstrate the effectiveness of our framework in enhancing the predictability and explainability of deep learning models in the context of medical imaging diagnosis applications.

Many real-world networks, such as graph-structured molecules or social networks, exhibit latent hierarchical structures at many different resolutions. Existing hierarchical graph neural networks (GNNs) mainly focus on modifying graph global pooling regions into partitioned clusters, while keeping the convolutional layers unchanged. However, these approaches may suffer from a loss of expressive power in learned representations due to the uncontrolled growth of the neighborhood, leading to a failure in capturing true hierarchies. Furthermore, many real-world hierarchical graphs possess an underlying fractal structure, which is crucial to unraveling the formation mechanism of networks. Unfortunately, existing hierarchical GNNs often overlook this important aspect of graph hierarchy. To tackle these challenges, this paper proposes a generic framework for hierarchical network representation learning. We propose the Self-Similar Graph Neural Network (SS-GNN), which leverages localized representations by excluding redundant nodes and edges. At each resolution of the coarsened map, SS-GNN extracts both intra- and inter-cluster embeddings to preserve the discriminative power of the model with a theoretical guarantee. To exploit the graph fractal structure, we introduce a novel module for measuring self-similarity between resolutions and a characterized objective function for automatic adjustment of model parameters. We demonstrate the strength of our proposed framework through extensive experiments on 13 real-world datasets by outperforming the state-of-the-art GNN models.

Spatial networks are networks whose graph topology is constrained by their embedded spatial space. Understanding the coupled spatial-graph properties is crucial for extracting powerful representations from spatial networks. Therefore, merely combining individual spatial and network representations cannot reveal the underlying interaction mechanism of spatial networks. Besides, existing spatial network representation learning methods can only consider networks embedded in Euclidean space, and can not well exploit the rich geometric information carried by irregular and non-uniform non-Euclidean space. In order to address this issue, in this paper we propose a novel generic framework to learn the representation of spatial networks that are embedded in non-Euclidean manifold space. Specifically, a novel message-passing-based neural network is proposed to combine graph topology and spatial geometry, where spatial geometry is extracted as messages on the edges. We theoretically guarantee that the learned representations are provably invariant to important symmetries such as rotation or translation, and simultaneously maintain sufficient ability in distinguishing different geometric structures. The strength of our proposed method is demonstrated through extensive experiments on both synthetic and real-world datasets.

Online health communities (OHCs) provide an essential platform for patients with similar health conditions to share experiences and offer moral support. However, many time-sensitive questions from patients often remain unanswered due to the multitude of threads and the random nature of patient visits in OHCs. Traditional recommendation systems solely based on similarity for recommendations cannot be directly applied in OHCs. They tend to overlook the influence of patients' dynamically changing features (e.g., health stages), affecting their ability to provide meaningful responses to questions. To address this, we propose a novel recommender system scenario designed for OHCs, which differs from traditional recommender systems in several ways. Firstly, it's challenging to model the social support factors that form helper-seeker links in OHCs. Secondly, the impact of patients' historical activities is complex to quantify. Lastly, ensuring recommended helpers have the requisite expertise is crucial. To overcome these challenges, we develop a Monotonically regularIzed diseNTangled Variational Autoencoders (MINT) model. This model formulates interactions between seekers and helpers as a dynamic graph, using encoded historical activities as node features. We also introduce a graph-based disentangle VAE to capture patient features and a monotonic regularizer to ensure the logical pairing of seekers and helpers. Our extensive experiments show the effectiveness of our approach.

Explanation supervision is a technique that guides a deep learning model to have correct attention during training and thus improve both the interpretability and predictability of the model. However, the exploration of explanation supervision methods for spatiotemporal prediction has been limited. In this paper, we propose a framework for explanation-supervised spatiotemporal forecasting which aims to explicitly incorporate human-annotated spatiotemporal explanations as supervision signals, achieved by introducing a unique objective that integrates human explanations for general spa-tiotemporal predictive models. Specifically, to extend the explanation supervision technique to spatiotemporal prediction, our framework addresses several inherent challenges associated with spatiotemporal data. Firstly, it tackles the difficulty of identifying and correcting the spatiotemporal reasoning process. Secondly, it addresses the challenge of handling the absence of human explanation annotation through interpolation techniques. Lastly, it handles the varying influence of different time points. To evaluate the effectiveness of our approach, we conducted extensive experiments on two real-world spatiotemporal datasets. The results demonstrate the superiority of our methods in improving the interpretability of explanations and the performance of the backbone deep neural network models, surpassing existing state-of-the-art explanation supervision methods.

Forecasting spatiotemporal social events has significant benefits for society to provide the proper amounts and types of resources to manage catastrophes and any accompanying societal risks. Nevertheless, forecasting event subtypes are far more complex than merely extending binary prediction to cover multiple subtypes because of spatial heterogeneity, experiencing a partial set of event subtypes, subtle discrepancy among different event subtypes, nature of the event subtype, spatial correlation of event subtypes. We presentDeep multi-task learning for spatio-temporal incomplete qualitative event forecasting (DETECTIVE) framework to effectively forecast the subtypes of future events by addressing all these issues. This formulates spatial locations into tasks to handle spatial heterogeneity in event subtypes and learns a joint deep representation of subtypes across tasks. This has the adaptability to be used for different types of problem formulation required by the nature of the events. Furthermore, based on the “first law of geography”, spatially-closed tasks share similar event subtypes or scale patterns so that adjacent tasks can share knowledge effectively. To optimize the non-convex and strongly coupled problem of the proposed model, we also propose algorithms based on the Alternating Direction Method of Multipliers (ADMM). Extensive experiments on real-world datasets demonstrate the model’s usefulness and efficiency.

The data generated in many real-world applications can be modeled as heterogeneous graphs of multi-typed entities (nodes) and relations (links). Nowadays, such data are commonly generated and stored by distributed clients, making direct centralized model training unpractical. While the data in each client are prone to biased local distributions, generalizable global models are still in frequent need for large-scale applications. However, the large number of clients enforce significant computational overhead due to the communication and synchronization among the clients, whereas the biased local data distributions indicate that not all clients and parameters should be computed and updated at all times. Motivated by specifically designed preliminary studies on training a state-of-the-art heterogeneous graph neural network (HGN) with the vanilla FedAvg framework, in this work, we propose to leverage the characteristics of heterogeneous graphs by designing dynamic activation strategies for the clients and parameters during the federated training of HGN, named FedDA. Moreover, we design a novel disentangled model D-HGN to enable type-oriented activation of model parameters for FedDA. The effectiveness and efficiency of our proposed techniques are backed by both theoretical and empirical analysis– We theoretically analyze the validity and convergence of FedDA and mathematically illustrate its efficiency gain; meanwhile, we demonstrate the significant performance gains of FedDA and corroborate its efficiency gains with extensive experiments over multiple realistic FL settings synthesized based on real-world heterogeneous graphs.

This work develops a node-edge co-evolution model for attributed graph transformation, where both the node and edge attributes undergo changes due to complex interactions. Due to two fundamental obstacles, learning and approximating attributed graph transformation have not been thoroughly explored: 1) the difficulty of jointly considering four types of atomic interactions including nodes-to-edges, nodes-to-nodes, edges-to-nodes, and edges-to-edges interactions. 2) the difficulty of capturing iterative long-range interactions between nodes and edges. To solve these issues, we offer a novel and scalable equilibrium model, NEC∞, with node-edge message passing and edge-node message passing. Additionally, we propose an efficient optimization algorithm that is based on implicit gradient theorem and includes a theoretical analysis of NEC∞. The effectiveness and efficiency of the proposed model have been demonstrated through extensive experiments on synthetic and real-world data sets.

Explanation supervision is a technique in which the model is guided by human-generated explanations during training. This technique aims to improve both the interpretability and predictability of the model by incorporating human understanding into the training process. Since explanation supervision requires a large scale of training data, the data augmentation technique is necessary to be applied to increase the size and diversity of the original dataset. However, data augmentation on sophisticated data like medical images is particularly challenging due to the following: 1) scarcity of data in training the learning-based data augmenter, 2) difficulty in generating realistic and sophisticated images, and 3) difficulty in ensuring the augmented data indeed boosts the performance of explanation-guided learning. To solve these challenges, we propose an Explanation Iterative Supervision via Saliency-guided Data Augmentation (ESSA) framework for conducting explanation supervision and adversarial-trained image data augmentation via a synergized iterative loop that handles the translation from annotation to sophisticated images and the generation of synthetic image-annotation pairs with an alternating training strategy. Extensive experiments on two datasets from the medical imaging domain demonstrate the effectiveness of our proposed framework in improving both the predictability and explainability of the model.

The field of graph neural networks (GNNs) has seen rapid and incredible strides over the recent years. Graph neural networks, also known as deep learning on graphs, graph representation learning, or geometric deep learning, have become one of the fastest-growing research topics in machine learning, especially deep learning. However, as the field rapidly grows, it has been extremely challenging to gain a global perspective of the developments of GNNs. Therefore, we feel the urgency to bridge the above gap and have a comprehensive tutorial on this fast-growing yet challenging topic.

Continual Learning (CL) is considered a key step toward next-generation Artificial Intelligence. Among various methods, replay-based approaches that maintain and replay a small episodic memory of previous samples are one of the most successful strategies against catastrophic forgetting. However, since forgetting is inevitable given bounded memory and unbounded tasks, ‘how to forget’ is a problem continual learning must address. Therefore, beyond simply avoiding (catastrophic) forgetting, an under-explored issue is how to reasonably forget while ensuring the merits of human memory, including 1) storage efficiency, 2) generalizability, and 3) some interpretability. To achieve these simultaneously, our paper proposes a new saliency-augmented memory completion framework for continual learning, inspired by recent discoveries in memory completion/separation in cognitive neuroscience. Specifically, we innovatively propose to store the part of the image most important to the tasks in episodic memory by saliency map extraction and memory encoding. When learning new tasks, previous data from memory are inpainted by an adaptive data generation module, which is inspired by how humans “complete” episodic memory. The module's parameters are shared cross all tasks and it can be jointly trained with a continual learning classifier as bilevel optimization. Extensive experiments on several continual learning and image classification benchmarks demonstrate the proposed method's effectiveness and efficiency.

Multi-task learning is a framework that enforces different tasks to share their knowledge to improve the generalization performance. It is a long-standing active domain that strives to handle several core issues including which tasks are correlated and similar and how to share the knowledge among correlated tasks. Existing works usually do not distinguish the polarity and magnitude of feature weights and commonly rely on linear correlation, due to three major technical challenges in: 1) optimizing the models that regularize feature weight polarity, 2) deciding whether to regularize sign or magnitude, 3) identifying which tasks should share their sign and/or magnitude patterns. To address them, this paper proposes a new multi-task learning framework that can regularize feature weight signs across tasks, beyond the conventional framework for feature weight regularization. We innovatively formulate such sign-regularization problem as a biconvex inequality constrained optimization upon the multiplications among feature weights with slacks. We then propose a new efficient algorithm for the optimization with theoretical guarantees on generalization performance and convergence. Extensive experiments on multiple datasets show the proposed methods’ effectiveness, efficiency, and reasonableness of the regularized feature weighted patterns.

In this paper, we propose a novel DynAttGraph2Seq framework to model complex dynamic transitions of an individual user's activities and the textual information of the posts over time in online health forums and learning how these correspond to his/her health stage. To achieve this, we first formulate the transition of user activities as a dynamic attributed graph with multi-attributed nodes that evolves over time, then formalize the health stage inference task as a dynamic attributed graph to sequence learning problem. Our proposed model consists of a novel dynamic graph encoder along with a two-level sequential encoder to capture the semantic features from user posts and an interpretable sequence decoder that learn the mapping between a sequence of time-evolving user activity graphs as well as user posts to a sequence of target health stages. We go on to propose new dynamic graph regularization and dynamic graph hierarchical attention mechanisms to facilitate the necessary multi-level interpretability. A comprehensive experimental analysis of its use for a health stage prediction task demonstrates both the effectiveness and the interpretability of the proposed models.

A growing number of research areas such as location-based social networks, intelligent transportation systems, and urban computing utilize large amounts of trajectory data for benchmarking data management approaches and analysis methods. Given the general lackness of available large datasets, realistic synthetic trajectory datasets become important. This work proposes deep generative models for trajectory data that can learn disentangled models for sophisticated latent patterns. Existing methods rely on predefined heuristics and cannot learn the unknown underlying generative mechanisms. The proposed novel deep generative VAE-like models factorize global and local semantics (habits vs. random routing change). We further develop new inference strategies based on variational inference and constrained optimization to encapsulate spatiotemporal validity. New deep neural network architectures are developed to implement generative and inference models with dynamic latent priors. The proposed methods represent significant quantitative and qualitative improvements over existing approaches as demonstrated by extensive experiments. The software is made publicly available 1.

Spatial interpolation is the task to interpolate the targeted index, such as PM2.5 values and temperature, at arbitrary locations based on the collected geospatial data. It greatly affects the key research topics in geoscience in terms of obtaining heterogeneous spatial information (e.g., soil conditions, precipitation rates, wheat yields) for geographic modeling and decision-making at local, regional, and global scales. Point-based data, collected by ground-level in-situ sensors, serve as an important data source for this task. However, several major challenges still exist: point-based data are sparse and unevenly distributed. More importantly, it is difficult to model the unknown spatial predictive mapping while handling the trade-off between spatial autocorrelation and heterogeneity. Third, representing spatial relations without substantial information loss is also a critical issue. To address these challenges, we propose a novel Deep Geometric Spatial Interpolation (DGSI) framework as the interpolation backbone that automatically interpolates the targeted index at unknown locations based on existing observations. Our proposed model takes into account both distance and orientation information, which is proven to preserve spatial information. Extensive experiments have been conducted on real-world datasets and demonstrated our model's superiority in performance over state-of-the-art models.

Analogical reasoning is the process of discovering and mapping correspondences from a target subject to a base subject. As the most well-known computational method of analogical reasoning, Structure-Mapping Theory (SMT) abstracts both target and base subjects into relational graphs and forms the cognitive process of analogical reasoning by finding a corresponding subgraph (i.e., correspondence) in the target graph that is aligned with the base graph. However, incorporating deep learning for SMT is still under-explored due to several obstacles: 1) the combinatorial complexity of searching for the correspondence in the target graph; 2) the correspondence mining is restricted by various cognitive theory-driven constraints. To address both challenges, we propose a novel framework for Analogical Reasoning (DeepGAR) that identifies the correspondence between source and target domains by assuring cognitive theory-driven constraints. Specifically, we design a geometric constraint embedding space to induce subgraph relation from node embeddings for efficient subgraph search. Furthermore, we develop novel learning and optimization strategies that could end-to-end identify correspondences that are strictly consistent with constraints driven by the cognitive theory. Extensive experiments are conducted on synthetic and real-world datasets to demonstrate the effectiveness of the proposed DeepGAR over existing methods. The code and data are available at: https://github.com/triplej0079/DeepGAR.

Spatial autocorrelation and spatial heterogeneity widely exist in spatial data, which make the traditional machine learning model perform badly. Spatial domain generalization is a spatial extension of domain generalization, which can generalize to unseen spatial domains in continuous 2D space. Specifically, it learns a model under varying data distributions that generalizes to unseen domains. Although tremendous success has been achieved in domain generalization, there exist very few works on spatial domain generalization. The advancement of this area is challenged by: 1) Difficulty in characterizing spatial heterogeneity, and 2) Difficulty in obtaining predictive models for unseen locations without training data. To address these challenges, this paper proposes a generic framework for spatial domain generalization. Specifically, We develop the spatial interpolation graph neural network1that handles spatial data as a graph and learns the spatial embedding on each node and their relationships. The spatial interpolation graph neural network infers the spatial embedding of an unseen location during the test phase. Then the spatial embedding of the target location is used to decode the parameters of the downstream-task model directly on the target location. Finally, extensive experiments on ten real-world datasets demonstrate the proposed method’s strength.1https://github.com/dyu62/Deep-domain-generalization

Effectively mining anomalous subgraphs in networks is crucial for many application scenarios, such as disease outbreak detection, financial fraud detection, and activity monitoring in social networks. Identifying anomalous subgraphs is extremely challenging due to their complex topological structures and high-dimensional attributes, various notions of anomalies, and the exponentially large subgraph space in a given graph. Existing classical shallow models typically rely on handcrafted anomaly measure functions, which cannot handle common situations when such prior knowledge is unavailable. Recently, deep learning-based methods provide an end-to-end way that learns the anomaly measure functions. However, although they have achieved great success in detecting node-level, edge-level, and graph-level anomalies, detecting anomalous at the subgraph level has been largely under-explored due to enormous difficulties in subgraph representation learning, supervision, and end-to-end anomaly quantification. To circumvent the above mentioned challenges, this paper proposes a novel deep framework named Anomalous Subgraph Autoencoder (AS-GAE) to extract the anomalous subgraphs in an unsupervised and weakly supervised manner. Specifically, we first develop a location-aware graph auto-encoder to uncover the anomalous areas in the given graph according to the mismatch during the reconstruction. Then a supermodular graph scoring function module is proposed to assign reasonable anomaly scores to the subgraphs in the extracted anomalous areas. The superiority of our proposed method was demonstrated through extensive experiments on two synthetic datasets and nine real-world datasets.

With the advancement of GPS and remote sensing technologies and the pervasiveness of smartphones and IoT devices, an enormous amount of spatiotemporal data are being collected from various domains. Knowledge discovery from spatiotemporal data is crucial in addressing many grand societal challenges, ranging from flood disaster management to monitoring coastal hazards, and from autonomous driving to disease forecasting. The recent success in deep learning technologies in computer vision and natural language processing provides new opportunities for spatiotemporal data mining, but existing deep learning techniques also face unique spatiotemporal challenges (e.g., autocorrelation, non-stationarity, physics awareness). This workshop provides a premium platform for researchers from both academia and industry to exchange ideas on the opportunities, challenges, and cutting-edge techniques related to deep learning for spatiotemporal data.

Multi-task learning (MTL) is a framework that enforces multiple learning tasks to share their knowledge to improve their generalization abilities. While shallow multi-task learning can learn task relations, it can only handle pre-defined features. Modern deep multi-task learning can jointly learn latent features and task sharing, but they are obscure in task relation. Also, they pre-define which layers and neurons should share across tasks and cannot learn adaptively. To address these challenges, this paper proposes a new multi-task learning framework that jointly learns latent features and explicit task relations by complementing the strength of existing shallow and deep multitask learning scenarios. Specifically, we propose to model the task relation as the similarity between tasks' input gradients, with a theoretical analysis of their equivalency. In addition, we innovatively propose a multi-task learning objective that explicitly learns task relations by a new regularizer. Theoretical analysis shows that the generalizability error has been reduced thanks to the proposed regularizer. Extensive experiments on several multi-task learning and image classification benchmarks demonstrate the proposed method's effectiveness, efficiency as well as reasonableness in the learned task relation patterns.

Despite the fast progress of explanation techniques in modern Deep Neural Networks (DNNs) where the main focus is handling "how to generate the explanations", advanced research questions that examine the quality of the explanation itself (e.g., "whether the explanations are accurate") and improve the explanation quality (e.g., "how to adjust the model to generate more accurate explanations when explanations are inaccurate") are still relatively under-explored. To guide the model toward better explanations, techniques in explanation supervision - which add supervision signals on the model explanation - have started to show promising effects on improving both the generalizability as and intrinsic interpretability of Deep Neural Networks. However, the research on supervising explanations, especially in vision-based applications represented through saliency maps, is in its early stage due to several inherent challenges: 1) inaccuracy of the human explanation annotation boundary, 2) incompleteness of the human explanation annotation region, and 3) inconsistency of the data distribution between human annotation and model explanation maps. To address the challenges, we propose a generic RES framework for guiding visual explanation by developing a novel objective that handles inaccurate boundary, incomplete region, and inconsistent distribution of human annotations, with a theoretical justification on model generalizability. Extensive experiments on two real-world image datasets demonstrate the effectiveness of the proposed framework on enhancing both the reasonability of the explanation and the performance of the backbone DNNs model.

Graph diffusion problems such as the propagation of rumors, computer viruses, or smart grid failures are ubiquitous and societal. Hence it is usually crucial to identify diffusion sources according to the current graph diffusion observations. Despite its tremendous necessity and significance in practice, source localization, as the inverse problem of graph diffusion, is extremely challenging as it is ill-posed: different sources may lead to the same graph diffusion patterns. Different from most traditional source localization methods, this paper focuses on a probabilistic manner to account for the uncertainty of different candidate sources. Such endeavors require to overcome significant challenges along the way including: 1) the uncertainty in graph diffusion source localization is hard to be quantified; 2) the complex patterns of the graph diffusion sources are difficult to be probabilistically characterized; 3) the generalization under any underlying diffusion patterns is hard to be imposed. To solve the above challenges, this paper presents a generic framework: Source Localization Variational AutoEncoder (SL-VAE) for locating the diffusion sources under arbitrary diffusion patterns. Particularly, we propose a probabilistic model that leverages the forward diffusion estimation model along with deep generative models to approximate the diffusion source distribution for quantifying the uncertainty. SL-VAE further utilizes prior knowledge of the source-observation pairs to characterize the complex patterns of diffusion sources by a learned generative prior. Lastly, a unified objective that integrates the forward diffusion estimation model is derived to enforce the model to generalize under arbitrary diffusion patterns. Extensive experiments are conducted on $7$ real-world datasets to demonstrate the superiority of SL-VAE in reconstructing the diffusion sources by excelling the state-of-the-arts on average 20% in AUC score. The code and data are available at: https://github.com/triplej0079/SLVAE.

The field of graph neural networks (GNNs) has seen rapid and incredible strides over the recent years. Graph neural networks, also known as deep learning on graphs, graph representation learning, or geometric deep learning, have become one of the fastest-growing research topics in machine learning, especially deep learning. This wave of research at the intersection of graph theory and deep learning has also influenced other fields of science, including recommendation systems, computer vision, natural language processing, inductive logic programming, program synthesis, software mining, automated planning, cybersecurity, and intelligent transportation. However, as the field rapidly grows, it has been extremely challenging to gain a global perspective of the developments of GNNs. Therefore, we feel the urgency to bridge the above gap and have a comprehensive tutorial on this fast-growing yet challenging topic. This tutorial of Graph Neural Networks (GNNs): Foundation, Frontiers and Applications will cover a broad range of topics in graph neural networks, by reviewing and introducing the fundamental concepts and algorithms of GNNs, new research frontiers of GNNs, and broad and emerging applications with GNNs. In addition, rich tutorial materials will be included and introduced to help the audience gain a systematic understanding by using our recently published book-Graph Neural Networks (GNN): Foundation, Frontiers, and Applications [12], which can easily be accessed at https://graph-neural-networks.github.io/index.html.

Designing molecules with specific properties is a long-lasting research problem and is central to advancing crucial domains such as drug discovery and material science. Recent advances in deep graph generative models treat molecule design as graph generation problems which provide new opportunities toward the breakthrough of this long-lasting problem. Existing models, however, have many shortcomings, including poor interpretability and controllability toward desired molecular properties. This paper focuses on new methodologies for molecule generation with interpretable and controllable deep generative models, by proposing new monotonically-regularized graph variational autoencoders. The proposed models learn to represent the molecules with latent variables and then learn the correspondence between them and molecule properties parameterized by polynomial functions. To further improve the intepretability and controllability of molecule generation towards desired properties, we derive new objectives which further enforce monotonicity of the relation between some latent variables and target molecule properties such as toxicity and clogP. Extensive experimental evaluation demonstrates the superiority of the proposed framework on accuracy, novelty, disentanglement, and control towards desired molecular properties. The code is anonymized at https://anonymous.4open.science/r/MDVAE-FD2C.

Localizing the source of graph diffusion phenomena, such as misinformation propagation, is an important yet extremely challenging task in the real world. Existing source localization models typically are heavily dependent on the hand-crafted rules and only tailored for certain domain-specific applications. Unfortunately, a large portion of the graph diffusion process for many applications is still unknown to human beings so it is important to have expressive models for learning such underlying rules automatically. Recently, there is a surge of research body on expressive models such as Graph Neural Networks (GNNs) for automatically learning the underlying graph diffusion. However, source localization is instead the inverse of graph diffusion, which is a typical inverse problem in graphs that is well-known to be ill-posed because there can be multiple solutions and hence different from the traditional (semi-)supervised learning settings. This paper aims to establish a generic framework of invertible graph diffusion models for source localization on graphs, namely Invertible Validity-aware Graph Diffusion (IVGD), to handle major challenges including 1) Difficulty to leverage knowledge in graph diffusion models for modeling their inverse processes in an end-to-end fashion, 2) Difficulty to ensure the validity of the inferred sources, and 3) Efficiency and scalability in source inference. Specifically, first, to inversely infer sources of graph diffusion, we propose a graph residual scenario to make existing graph diffusion models invertible with theoretical guarantees; second, we develop a novel error compensation mechanism that learns to offset the errors of the inferred sources. Finally, to ensure the validity of the inferred sources, a new set of validity-aware layers have been devised to project inferred sources to feasible regions by flexibly encoding constraints with unrolled optimization techniques. A linearization technique is proposed to strengthen the efficiency of our proposed layers. The convergence of the proposed IVGD is proven theoretically. Extensive experiments on nine real-world datasets demonstrate that our proposed IVGD outperforms state-of-the-art comparison methods significantly. We have released our code at https://github.com/xianggebenben/IVGD.

In today’s era of big data, robust least-squares regression becomes a more challenging problem when considering the extremely corrupted labels along with explosive growth of datasets. Traditional robust methods can handle the noise but suffer from several challenges when applied in huge dataset including (1) computational infeasibility of handling an entire dataset at once, (2) existence of heterogeneously distributed corruption, and (3) difficulty in corruption estimation when data cannot be entirely loaded. This article proposes online and distributed robust regression approaches, both of which can concurrently address all the above challenges. Specifically, the distributed algorithm optimizes the regression coefficients of each data block via heuristic hard thresholding and combines all the estimates in a distributed robust consolidation. In addition, an online version of the distributed algorithm is proposed to incrementally update the existing estimates with new incoming data. Furthermore, a novel online robust regression method is proposed to estimate under a biased-batch corruption. We also prove that our algorithms benefit from strong robustness guarantees in terms of regression coefficient recovery with a constant upper bound on the error of state-of-the-art batch methods. Extensive experiments on synthetic and real datasets demonstrate that our approaches are superior to those of existing methods in effectiveness, with competitive efficiency.

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.

In recent years, graph neural networks (GNNs) and the research on their explainability are experiencing rapid developments and achieving significant progress. Many methods are proposed to explain the predictions of GNNs, focusing on “how to generate explanations” However, research questions like “whether the GNN explanations are inaccurate”, “what if the explanations are inaccurate”, and “how to adjust the model to generate more accurate explanations” have not been well explored. To address the above questions, this paper proposes a GNN Explanation Supervision (GNES)1framework to adaptively learn how to explain GNNs more correctly. Specifically, our framework jointly optimizes both model prediction and model explanation by enforcing both whole graph regularization and weak supervision on model explanations. For the graph regularization, we propose a unified explanation formulation for both node-level and edge-level explanations by enforcing the consistency between them. The node- and edge-level explanation techniques we propose are also generic and rigorously demonstrated to cover several existing major explainers as special cases. Extensive experiments on five real-world datasets across two application domains demonstrate the effectiveness of the proposed model on improving the reasonability of the explanation while still keep or even improve the backbone GNNs model performance.1Code available at: https://github.com/YuyangGao/GNES.

Heterogeneous graphs are ubiquitous data structures that can inherently capture multi-type and multi-modal interactions between objects. In recent years, research on encoding heterogeneous graph into latent representations have enjoyed a rapid increase. However, its reverse process, namely how to construct heterogeneous graphs from underlying representations and distributions have not been well explored due to several challenges in 1) modeling the local heterogeneous semantic distribution; 2) preserving the graph-structured distributions over the local semantics; and 3) characterizing the global heterogeneous graph distributions. To address these challenges, we propose a novel framework for heterogeneous graph generation (HGEN) that jointly captures the semantic, structural, and global distributions of heterogeneous graphs. Specifically, we propose a heterogeneous walk generator that hierarchically generates meta-paths and their path instances. In addition, a novel heterogeneous graph assembler is developed that can sample and combine the generated meta-path instances (e.g., walks) into heterogeneous graphs in a stratified manner. Theoretical analysis on the preservation of heterogeneous graph patterns by the proposed generation process has been performed. Extensive experiments1on multiple real-world and synthetic heterogeneous graph datasets demonstrate the effectiveness of the proposed HGEN in generating realistic heterogeneous graphs.1https://github.com/lingchen0331/HGEN

Spatial networks represent crucial data structures where the nodes and edges are embedded in a geometric space. Nowadays, spatial network data is becoming increasingly popular and important, ranging from microscale (e.g., protein structures), to middle-scale (e.g., biological neural networks), to macro-scale (e.g., mobility networks). Although, modeling and understanding the generative process of spatial networks are very important, they remain largely under-explored due to the significant challenges in automatically modeling and distinguishing the independency and correlation among various spatial and network factors. To address these challenges, we first propose a novel objective for joint spatial-network disentanglement from the perspective of information bottleneck as well as a novel optimization algorithm to optimize the intractable objective. Based on this, a spatial-network variational autoencoder (SND-VAE) with a new spatial-network message passing neural network (S-MPNN) is proposed to discover the independent and dependent latent factors of spatial and networks. Qualitative and quantitative experiments on both synthetic and real-world datasets demonstrate the superiority of the proposed model over the state-of-the-arts by up to 66.9% for graph generation and 37.3% for interpretability.

With the advancement of GPS and remote sensing technologies and the pervasiveness of smartphones and mobile devices, large amounts of spatiotemporal data are being collected from various domains. Knowledge discovery from spatiotemporal data is crucial in broad societal applications. Examples range from mapping flooded areas on satellite imagery for disaster response to monitoring crop health for food security, from estimating travel time between locations on Google Maps to forecasting hotspots of diseases like Covid-19 in public health. The recent success in deep learning technologies in computer vision and natural language processing provides unique opportunities for spatiotemporal data mining (e.g., automatically extracting spatial contextual features without manual feature engineering) but also faces unique challenges (e.g., spatial autocorrelation, heterogeneity, multiple scales, and resolutions, the existence of domain knowledge and constraints). This workshop provides a premium platform for researchers from both academia and industry to exchange ideas on opportunities, challenges, and cutting-edge techniques of deep learning for spatiotemporal data. We hope to inspire novel ideas and visions through the workshop and facilitate the development of this emerging research area.

Deep generative models for graphs have exhibited promising performance in ever-increasing domains such as design of molecules (i.e, graph of atoms) and structure prediction of proteins (i.e., graph of amino acids). Existing work typically focuses on static rather than dynamic graphs, which are actually very important in the applications such as protein folding, molecule reactions, and human mobility. Extending existing deep generative models from static to dynamic graphs is a challenging task, which requires to handle the factorization of static and dynamic characteristics as well as mutual interactions among node and edge patterns. Here, this paper proposes a novel framework of factorized deep generative models to achieve interpretable dynamic graph generation. Various generative models are proposed to characterize conditional independence among node, edge, static, and dynamic factors. Then, variational optimization strategies as well as dynamic graph decoders are proposed based on newly designed factorized variational autoencoders and recurrent graph deconvolutions. Extensive experiments on multiple datasets demonstrate the effectiveness of the proposed models.

During the pandemic caused by coronavirus disease (COVID-19), social media has played an important role by enabling people to discuss their experiences and feelings of this global crisis. To help combat the prolonged pandemic that has exposed vulnerabilities impacting community resilience, in this paper, based on our established large-scale COVID-19 related social media data, we propose and develop an integrated framework (named Dr.Emotion) to learn disentangled representations of social media posts (i.e., tweets) for emotion analysis and thus to gain deep insights into public perceptions towards COVID-19. In Dr.Emotion, for given social media posts, we first post-train a transformer-based model to obtain the initial post embeddings. Since users may implicitly express their emotions in social media posts which could be highly entangled with other descriptive information in the post content, to address this challenge for emotion analysis, we propose an adversarial disentangler by integrating emotion-independent (i.e., sentiment-neutral) priors of the posts generated by another post-trained transformer-based model to separate and disentangle the implicitly encoded emotions from the content in latent space for emotion classification at the first attempt. Extensive experimental studies are conducted to fully evaluate Dr.Emotion and promising results demonstrate its performance in emotion analysis by comparison with the state-of-the-art baseline methods. By exploiting our developed Dr.Emotion, we further perform emotion analysis over a large number of social media posts and provide in-depth investigation from both temporal and geographical perspectives, based on which additional work can be conducted to extract and transform the constructive ideas, experiences and support into actionable information to improve community resilience in responses to a variety of crises created by COVID-19 and well beyond.

Deep generative models of graph-structured data have become popular in very recent years. Although initial research has focused on static graphs in applications such as molecular design and social networks, many challenges involve temporal graphs whose topology and attribute values evolve dynamically over time. Sophisticated and unknown network processes that affect temporal graphs cannot be captured adequately by prescribed models. Application areas include social mobility networks and catastrophic cybersecurity failures. These web-scale applications challenge current deep graph generative models with the need to capture 1) time-validity constraints, 2) time and topological distributions, and 3) joint time and graph encoding and decoding. Here, we propose the “Temporal Graph Generative Adversarial Network” (TG-GAN) for continuous-time graph generation with time-validity constraints 1. TG-GAN can jointly generate the time, node, and edge information for truncated temporal walks via a novel recurrent-based model and a valid time decoder. The generated truncated temporal walks are then assembled into time-budgeted temporal walks for temporal graphs under the learned topological and temporal dependencies. In addition, a discriminator is proposed to combine time and node encoding operations over a recurrent architecture to distinguish generated sequences from real ones sampled by a truncated temporal walk sampler. Extensive experiments on both synthetic and real-world datasets confirm that TG-GAN significantly outperforms five benchmarking methods in terms of efficiency and effectiveness.

With the rapid growth of real-time machine learning applications, the process of feature selection and model optimization requires to integrate with the constraints on computational budgets. A specific computational resource in this regard is the time needed for evaluating predictions on test instances. The joint optimization problem of prediction accuracy and prediction-time efficiency draws more and more attention in the data mining and machine learning communities. The runtime cost is dominated by the feature generation process that contains significantly redundant computations across different features that sharing the same computational component in practice. Eliminating such redundancies would obviously reduce the time costs in the feature generation process. Our previous Cost-aware classification using Feature computational dependencies heterogeneous Hypergraph (CAFH) model has achieved excellent performance on the effectiveness. In the big data era, the high dimensionality caused by the heterogeneous data sources leads to the difficulty in fitting the entire hypergraph into the main memory and the high computational cost during the optimization process. Simply partitioning the features into batches cannot give the optimal solution since it will lose some feature dependencies across the batches. To improve the high memory and computational costs in the CAFH model, we propose an equivalent Accelerated CAFH (ACAFH) model based on the lossless heterogeneous hypergraph decomposition. An efficient and effective nonconvex optimization algorithm based on the alternating direction method of multipliers (ADMM) is developed to optimize the ACAFH model. The time and space complexities of the optimization algorithm for the ACAFH model are three and one polynomial degrees less than our previous algorithm for the CAFH model, respectively. Extensive experiments demonstrate the proposed ACAFH model achieves competitive performance on the effectiveness and much better performance on the efficiency.

The emerging underground markets (e.g., Hack Forums) have been widely used by cybercriminals to trade in illicit products or services, which have played a vital role in the cybercriminal ecosystem. In order to combat the evolving cybercrimes, in this paper, we propose and develop an intelligent framework (named PIdentifier) to automate the analysis of Hack Forums for the identification of illicit product traded in a private contract at the first attempt (to evade the law enforcement, a private contract is made between a vendor and a buyer where the traded product and its detail are invisible). In PIdentifier, based on the large-scale extracted user profiles, user posts and different types of relations within the complex ecosystem in Hack Forums, we first introduce an attributed heterogeneous information network (AHIN) to model the rich semantics and complex relations among multi-typed entities (i.e., vendors, buyers, products, comments and topics). Then, we design different metagraphs to formulate the relatedness between buyers and products based on which a metagraph aggregated heterogeneous graph neural network (denoted as mHGNN) is proposed to learn node representations for illicit traded product identification by attentively propagating and aggregating the neighborhood information defined by the designed metagraphs. Comprehensive experiments are conducted on the real-world dataset collected from Hack Forums. Promising results demonstrate the performance of our proposed PIdentifier framework in illicit traded product identification by comparison with the state-of-the-art baselines.

Alternating Direction Method of Multipliers (ADMM) has recently been proposed as a potential alternative optimizer to the Stochastic Gradient Descent(SGD) for deep learning problems. This is because ADMM can solve gradient vanishing and poor conditioning problems. Moreover, it has shown good scalability in many large-scale deep learning applications. However, there still lacks a parallel ADMM computational framework for deep neural networks because of layer dependency among variables. In this paper, we propose a novel parallel deep learning ADMM framework (pdADMM) to achieve layer parallelism: parameters in each layer of neural networks can be updated independently in parallel. The convergence of the proposed pdADMM to a critical point is theoretically proven under mild conditions. The convergence rate of the pdADMM is proven to be o(1/k) where k is the number of iterations. Extensive experiments on six benchmark datasets demonstrated that our proposed pdADMM can lead to more than 10 times speedup for training large-scale deep neural networks, and outperformed most of the comparison methods. Our code is available at: https://github.com/xianggebenben/pdADMM.

Disentangled representation learning has recently attracted a significant amount of attention, particularly in the field of image representation learning. However, learning the disentangled representations behind a graph remains largely unexplored, especially for the attributed graph with both node and edge features. Disentanglement learning for graph generation has substantial new challenges including 1) the lack of graph deconvolution operations to jointly decode node and edge attributes; and 2) the difficulty in enforcing the disentanglement among latent factors that respectively influence: i) only nodes, ii) only edges, and iii) joint patterns between them. To address these challenges, we propose a new disentanglement enhancement framework for deep generative models for attributed graphs. In particular, a novel variational objective is proposed to disentangle the above three types of latent factors, with novel architecture for node and edge deconvolutions. Qualitative and quantitative experiments on both synthetic and real-world datasets demonstrate the effectiveness of the proposed model and its extensions.

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.

Despite the apparent benefits of modern social coding paradigm such as Stack Overflow, its potential security risks have been largely overlooked (e.g., insecure codes could be easily embedded and distributed). To address this imminent issue, in this paper, we bring a significant insight to leverage both social coding properties and code content for automatic detection of insecure code snippets in Stack Overflow. To determine if the given code snippets are insecure, we not only analyze the code content, but also utilize various kinds of relations among users, badges, questions, answers and code snippets in Stack Overflow. To model the rich semantic relationships, we first introduce a structured heterogeneous information network (HIN) for representation and then use meta-path based approach to incorporate higher-level semantics to build up relatedness over code snippets. Later, we propose a novel hierarchical attention-based sequence learning model named CodeHin2Vec to seamlessly integrate node (i.e., code snippet) content with HIN-based relations for representation learning. After that, a classifier is built for insecure code snippet detection. Integrating our proposed method, an intelligent system named iTrustSO is accordingly developed to address the code security issues in modern software coding platforms. Comprehensive experiments on the data collections from Stack Overflow are conducted to validate the effectiveness of our developed system iTrustSO by comparisons with alternative methods.

At present, object recognition studies are mostly conducted in a closed lab setting with classes in test phase typically in training phase. However, real-world problem are far more challenging because: i)~new classes unseen in the training phase can appear when predicting; ii)~discriminative features need to evolve when new classes emerge in real time; and iii)~instances in new classes may not follow the "independent and identically distributed" (iid) assumption. Most existing work only aims to detect the unknown classes and is incapable of continuing to learn newer classes. Although a few methods consider both detecting and including new classes, all are based on the predefined handcrafted features that cannot evolve and are out-of-date for characterizing emerging classes. Thus, to address the above challenges, we propose a novel generic end-to-end framework consisting of a dynamic cascade of classifiers that incrementally learn their dynamic and inherent features. The proposed method injects dynamic elements into the system by detecting instances from unknown classes, while at the same time incrementally updating the model to include the new classes. The resulting cascade tree grows by adding a new leaf node classifier once a new class is detected, and the discriminative features are updated via an end-to-end learning strategy. Experiments on two real-world datasets demonstrate that our proposed method outperforms existing state-of-the-art methods.

Online underground forums have been widely used by cybercriminals to exchange knowledge and trade in illicit products or services, which have played a central role in the cybercriminal ecosystem. In order to combat the evolving cybercrimes, in this paper, we propose and develop an intelligent system named iDetective to automate the analysis of underground forums for the identification of key players (i.e., users who play the vital role in the value chain). In iDetective, we first introduce an attributed heterogeneous information network (AHIN) for user representation and use a meta-path based approach to incorporate higher-level semantics to build up relatedness over users in underground forums; then we propose Player2Vec to efficiently learn node (i.e., user) representations in AHIN for key player identification. In Player2Vec, we first map the constructed AHIN to a multi-view network which consists of multiple single-view attributed graphs encoding the relatedness over users depicted by different designed meta-paths; then we employ graph convolutional network (GCN) to learn embeddings of each single-view attributed graph; later, an attention mechanism is designed to fuse different embeddings learned based on different single-view attributed graphs for final representations. Comprehensive experiments on the data collections from different underground forums (i.e., Hack Forums, Nulled) are conducted to validate the effectiveness of iDetective in key player identification by comparisons with alternative approaches.

Critical incident stages identification and reasonable prediction of traffic incident duration are essential in traffic incident management. In this paper, we propose a traffic incident duration prediction model that simultaneously predicts the impact of the traffic incidents and identifies the critical groups of temporal features via a multi-task learning framework. First, we formulate a sparsity optimization problem that extracts low-level temporal features based on traffic speed readings and then generalizes higher level features as phases of traffic incidents. Second, we propose novel constraints on feature similarity exploiting prior knowledge about the spatial connectivity of the road network to predict the incident duration. The proposed problem is challenging to solve due to the orthogonality constraints, non-convexity objective, and non-smoothness penalties. We develop an algorithm based on the alternating direction method of multipliers (ADMM) framework to solve the proposed formulation. Extensive experiments and comparisons to other models on real-world traffic data and traffic incident records justify the efficacy of our model.

Online health communities such as the online breast cancer forum enable patients (i.e., users) to interact and help each other within various subforums, which are subsections of the main forum devoted to specific health topics. The changing nature of the users' activities in different subforums can be strong indicators of their health status changes. This additional information could allow health-care organizations to respond promptly and provide additional help for the patient. However, modeling complex transitions of an individual user's activities among different subforums over time and learning how these correspond to his/her health stage are extremely challenging. In this paper, we first formulate the transition of user activities as a dynamic graph with multi-attributed nodes, then formalize the health stage inference task as a dynamic graph-to-sequence learning problem, and hence propose a novel dynamic graph-to-sequence neural networks architecture (DynGraph2Seq) to address all the challenges. Our proposed DynGraph2Seq model consists of a novel dynamic graph encoder and an interpretable sequence decoder that learn the mapping between a sequence of time-evolving user activity graphs and a sequence of target health stages. We go on to propose dynamic graph hierarchical attention mechanisms to facilitate the necessary multi-level interpretability. A comprehensive experimental analysis of its use for a health stage prediction task demonstrates both the effectiveness and the interpretability of the proposed models.

Generalized from image and language translation, graph translation aims to generate a graph in the target domain by conditioning an input graph in the source domain. This promising topic has attracted fast-increasing attention recently. Existing works are limited to either merely predicting the node attributes of graphs with fixed topology or predicting only the graph topology without considering node attributes, but cannot simultaneously predict both of them, due to substantial challenges: 1) difficulty in characterizing the interactive, iterative, and asynchronous translation process of both nodes and edges and 2) difficulty in discovering and maintaining the inherent consistency between the node and edge in predicted graphs. These challenges prevent a generic, end-to-end framework for joint node and edge attributes prediction, which is a need for real-world applications such as malware confinement in IoT networks and structural-to-functional network translation. These real-world applications highly depend on hand-crafting and ad-hoc heuristic models, but cannot sufficiently utilize massive historical data. In this paper, we termed this generic problem "multi-attributed graph translation" and developed a novel framework integrating both node and edge translations seamlessly. The novel edge translation path is generic which is proven to be a generalization of the existing topology translation models. Then, a spectral graph regularization based on our non-parametric graph Laplacian is proposed to learn and maintain the consistency of the predicted nodes and edges. Finally, extensive experiments on both synthetic and real-world application data demonstrated the effectiveness of the proposed method.

A controlled experiment is an empirical interventional study method to evaluate the causal impact of an intervention, by identifying the dynamic feature dependency patterns in the contrast multivariate time series (CMTS) collected from the control and experimental groups. Manually labeling or interpreting the effects caused by the intervention from the CMTS data has become an infeasible task even for domain experts. Thus, it is imperative to develop an integrated technique, preferably in an unsupervised manner, that can simultaneously identify and characterize feature dynamic dependencies and their contrast patterns in CMTS, which we call the contrast dynamic feature dependency (CDFD) patterns. In this paper, we propose a generative model with partial correlation-based feature dependency regularization to help analysts understand the CMTS data by jointly 1) characterizing a set of comparable multivariate Gaussian distributions from CMTS, and 2) determining whether the intervention causes the changes between two comparable distributions. Extensive experiments demonstrate the effectiveness and scalability of the proposed method. The proposed method applied to a driving behavior application demonstrates its utility and interpretability.

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.

Alternating Direction Method of Multipliers (ADMM) has been used successfully in many conventional machine learning applications and is considered to be a useful alternative to Stochastic Gradient Descent (SGD) as a deep learning optimizer. However, as an emerging domain, several challenges remain, including 1) The lack of global convergence guarantees, 2) Slow convergence towards solutions, and 3) Cubic time complexity with regard to feature dimensions. In this paper, we propose a novel optimization framework for deep learning via ADMM (dlADMM) to address these challenges simultaneously. The parameters in each layer are updated backward and then forward so that the parameter information in each layer is exchanged efficiently. The time complexity is reduced from cubic to quadratic in (latent) feature dimensions via a dedicated algorithm design for subproblems that enhances them utilizing iterative quadratic approximations and backtracking. Finally, we provide the first proof of global convergence for an ADMM-based method (dlADMM) in a deep neural network problem under mild conditions. Experiments on benchmark datasets demonstrated that our proposed dlADMM algorithm outperforms most of the comparison methods.

Analysis of large-scale sequential data has been one of the most crucial tasks in areas such as bioinformatics, text, and audio mining. Existing string kernels, however, either (i) rely on local features of short substructures in the string, which hardly capture long discriminative patterns, (ii) sum over too many substructures, such as all possible subsequences, which leads to diagonal dominance of the kernel matrix, or (iii) rely on non-positive-definite similarity measures derived from the edit distance. Furthermore, while there have been works addressing the computational challenge with respect to the length of string, most of them still experience quadratic complexity in terms of the number of training samples when used in a kernel-based classifier. In this paper, we present a new class of global string kernels that aims to (i) discover global properties hidden in the strings through global alignments, (ii) maintain positive-definiteness of the kernel, without introducing a diagonal dominant kernel matrix, and (iii) have a training cost linear with respect to not only the length of the string but also the number of training string samples. To this end, the proposed kernels are explicitly defined through a series of different random feature maps, each corresponding to a distribution of random strings. We show that kernels defined this way are always positive-definite, and exhibit computational benefits as they always produce Random String Embeddings (RSE) that can be directly used in any linear classification models. Our extensive experiments on nine benchmark datasets corroborate that RSE achieves better or comparable accuracy in comparison to state-of-the-art baselines, especially with the strings of longer lengths. In addition, we empirically show that RSE scales linearly with the increase of the number and the length of string.

Graph kernels are widely used for measuring the similarity between graphs. Many existing graph kernels, which focus on local patterns within graphs rather than their global properties, suffer from significant structure information loss when representing graphs. Some recent global graph kernels, which utilizes the alignment of geometric node embeddings of graphs, yield state-of-the-art performance. However, these graph kernels are not necessarily positive-definite. More importantly, computing the graph kernel matrix will have at least quadratic time complexity in terms of the number and the size of the graphs. In this paper, we propose a new family of global alignment graph kernels, which take into account the global properties of graphs by using geometric node embeddings and an associated node transportation based on earth mover's distance. Compared to existing global kernels, the proposed kernel is positive-definite. Our graph kernel is obtained by defining a distribution over random graphs, which can naturally yield random feature approximations. The random feature approximations lead to our graph embeddings, which is named as "random graph embeddings" (RGE). In particular, RGE is shown to achieve (quasi-)linear scalability with respect to the number and the size of the graphs. The experimental results on nine benchmark datasets demonstrate that RGE outperforms or matches twelve state-of-the-art graph classification algorithms.

Due to its anonymity, there has been a dramatic growth of underground drug markets hosted in the darknet (e.g., Dream Market and Valhalla). To combat drug trafficking (a.k.a. illicit drug trading) in the cyberspace, there is an urgent need for automatic analysis of participants in darknet markets. However, one of the key challenges is that drug traffickers (i.e., vendors) may maintain multiple accounts across different markets or within the same market. To address this issue, in this paper, we propose and develop an intelligent system named uStyle-uID leveraging both writing and photography styles for drug trafficker identification at the first attempt. At the core of uStyle-uID is an attributed heterogeneous information network (AHIN) which elegantly integrates both writing and photography styles along with the text and photo contents, as well as other supporting attributes (i.e., trafficker and drug information) and various kinds of relations. Built on the constructed AHIN, to efficiently measure the relatedness over nodes (i.e., traffickers) in the constructed AHIN, we propose a new network embedding model Vendor2Vec to learn the low-dimensional representations for the nodes in AHIN, which leverages complementary attribute information attached in the nodes to guide the meta-path based random walk for path instances sampling. After that, we devise a learning model named vIdentifier to classify if a given pair of traffickers are the same individual. Comprehensive experiments on the data collections from four different darknet markets are conducted to validate the effectiveness of uStyle-uID which integrates our proposed method in drug trafficker identification by comparisons with alternative approaches.

The presence of data noise and corruptions has recently invoked increasing attention on robust least-squares regression ( RLSR ), which addresses this fundamental problem that learns reliable regression coefficients when response variables can be arbitrarily corrupted. Until now, the following important challenges could not be handled concurrently: (1) rigorous recovery guarantee of regression coefficients, (2) difficulty in estimating the corruption ratio parameter, and (3) scaling to massive datasets. This article proposes a novel Robust regression algorithm via Heuristic Corruption Thresholding ( RHCT ) that concurrently addresses all the above challenges. Specifically, the algorithm alternately optimizes the regression coefficients and estimates the optimal uncorrupted set via heuristic thresholding without a pre-defined corruption ratio parameter until its convergence. Moreover, to improve the efficiency of corruption estimation in large-scale data, a Robust regression algorithm via Adaptive Corruption Thresholding ( RACT ) is proposed to determine the size of the uncorrupted set in a novel adaptive search method without iterating data samples exhaustively. In addition, we prove that our algorithms benefit from strong guarantees analogous to those of state-of-the-art methods in terms of convergence rates and recovery guarantees. Extensive experiments demonstrate that the effectiveness of our new methods is superior to that of existing methods in the recovery of both regression coefficients and uncorrupted sets, with very competitive efficiency.

It is important to track adverse events that occur due to flu shots as those could pose a serious threat to public health. Traditional adverse event reporting systems suffer from poor timeliness and a severe lack of data. In contrast, social media like Twitter and Facebook have become ubiquitous real-time social sensors where user states are indicated swiftly and extensively. However, little work has focused on adverse event detection using social media because of several challenges that have not been jointly solved: 1) message sparsity with irrelevant topics, 2) the difficulty of labeling health states, and 3) scalability in parameter optimization. To address these problems simultaneously, this paper presents a new semi-supervised multi-instance learning model to detect potential adverse events reflected by social media, which will facilitate the further clinical verification and prompt intervention. Specifically, given only user-level labels, this model interpretably identifies the user's adverse-event-indicative messages by employing a multi-instance learning strategy; unlabeled users' messages are also utilized to improve classifier performance by a semi-supervised term. Two models and corresponding algorithms, namely the non-smooth Semi-Supervised Multi-instance (nSSM) algorithm and the smooth Semi-Supervised Multi-instance (sSSM) algorithm, have been developed to optimize parameters accurately and efficiently. Experiments on a synthetic dataset and a real Twitter dataset confirm that our model outperforms other baseline models. Case studies show interesting interpretable patterns including key messages, keywords, and several common symptoms found in adverse-relevant tweets extracted by our methods.

Predicting individuals personality traits with their social media profile has proved to be feasible, but researchers recently have run into bottlenecks on further improving the prediction accuracy. One major limitation is that existing studies failed to consider context information in predicting social media users' behaviors. In this paper, we adopted the DIAMONDS situation theory in psychology to capture the context information in Facebook posts. To solve this issue, we proposed a novel situation-based feature interaction learning model. In this study, we extracted situation features according to the DIAMONDS lexicon and computed the interaction values between these situation features and the commonly used n-gram features at the post level. Features at the post level were aggregated up to the user level using the averaging strategy. A group lasso penalty was employed to enforce strong heredity in the model, which addressed the overfitting challenge introduced by the interaction features. Empirical tests on a large-scale data set have demonstrated the effectiveness of the proposed method.

It is important for decision-makers to effectively and proactively differentiate the significance of various public concerns, and address them with optimal strategy under the limited resources. Online Petition Platforms (OPPs) are replacing traditional social and market surveys for the advantages of low financial cost and high-fidelity social indicators. Despite benefits from OPPs, the raw information from millions of petition signers can easily overwhelm decision makers. In addition, spatio-temporal and semantic dissemination patterns increase the complexity of such OPP data. These two aspects show the necessity of a framework that learns from all available data, which is encoded by dynamic representation of features, to predict whether a petition will successfully lead to a change by decision makers. To build such framework, we need to overcome several challenges including: 1) missing values in dynamic features; 2) strong uncertainty in petition prediction; 3) unknown labels for ongoing petitions and 4) Scalability regarding increasing features and petitions. To address these difficulties simultaneously, we propose a novel chain-structure Multi-task Learning framework with Uncertainty Estimation (MLUE) to predict potentially victorious petitions, which facilitates the process of decision making. Specifically, we divide data into different Increasing Feature Blocks (IFBs) according to missing patterns. Besides, we propose a novel criterion to estimate uncertainty in order to label petitions as early as possible. To handle the challenge of scalability, we present an Expectation-Maximization (EM)-based algorithm to optimize the non-convex objective function accurately and efficiently. Various experiments on six petition datasets demonstrate that our MLUE outperformed other baselines by a large margin.

The presence of data corruption in user-generated streaming data, such as social media, motivates a new fundamental problem that learns reliable regression coefficient when features are not accessible entirely at one time. Until now, several important challenges still cannot be handled concurrently: 1) corrupted data estimation when only partial features are accessible; 2) online feature selection when data contains adversarial corruption; and 3) scaling to a massive dataset. This paper proposes a novel RObust regression algorithm via Online Feature Selection (RoOFS) that concurrently addresses all the above challenges. Specifically, the algorithm iteratively updates the regression coefficients and the uncorrupted set via a robust online feature substitution method. Extensive empirical experiments in both synthetic and real-world data sets demonstrated that the effectiveness of our new method is superior to that of existing methods in the recovery of both feature selection and regression coefficients, with very competitive efficiency.

As machine learning methods are utilized in more and more real-world applications involving constraints on computational budgets, the systematic integration of such constraints into the process of model selection and model optimization is required to an increasing extent. A specific computational resource in this regard is the time needed for evaluating predictions on test instances. There is meanwhile a substantial body of work concerned with the joint optimization of accuracy and test-time efficiency by considering the time costs of feature generation and model prediction. During the feature generation process, significant redundant computations across different features occur in many applications. Although the elimination of such redundancies would reduce the time cost substantially, there has been little research in this area due to substantial technical challenges involved, especially: 1) the lack of an effective formulation for feature computation dependency; and 2) the nonconvex and discrete nature of the optimization over feature computation dependency. In order to address these problems, this paper first proposes a heterogeneous hypergraph to represent the feature computation dependency, after which a framework is proposed that jointly optimizes the accuracy and the exact test-time cost based on a given feature computational dependency. A continuous tight approximation to this original problem is proposed based on a non-monotone nonconvex regularization term. Finally, an effective nonconvex optimization algorithm is proposed to solve the problem, along with a theoretical analysis of the convergence conditions. Extensive experiments on eight synthetic datasets and six real-world datasets demonstrate the proposed models' outstanding performance in terms of both accuracy and prediction-time cost.

Detection of vaccine adverse events is crucial to the discovery and improvement of problematic vaccines. To achieve it, traditionally formal reporting systems like VAERS support accurate but delayed surveillance, while recently social media have been mined for timely but noisy observations. Utilizing the complementary strengths of these two domains to boost the detection performance looks good but cannot be effectively achieved by existing methods due to significant differences between their data characteristics, including: 1) formal language v.s. informal language, 2) single-message per user v.s. multi-messages per user, and 3) one class v.s. binary class. In this paper, we propose a novel generic framework named Multi-instance Domain Adaptation (MIDA) to maximize the synergy between these two domains in the vaccine adverse event detection task for social media users. Specifically, we propose a generalized Maximum Mean Discrepancy (MMD) criterion to measure the semantic distances between the heterogeneous messages from these two domains in their shared latent semantic space. Then these message-level generalized MMD distances are synthesized by newly proposed mixed instance kernels to user-level distances. We finally minimize the distances between the samples of the partially-matched classes from these two domains. In order to solve the non-convex optimization problem, an efficient Alternating Direction Method of Multipliers (ADMM) based algorithm combined with the Convex-Concave Procedure (CCP) is developed to optimize parameters accurately. Extensive experiments demonstrated that our model outperformed the baselines by a large margin under six metrics. Case studies showed that formal reports and extracted adverse-relevant tweets by MIDA shared a similarity of keyword and description patterns.

Social media has become a popular data source to track and analyze societal events. Targeted domains such as election, civil unrest, and spreading disease all require a natural language normalization tool capable of extracting information pertinent to these domains accurately. Due to the unstructured language, short-length messages, casual posting styles, and homonyms, it is technically difficult and labor-intensive to remove barriers that may lead to inaccurate analysis. Because the fact that typos or other symbolic representations of sentiment may lead to lower frequency of term appearance, language preprocessing becomes critical and necessary to improve social media text reasoning. We propose a novel unsupervised preprocessing approach to enhance text understanding quality and illustrate this approach using one specific domain, flu shot reasoning. The proposed approach relies on a database of synonyms and opposite words and an algorithm to transform negative sentences into its affirmative form. In this form, the features and opinions are reflected accurately via transforming parts of speech. For instance, features are presented as nouns and opinions are presented as verbs or adjectives. The algorithm also corrects words if they are not correctly written and normalizes them to increase its frequency of appearance. The effectiveness of our algorithm is evaluated on the tweets dataset to answer why people are reluctant to take flu shots.

In the era of information overload, people are struggling to make sense of complex story events in massive social media data. Most existing approaches are designed to address event extraction in news reports, documents and abstracts, but such approaches are not suitable for Twitter data streams due to their unstructured language, short-length messages, and heterogeneous features; few existing approach generates a story by considering both the shared topics throughout the story and the smooth connection between successive nodes simultaneously. In this paper, a novel Twitter stoRy generation framework via shAred subspaCe and tEmporal Smoothness called TRACES is proposed. Given a query of an ongoing event, a novel multi-task clustering method integrated with shared subspace and temporal smoothness (STMTC) is proposed to generate the event stories. Extensive experimental evaluations of data sets for different events demonstrate the effectiveness of this new approach.

In today's era of information overload, people are struggling to detect the evolution of hot topics from massive news media and microblogs such as Twitter. Reports from mainstream news agencies and discussions from microblogs could complement each other to form a complete picture of major events. Existing work has generally focused on a single source, seldom attempting to combine multiple sources to track the evolution of topics: emerging, evolving and fading phrases as this would require a considerably more sophisticated model. This paper proposes a novel story discovery model that integrates evolutionary topics in news and Twitter data sources using an incremental algorithm by 1) discovering complementary information from news and microblogs that provides a more complete view of major events; 2) modeling emerging, evolving and fading topics and features throughout ongoing events; and 3) creating a scalable algorithm that is capable of handling massive data from news and social media. The parameters of the new model are optimized using a novel algorithm based on the alternative direction method of multipliers (ADMM). Extensive experimental evaluations on multiple datasets from different domains demonstrate the effectiveness and efficiency of our proposed approach.

Hyper-local pricing data, e.g., about foods and commodities, exhibit subtle spatiotemporal variations that can be useful as crucial precursors of future events. Three major challenges in modeling such pricing data include: i) temporal dependencies underlying features; ii) spatiotemporal missing values; and iii) constraints underlying economic phenomena. These challenges hinder traditional event forecasting models from being applied effectively. This paper proposes a novel spatiotemporal event forecasting model that concurrently addresses the above challenges. Specifically, given continuous price data, a new soft time-lagged model is designed to select temporally dependent features. To handle missing values, we propose a data tensor completion method based on price domain knowledge. The parameters of the new model are optimized using a novel algorithm based on the Alternative Direction Methods of Multipliers (ADMM). Extensive experimental evaluations on multiple datasets demonstrate the effectiveness of our proposed approach.

Most trajectory data are collected with a constant sample rate (e.g. GPS data). However, the variance of velocities can be very large, which causes the non-uniformity of the sample points in trajectory dataset. That is, the trajectory dataset can be very sparse in some parts which cause most existing distance measures to get unexpected results. On the other hand, the dataset can be extremely dense in some other parts which results in unnecessarily high computational complexity. Due to the above phenomenon, choosing an appropriate sample rate becomes a difficult challenge. In order to address the dilemma, we propose a Step-Invariant Trajectory (SIT) representation that can provide a dynamic sample rate to represent any trajectories in a uniform way. The translation takes only linear time. We also propose an effective and scalable distance measure for SIT representation. We evaluate the effectiveness and efficiency of our representation along with its distance measure by performing multiple trajectory classification and clustering experiments. These results show that our distance measures on SIT representation is much more accurate and robust than other representations and distance measures on sparse trajectory datasets. Our approach can also achieve competitive accuracy compared with the state of the art model-based trajectory representations on dense datasets. However, the time required to translate the data to our representation is 2 orders of magnitude faster, on average, than translate to other model-based representations. Furthermore, our representation can also serve as a preprocessing step to provide high quality input to all trajectory learning methods.

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.

In today's era of big data, robust least-squares regression becomes a more challenging problem when considering the adversarial corruption along with explosive growth of datasets. Traditional robust methods can handle the noise but suffer from several challenges when applied in huge dataset including 1) computational infeasibility of handling an entire dataset at once, 2) existence of heterogeneously distributed corruption, and 3) difficulty in corruption estimation when data cannot be entirely loaded. This paper proposes online and distributed robust regression approaches, both of which can concurrently address all the above challenges. Specifically, the distributed algorithm optimizes the regression coefficients of each data block via heuristic hard thresholding and combines all the estimates in a distributed robust consolidation. Furthermore, an online version of the distributed algorithm is proposed to incrementally update the existing estimates with new incoming data. We also prove that our algorithms benefit from strong robustness guarantees in terms of regression coefficient recovery with a constant upper bound on the error of state-of-the-art batch methods. Extensive experiments on synthetic and real datasets demonstrate that our approaches are superior to those of existing methods in effectiveness, with competitive efficiency.

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.

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.

EMBERS is an anticipatory intelligence system forecasting population-level events in multiple countries of Latin America. A deployed system from 2012, EMBERS has been generating alerts 24x7 by ingesting a broad range of data sources including news, blogs, tweets, machine coded events,currency rates, and food prices. In this paper, we describe our experiences operating EMBERS continuously for nearly 4 years, with specific attention to the discoveries it has enabled, correct as well as missed forecasts, lessons learnt from participating in a forecasting tournament, and our perspectives on the limits of forecasting including ethical considerations.

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.

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.

Developed under the IARPA Open Source Initiative program, EMBERS (Early Model Based Event Recognition using Surrogates) is a large-scale Big-Data analytics system for forecasting significant societal events, such as civil unrest incidents and disease outbreaks on the basis of continuous, automated analysis of large volumes of publicly available data. It has been operational since November of 2012, delivering approximately 50 predictions each day. EMBERS is built on a streaming, scalable, share-nothing architecture and is deployed on Amazon Web Services (AWS).

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.

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.