Trajectory recovery (TrajRec), which primarily seeks to reconstruct complete trajectories from segments sampled at low rates and align them with road networks, has gained attention in both urban computing and intelligent transportation areas. Existing solutions predominantly focus on using dependency learning to bridge the gap between the missing and the observed parts constrained by the road network–while rarely considering the positive signals of spatiotemporal corrections in a self-augmenting manner and ignoring transition pReferences alongside road network limitations. To this end, this study proposes a novel road-informed solution that combinesDual-offset trajectory learning with dynamicTransitionProbability (DTPTrajRec), primarily striving to enhance inherent spatiotemporal correlations with dual-offset trajectories while aligning the inferred GPS points with roads by collaborating them with dynamic transition preferences. More importantly, our proposed DTPTrajRec concentrates on enhancing the low-quality trajectory data by filling gaps (missing points) with the nearest available points and managing them within latent spaces, yielding more robust trajectory representations. To improve recovery reliability, it synchronizes transition preferences with road restrictions using adaptive transition probabilities. In the end, experimental results on two large-scale taxi datasets demonstrate the superiority of our DTPTrajRec over several baseline methods.

The metro flow in Urban Rail Transit Systems (URTS) differs from other urban traffic flows because it is characterized by: (1) highly predetermined scheduling; and (2) interactively dynamic dependencies over the fixed physical infrastructure that vary with spatiotemporal and environmental factors. Notwithstanding the advances in graph neural networks, existing efforts fail to fully capture the characteristics and complex spatiotemporal dynamics specific to metro flow, as the innate graph-aware interactions underlying a metro flow are frequently affected by an amalgamation of: intrinsic connectivity, environmental associations, and flow-activated correlation, which usually dynamically evolve over time while containing redundant signals. We propose ReDyNet, a novel Responsive Dynamic Graph Neural Network to accurately understand the spatiotemporal dynamics of metro flow and external factors. Specifically, it employs a responsive mechanism that adapts to variations in metro flow and external influences, ensuring the construction of an appropriate dynamic graph. In addition, ReDyNet follows the merits of information bottleneck (IB) theory with redundancy disentanglement to enhance the clarity and precision of contextual spatial signals. Our experiments conducted on three real-world metro passenger flow datasets demonstrate that the proposed ReDyNet outperforms several representative baselines.

High-quality embeddings for urban regions have enabled influential insights into urban structures and characteristics, facilitating the creation of more sustainable cities. However, the existing practices still face certain challenges, notably: (1) When multiple views contain distinct semantic information, ignoring the reliability and possibly inadequate collection differences (e.g., data missingness) among those views may degrade the representation robustness. (2) Consensus semantics extracted from different views are often fused in a simplistic manner, without considering the uniformity of embeddings (quality variations) and the complementarity between views. To address such challenges, we propose a novel Adaptive Risk-aware Consensus learning (ARC) solution for urban region embeddings. Specifically, we design both local- and region-level masking within the inter-view representation, following the paradigm of masked autoencoders, to better handle uncertainty risks. More importantly, we introduce a self-weighted contrastive mechanism in consensus learning to achieve maximum alignment and mitigate degradation. To enhance the uniformity of embeddings, we employ entropy, ensuring the diversity and complementarity of information. Ultimately, we apply the learned embeddings to down-stream tasks, demonstrating remarkable improvements compared to several representative baselines.

The use of drones has become increasingly popular in applications like surveilance, delivery, tracking and response to significant events. When there is a fleet of drones assigned to a given geographic area, typically the area of interest is divided into smaller regions and each drone is assigned to a specific region, to ensure a balance on the upper bound of the worst-case response time. Towards that, various spatial partitioning methods can be applied. However, not much has been done to ensure a balance on the worst-case response time when there are obstacles (i.e., "no-fly" zones) present. Such zones induce larger response time due to the necessity for circum-navigating around them when responding to an event of interest.

This work presents a systematic investigation into the trustworthiness of explanations generated by self-interpretable graph neural networks (GNNs), revealing why models trained with different random seeds yield inconsistent explanations. We identify redundancy—resulting from weak conciseness constraints—as the root cause of both explanation inconsistency and its associated inaccuracy, ultimately hindering user trust and limiting GNN deployment in high-stakes applications. Our analysis demonstrates that redundancy is difficult to eliminate; however, a simple ensemble strategy can mitigate its detrimental effects. We validate our findings through extensive experiments across diverse datasets, model architectures, and self-interpretable GNN frameworks, providing a benchmark to guide future research on addressing redundancy and advancing GNN deployment in critical domains. Our code is available at \url{https://github.com/ICDM-UESTC/TrustworthyExplanation}.

When a fleet of mobile units is used for surveillance and response to potential events, the geographic area of interest is often partitioned into smaller regions, and a particular (subset of) unit(s) is assigned to each region. One of the main reasons is to put a bound on the travel time for a unit in charge of responding to a new event/request from the unit's current location to the location of the occurrence of that event. In practice, the area may contain obstacles (e.g., buildings that have to be circumvented by ground mobile units or no-fly zones in case of drones). Although the problems of navigating among obstacles and spatial partitioning have been studied in the past, in this work we take a step towards tackling the setting of partitioning a geographic area of interest with obstacles in it, for the purpose of bounding the worst-case response time to an event by a member of a fleet of mobile units. To this end, we introduce a novel data structure and present an algorithmic solution for its construction, enabling a distribution of a fleet of mobile units to disjoint regions of the area of interest in a manner that will ensure a bound on the worst case response time in each region. Our experiments over real and synthetic datasets demonstrate the benefits of the proposed methodology over adaptation of existing spatial partitioning techniques.

One important “fact of life” when modeling motion, especially when it comes from real location-in-time data sources, is the uncertainty of the objects' whereabouts at a given time instant. Different models have been proposed in the literature and their impacts have been considered on algorithms for processing various spatio-temporal (continuous as well as snapshot) queries like range, k-nearest neighbor (kNN), contact, etc. However, having the available models and solutions does not bring them closer for use by domain scientist who may want to explore the impact of the uncertainty on realistic domains such as tracking of animals. In such scenarios, a domain scientist may be interested in getting an idea as to what is the possibility of an animal being within certain distance from a water supply (i.e., range query). Similarly, the domain scientists may be interested in the probability of two atoms being within a certain distance from each other (i.e., alibi query). To enable such analysis, we developed a prototype system that offers: (1) selection of a dataset consisting of ($x, y, t$) points corresponding to discrete locations of the objects' motion; (2) visualization of the uncertainty of that motion under the model of space-time prisms (also referred to as beads); (3) Visualization of the answers to range and alibi queries (and, where applicable, the map of the given area). In this demo paper we describe the basic architecture of our prototype system and discuss its functionalities.

Abstract The Doubly Connected Edge List (DCEL) is an edge-list structure widely used in spatial applications, primarily for planar topological and geometric computations. However, it is also applicable to various types of data, including 3D models and geographic data. An essential operation is the overlay operation, which combines the DCELs of two input polygon layers and can easily support spatial queries on polygons like the intersection, union, and difference between these layers. However, existing techniques for spatial overlay operations suffer from two main limitations. First, they fail to handle many large datasets practically used in real applications. Second, they cannot handle arbitrary spatial lines that practically form polygons, e.g., city blocks, but they are given as a set of scattered lines. This work proposes a distributed and scalable way to compute the overlay operation and its related supported queries. Our operations also support arbitrary spatial lines through a scalable polygonization process. We address the issues of efficiently distributing the lines and overlay operators and offer various optimizations that improve performance. Our experiments demonstrate that the proposed scalable solution can efficiently compute the overlay of large real datasets.

Trip recommendation aims to plan user’s travel based on their specified preferences. Traditional heuristic and statistical approaches often fail to capture the intricate nuances of user intentions, leading to subpar performance. Recent deep-learning methods show attractive accuracy but struggle to generate faithful trajectories that match user intentions. In this work, we propose a DDPM-based incremental knowledge injection module to ensure the faithfulness of the generated trajectories. Experiments on two datasets verify the effectiveness of our approach.

To avoid high costs and to provide safety during exploratory stages, most manufacturers of drugs run simulations of molecular interactions. Subsequently, the outputs are used for analyzing the movements of atoms (in the context of multiple molecules that they belong to), with a goal to detect whether certain events of interest occur. Such events typically mean that certain properties of the drug under development are satisfied (or not). In this demo paper, we describe a system for detecting the formation and persistence of Hydrogen Bonds (HBs) during the evolution of a given chemical compound, based on simulation data. The rationale is that such phenomena (occurrence and duration) indicate desirable properties throughout certain interactions. Our prototype system allows the users to analyze the simulation datasets in a manner that enables: (1) detection of persistent, long-lasting HBs; (2) generation of a detailed report; (3) providing a visual representation of the persistent HBs (if they occur within the data set).

Graph neural networks, as well as attention mechanisms, have gained widespread popularity for traffic flow forecasting due to their capacity to incorporate the complicated interactions behind flow dynamics. However, existing solutions either formulate a graph-based skeleton with narrow (e.g., static) interaction capture or build the spatiotemporal (e.g., dynamic) attention without proper comprehension of diverse risks, which inevitably burdens the generalization of high-accuracy traffic trends. In this study, we introduce Gboot (Graph bootstrap) enhancement framework for traffic flow forecasting. Gboot takes the traffic flow forecasting problem from a dependency dynamic learning perspective by treating each traffic sensor as the graph node while regarding the observed flows at each sensor as the node feature. In addition to exposing the explicit spatial connectivity behind traffic flows, we hierarchically devise temporal-aware and factual-aware graph learning blocks to consider temporal interactive dynamics and factual interactive dynamics. The former shows the trend dependencies behind flow signals and the latter uncovers different views of traffic situations (e.g., current observation vs. historical observation). More importantly, we present a Dual-view Bootstrap (DvBoot) mechanism in Gboot, which includes both risk-free and risk-aware stands. DvBoot attempts to flexibly align these two views in the latent space to enhance the generalization capability of capturing dynamic dependencies. Experiments on several real-world traffic datasets demonstrate the superiority of our Gboot over representative approaches.

We address the problem of combining proximity and semantic criteria for detecting co-moving clusters of interest in atomic trajectories. Specifically, we are interested in the motion of atoms from different molecules that at some point form a Hydrogen Bond (HB) and that HB persists over time with additional constraints within clusters. Moreover, it is permissible that an HB within a cluster is disrupted for a brief period. To enable the detection of such phenomena, we introduce the notion of Bond-Aware Relaxed Moving Clusters (BARMC) pattern and present a Naïve algorithm for its detection.

The advancements in Location Based Services (LBS) and Location Based Social Networks (LBSN) have spurred multiple research efforts in query processing as well as recommendation systems that enable planning trips based on combining location and semantic properties of Points of Interest (POI). However, often times such trips need to involve the reality of existing road networks, for the purpose of obeying constraints such as distance or travel-time. Although there are many publicly available datasets (e.g., Gowalla) that include check-in data at POIs with location, they are often not integrated with existing roads-based data (e.g., Open Street Maps (OSM)) causing researchers to spend extra time and labour to experimentally evaluate their findings. In this paper, we present: (1) methodologies for extracting information regarding POIs from publicly available datasets based on users posting; (2) extracting concise semantic categories for each POI; (3) integrating their location and semantic categories with an existing road network. In addition to the methodologies, we also provide two datasets (based on POIs and road networks in Chicago and New York City) constructed using our methodologies that researchers can readily use for their semantic-aware POIs with location and trip based query processing tasks as well as deep learning tasks.

Accurately predicting the popularity of multimodal user-generated content (UGC) is fundamental for many real-world applications such as online advertising and recommendation. Existing approaches generally focus on limited contextual information within individual UGCs, yet overlook the potential benefit of exploiting meaningful knowledge in relevant UGCs. In this work, we propose RAGTrans, an aspect-aware retrieval-augmented multi-modal hypergraph transformer that retrieves pertinent knowledge from a multi-modal memory bank and enhances UGC representations via neighborhood knowledge aggregation on multi-model hypergraphs. In particular, we initially retrieve relevant multimedia instances from a large corpus of UGCs via the aspect information and construct a knowledge-enhanced hypergraph based on retrieved relevant instances. This allows capturing meaningful contextual information across the data. We then design a novel bootstrapping hypergraph transformer on multimodal hypergraphs to strengthen UGC representations across modalities via customizing a propagation algorithm to effectively diffuse information across nodes and edges. Additionally, we propose a user-aware attention-based fusion module to comprise the enriched UGC representations for popularity prediction. Extensive experiments on real-world social media datasets demonstrate that RAGTrans outperforms state-of-the-art popularity prediction models across settings.

Graph-level anomaly detection is significant in diverse domains. To improve detection performance, counterfactual graphs have been exploited to benefit the generalization capacity by learning causal relations. Most existing studies directly introduce perturbations (e.g., flipping edges) to generate counterfactual graphs, which are prone to alter the semantics of generated examples and make them off the data manifold, resulting in sub-optimal performance. To address these issues, we propose a novel approach, Motif-consistent Counterfactuals with Adversarial Refinement (MotifCAR), for graph-level anomaly detection. The model combines the motif of one graph, the core subgraph containing the identification (category) information, and the contextual subgraph (non-motif) of another graph to produce a raw counterfactual graph. However, the produced raw graph might be distorted and cannot satisfy the important counterfactual properties: Realism, Validity, Proximity and Sparsity. Towards that, we present a Generative Adversarial Network (GAN)-based graph optimizer to refine the raw counterfactual graphs. It adopts the discriminator to guide the generator to generate graphs close to realistic data, i.e., meet the property Realism. Further, we design the motif consistency to force the motif of the generated graphs to be consistent with the realistic graphs, meeting the property Validity. Also, we devise the contextual loss and connection loss to control the contextual subgraph and the newly added links to meet the properties Proximity and Sparsity. As a result, the model can generate high-quality counterfactual graphs. Experiments demonstrate the superiority of MotifCAR.

A critical aspect of graph neural networks (GNNs) is to enhance the node representations by aggregating node neighborhood information. However, when detecting anomalies, the representations of abnormal nodes are prone to be averaged by normal neighbors, making the learned anomaly representations less distinguishable. To tackle this issue, we propose an unsupervised counterfactual data augmentation method for graph anomaly detection (CAGAD) that introduces a graph pointer neural network as the heterophilic node detector to identify potential anomalies whose neighborhoods are normal-node-dominant. For each identified potential anomaly, we design a graph-specific diffusion model to translate a part of its neighbors, which are probably normal, into anomalous ones. At last, we involve these translated neighbors in GNN neighborhood aggregation to produce counterfactual representations of anomalies. Through aggregating the translated anomalous neighbors, counterfactual representations become more distinguishable and further advocate detection performance. The experimental results on four datasets demonstrate that CAGAD significantly outperforms strong baselines, with an average improvement of 2.35% on F1, 2.53% on AUC-ROC, and 2.79% on AUC-PR.

Landslides refer to occurrences of massive ground movements due to geological (and meteorological) factors, and can have disastrous impacts on property, economy, and even lead to the loss of life. The advances in remote sensing provide accurate and continuous terrain monitoring, enabling the study and analysis of land deformation which, in turn, can be used for land deformation prediction. Prior studies either rely on predefined factors and patterns or model static land observations without considering the subtle interactions between different point locations and the dynamic changes of the surface conditions, causing the prediction model to be less generalized and unable to capture the temporal deformation characteristics. To address these issues, we present DyLand, a dynamic manifold learning framework that models the dynamic structures of the terrain surface. We contribute to the land deformation prediction literature in four directions. First, DyLand learns the spatial connections of interferometric synthetic aperture radar (InSAR) measurements and estimates the conditional distributions on a dynamic terrain manifold with a novel normalizing flow-based method. Second, instead of modeling the stable terrains, we incorporate surface permutations and capture the innate dynamics of the land surface while allowing for tractable likelihood estimations on the manifold. Third, we formulate the spatiotemporal learning of land deformations as a dynamic system and unify the learning of spatial embeddings and surface deformation. Finally, extensive experiments on curated real-world InSAR datasets (land slopes prone to landslides) show that DyLand outperforms existing benchmark models.

Understanding human mobility has become an important aspect of location-based services in tasks such as personalized recommendation and individual moving pattern recognition, enabled by the large volumes of data from geo-tagged social media (GTSM). Prior studies mainly focus on analyzing human historical footprints collected by GTSM and assuming the veracity of the data, which need not hold when some users are not willing to share their real footprints due to privacy concerns—thereby affecting reliability/authenticity. In this study, we address the problem of Inferring Real Mobility (IRMo) of users, from their unreliable historical traces. Tackling IRMo is a non-trivial task due to the: (1) sparsity of check-in data; (2) suspicious counterfeit check-in behaviors; and (3) unobserved dependencies in human trajectories. To address these issues, we develop a novel Graph-enhanced Attention model called IRMoGA , which attempts to capture underlying mobility patterns and check-in correlations by exploiting the unreliable spatio-temporal data. Specifically, we incorporate the attention mechanism (rather than solely relying on traditional recursive models) to understand the regularity of human mobility, while employing a graph neural network to understand the mutual interactions from human historical check-ins and leveraging prior knowledge to alleviate the inferring bias. Our experiments conducted on four real-world datasets demonstrate the superior performance of IRMoGA over several state-of-the-art baselines, e.g., up to 39.16% improvement regarding the Recall score on Foursquare.

Accurate urban flow prediction (UFP) is crucial for a range of smart city applications such as traffic management, urban planning, and risk assessment. To capture the intrinsic characteristics of urban flow, recent efforts have utilized spatial and temporal graph neural networks to deal with the complex dependence between the traffic in adjacent areas. However, existing graph neural network based approaches suffer from several critical drawbacks, including improper graph representation of urban traffic data, lack of semantic correlation modeling among graph nodes, and coarse-grained exploitation of external factors. To address these issues, we propose DiffUFP , a novel probabilistic graph-based framework for UFP. DiffUFP consists of two key designs: (1) a semantic region dynamic extraction method that effectively captures the underlying traffic network topology, and (2) a conditional denoising score-based adjacency matrix generator that takes spatial, temporal, and external factors into account when constructing the adjacency matrix rather than simply concatenation in existing studies. Extensive experiments conducted on real-world datasets demonstrate the superiority of DiffUFP over the state-of-the-art UFP models and the effect of the two specific modules.

Information cascade popularity prediction is an important problem in social network content diffusion analysis. Various facets have been investigated (e.g., diffusion structures and patterns, user influence) and, recently, deep learning models based on sequential architecture and graph neural network (GNN) have been leveraged. However, despite the improvements attained in predicting the future popularity, these methodologies fail to capture two essential aspects inherent to information diffusion: (1) the temporal irregularity of cascade event – i.e., users’ re-tweetings at random and non-periodic time instants; and (2) the inherent uncertainty of the information diffusion. To address these challenges, in this work, we present CasDO – a novel framework for information cascade popularity prediction with probabilistic diffusion models and neural ordinary differential equations (ODEs). We devise a temporal ODE network to generalize the discrete state transitions in RNNs to continuous-time dynamics. CasDO introduces a probabilistic diffusion model to consider the uncertainties in information diffusion by injecting noises in the forwarding process and reconstructing cascade embedding in the reversing process. Extensive experiments that we conducted on three large-scale datasets demonstrate the advantages of the CasDO model over baselines.

Deep neural networks have recently achieved considerable improvements in learning human behavioral patterns and individual preferences from massive spatial-temporal trajectory data. However, most of the existing research concentrates on fusing different semantics underlying sequential trajectories for mobility pattern learning which, in turn, yields a narrow perspective on comprehending human intrinsic motions. In addition, the inherent sparsity and under-explored heterogeneous collaborative items pertaining to human check-ins hinder the potential exploitation of human diverse periodic regularities as well as common interests. Motivated by recent advances in disentanglement learning, we propose a novel disentangled solution called SSDL for tackling the next POI prediction problem. SSDL primarily seeks to disentangle the potential time-invariant and time-varying factors into different latent spaces from massive trajectories, providing an interpretable view to understand the intricate semantics underlying human diverse mobility representations. To address the data sparsity issue, we present two realistic trajectory augmentation approaches to enhance the understanding of both the human intrinsic periodicity/habits and constantly-changing intents. In addition, we devise a POI-centric graph structure to explore heterogeneous collaborative signals underlying historical check-ins. Extensive experiments conducted on four real-world datasets demonstrate that SSDL significantly outperforms the state-of-the-art approaches–for example, it yields up to 8.57% averaged improvement on ACC@1.

Predicting information cascade popularity is a fundamental problem for understanding the nature of information propagation on social media. However, existing works fail to capture an essential aspect of information propagation: the temporal irregularity of cascade event -- i.e., users' re-tweetings at random and non-periodic time instants. In this work, we present a novel framework CasODE for information cascade prediction with neural ordinary differential equations (ODEs). CasODE generalizes the discrete state transitions in RNNs to continuous-time dynamics for modeling the irregular-sampled events in information cascades. Experimental evaluations on real-world datasets demonstrate the advantages of the CasODE over baseline approaches.

Recent literature has shown that denoising diffusion probabilistic models (DDPMs) can be used to synthesize high-fidelity samples with a competitive (or sometimes better) quality than previous state-of-the-art approaches. However, few attempts have been made to apply DDPM for the speech enhancement task. The reported performance of the existing works is relatively poor and significantly inferior to other generative methods. In this work, we first reveal the difficulties in applying existing diffusion models to the field of speech enhancement. Then we introduce DR-DiffuSE, a simple and effective framework for speech enhancement using conditional diffusion models. We present three strategies (two in diffusion training and one in reverse sampling) to tackle the condition collapse and guarantee the sufficient use of condition information. For efficiency, we introduce the fast sampling technique to reduce the sampling process into several steps and exploit a refinement network to calibrate the defective speech. Our proposed method achieves the state-of-the-art performance to the GAN-based model and shows a significant improvement over existing DDPM-based algorithms.

The recent advance in graph neural networks (GNNs) has inspired a few studies to leverage the dependencies of variables for time series prediction. Despite the promising results, existing GNN-based models cannot capture the global dynamic relations between variables owing to the inherent limitation of their graph learning module. Besides, multi-scale temporal information is usually ignored or simply concatenated in prior methods, resulting in inaccurate predictions. To overcome these limitations, we present CGMF, a Continuous Graph learning method for Multivariate time series Forecasting (CGMF). Our CGMF consists of a continuous graph module incorporating differential equations to capture the long-range intra- and inter-relations of the temporal embedding sequence. We also introduce a controlled differential equation-based fusion mechanism that efficiently exploits multi-scale representations to form continuous evolutional dynamics and learn rich relations and patterns shared across different scales. Comprehensive experiments demonstrate the effectiveness of our method for a variety of datasets.

Temporal heterogeneous networks (THNs) investigate the structural interactions and their evolution over time in graphs with multiple types of nodes or edges. Existing THNs describe evolving networks as a sequence of graph snapshots and adopt mechanisms from static heterogeneous networks to capture the spatial-temporal correlation. However, these works are confined to the discrete-time setting and the implementation of stacked mechanisms often introduces a high level of complexity, both conceptually and computationally. Here, we conduct comprehensive examinations and propose STHN, a simplifying THN for continuous-time link prediction. Concretely, to integrate continuous dynamics, we maintain a historical interaction memory for each node. A link encoder that incorporates two components - type encoding and relative time encoding - is introduced to encapsulate implicit heterogeneous characteristics of interaction and extract the most informative temporal information. We further propose to use a patching technique that assists with Transformer feature extractor to support the interaction sequence with long histories. Extensive experiments on three real-world datasets empirically demonstrate that STHN outperforms state-of-the-art methods with competitive task accuracy and predictive efficiency on both transductive and inductive settings.

While many countries are developing appropriate actions towards a greener future and moving towards adopting sustainable mobility activities, the real-time management and planning of innovative transportation facilities and services in urban environments still require the development of advanced mobile data management infrastructures. Novel green mobility solutions, such as electric, hybrid, solar and hydrogen vehicles, as well as public and gig-based transportation resources are very likely to reduce the carbon footprint. However, their successful implementation still needs efficient spatio-temporal data management resources and applications to provide a clear picture and demonstrate their effectiveness. This paper discusses the major data management challenges, open issues, and application opportunities closely related to urban green mobility. Additionally, it reports on recent successful experiences and challenging research questions. Furthermore, it highlights the global benefits one can expect when developing green mobility and emphasizes how mobile data infrastructures and services will play a crucial role in achieving these goals.

Inferring the citywide urban traffic flows is critical for numerous smart city applications such as urban planning, traffic control, and transportation management. Urban traffic flow inference problem aims to generate fine-grained flow maps from the coarse-grained ones. It is still challenging due to the lack of handling uncertainties of flow distributions and complex external factors that affect the inference performance. In this work, we propose a diffusion probabilistic augmentation-based network for considering the uncertainties of urban flows with a relaxed structural constraint and a disentangled scheme for flow map and external factor learning. Experiments are conducted on four large-scale urban flow datasets, and the results show that our method achieves significant performance improvements over strong baselines.

Typically, trajectories considered anomalous are the ones deviating from usual (e.g., traffic-dictated) driving patterns. However, this closed-set context fails to recognize the unknown anomalous trajectories, resulting in an insufficient self-motivated learning paradigm. In this study, we investigate the novel Anomalous Trajectory Recognition problem in an Open-world scenario (ATRO) and introduce a novel probabilistic Metric learning model, namely ATROM, to address it. Specifically, ATROM can detect the presence of unknown anomalous behavior in addition to identifying known behavior. It has a Mutual Interaction Distillation that uses contrastive metric learning to explore the interactive semantics regarding the diverse behavioral intents and a Probabilistic Trajectory Embedding that forces the trajectories with distinct behaviors to follow different Gaussian priors. More importantly, ATROM offers a probabilistic metric rule to discriminate between known and unknown behavioral patterns by taking advantage of the approximation of multiple priors. Experimental results on two large-scale trajectory datasets demonstrate the superiority of ATROM in addressing both known and unknown anomalous patterns.

The rising popularity of online social network services has attracted a lot of research focusing on mining various user patterns. Among them, accurate IP geolocation is essential for a plethora of location-aware applications. However, despite extensive research efforts and significant advances, the "accurate and reliable'' desideratum is yet to be achieved at a higher quality level. This work presents a graph neural network (GNN)-based model, called TrustGeo, for trustworthy street-level IP geolocation. A distinct and important aspect of TrustGeo is the incorporation of sources of uncertainty in the learning process. The results of our extensive experimental evaluations on three real-world datasets demonstrate the superiority of our framework in significantly improving the accuracy and trustworthiness of street-level IP geolocation. Our code and datasets are available at https://github.com/ICDM-UESTC/TrustGeo.

we present a system that enables testing the impacts of collaborative monitoring of geographical regions by a fleet of drones. Specifically, we consider the settings in which a simulation is executed, based on the properties of a particular approach, and we enable users to gather the basic statistics and compare the parameters of interest for different approaches under varying conditions, as well as observe a basic visualization of the flight paths. In particular, we can vary the number of drones in the fleet, their initial distribution, the occurrences of events of interests (e.g., a potential threat), and the transition of the drones (i.e., their trajectories) in response to a detection of an event. In addition to viewing and analyzing different values of interest, users can upload their collaboration algorithm, add/change the environmental factors, observe the discrepancies, and decide which algorithm is best for their application. Moreover, an authenticated user can save the algorithm and resulting metrics for subsequent retrieval. Our prototype is a web-based system using SpringBoot, a Java framework, relying on MySQL for data management and APIs to communicate with the front-end built on React, enabling various extensibilities (algorithms, environmental parameters, events, drones configuration).

Speech enhancement (SE) aims to improve the intelligibility and quality of speech in the presence of non-stationary additive noise. Deterministic deep learning models have traditionally been used for SE, but recent studies have shown that generative approaches, such as denoising diffusion probabilistic models (DDPMs), can also be effective. However, incorporating condition information into DDPMs for SE remains a challenge. We propose a model-agnostic method called DOSE that employs two efficient condition-augmentation techniques to address this challenge, based on two key insights: (1) We force the model to prioritize the condition factor when generating samples by training it with dropout operation; (2) We inject the condition information into the sampling process by providing an informative adaptive prior. Experiments demonstrate that our approach yields substantial improvements in high-quality and stable speech generation, consistency with the condition factor, and inference efficiency. Codes are publicly available at https://github.com/ICDM-UESTC/DOSE.

Route planning based on user’s preferences and Points of Interests (POIs) is one of the most popular applications of Location-Based Services (LBS). Variants of route planning consider distance constraints (e.g., the maximum length of the route), origin constraints (e.g., a set of possible starting locations of the route), and category constraints (e.g., a multiset of POI categories that the route must visit). However, the problem of deciding whether a route exists that visits all required POI categories under the distance constraint is known to be NP-hard. Assuming P ≠ NP, this means that there is no efficient (polynomial time) solution to find such paths. Recently, approximate algorithms have been proposed for searching for such a path. This demonstration leverages several of these algorithms to provide a web-based system with a graphical user interface (UI) which allows the users to find a path that: (a) satisfies a distance limit; (b) generates a route to visit a list of POIs, based on the user’s preferred categories; (c) provides a set of hotels (as possible starting locations of the path). If the approximate search algorithms are able to find such a path, it will be displayed on a Mapbox-based map interface that shows: (1) all POIs on a path and (2) alternative paths if any were found. The system then allows a user to explore the returned paths, select a path, or refine their constraints. Moreover, the system allows the users to select which approximate algorithm they would prefer to execute.

Fine-grained urban flow inference (FUFI) problem aims to infer the fine-grained flow maps from coarse-grained ones, benefiting various smart-city applications by reducing electricity, maintenance, and operation costs. Existing models use techniques from image super-resolution and achieve good performance in FUFI. However, they often rely on supervised learning with a large amount of training data, and often lack generalization capability and face overfitting. We present a new solution:Spatial-TemporalContrasting for Fine-Grained UrbanFlow Inference (STCF). It consists of (i) two pre-training networks for spatial-temporal contrasting between flow maps; and (ii) one coupled fine-tuning network for fusing learned features. By attractingspatial-temporally similarflow maps while distancing dissimilar ones within the representation space, STCF enhances efficiency and performance. Comprehensive experiments on two large-scale, real-world urban flow datasets reveal that STCF reduces inference error by up to 13.5%, requiring significantly fewer data and model parameters than prior arts.

Understanding in-network information diffusion is a fundamental problem in many applications and one of the primary challenges is to predict the information cascade size. Most of the existing models rely either on hypothesized point process (e.g., Poisson and Hawkes processes), or simply predict the information propagation via deep neural networks. However, they fail to simultaneously capture the underlying global and local structures of a cascade and the propagation uncertainty in the diffusion, which may result in unsatisfactory prediction performance. To address these, in this work we propose a novel probabilistic cascade prediction frameworkCasFlow: Hierarchical Cascade Normalizing Flows. CasFlow allows a non-linear information diffusion inference and models the information diffusion process by learning the latent representation of both the structural and temporal information. It is a pattern-agnostic model leveraging normalizing flows to learn the node-level and cascade-level latent factors in an unsupervised manner. In addition, CasFlow is capable of capturing both the cascade representation uncertainty and node infection uncertainty, while enabling hierarchical pattern learning of information diffusion. Extensive experiments conducted on real-world datasets demonstrate that CasFlow reduces the prediction error to 21.0% by only observing half an hour of cascades, compared to state-of-the-art approaches, while also enabling model interpretability.

Shortest path computation is a fundamental operation in many application domains and is especially challenging in frequently evolving small-world networks (i.e., graphs in which many nodes can be reached from every other node by a small number of hops). Index-based methods, especially ones based on 2-hop labeling are often used for high query efficiency. However, the evolvements of small-world networks in many realistic scenarios pose the challenge of efficient maintenance of the shortest path index. In this work, we adopt the state-of-the-artParallel Shortest-distance Labeling (PSL)as the underlying 2-hop labeling construction method, and design algorithms to support its efficient update given edge weight changes (increase and decrease). Specifically, we focus on weightedPSL (WPSL)and propose a propagation-based update mechanism for both synchronous and asynchronous propagation. We also identify thecurse of pruning powerin the edge weight increase case, and solve it with a balance between index size and effectiveness. Followed by, we extend the asynchronous propagation method toPruned Landmark Labeling (PLL)for faster index maintenance and query processing with a smaller index size. Finally, we further optimize the index performance by reducing the index size through graph contraction and accelerating the index update through parallelized mix index update. Our experimental results on real-life and synthetic networks demonstrate the superiority of our algorithms over the relevant baselines on index maintenance.

The problem of trip recommendation has been extensively studied in recent years, by both researchers and practitioners. However, one of its key aspects-understanding human mobility-remains under-explored. Many of the proposed methods for trip modeling rely on empirical analysis of attributes associated with historical points-of-interest (POIs) and routes generated by tourists while attempting to also intertwine personal preferences-such as contextual topics, geospatial, and temporal aspects. However, the implicit transitional preferences and semantic sequential relationships among various POIs, along with the constraints implied by the starting point and destination of a particular trip, have not been fully exploited. Inspired by the recent advances in generative neural networks, in this work we propose DeepTrip-an end-to-end method for better understanding of the underlying human mobility and improved modeling of the POIs' transitional distribution in human moving patterns. DeepTrip consists of: a trip encoder (TE) to embed the contextual route into a latent variable with a recurrent neural network (RNN); and a trip decoder to reconstruct this route conditioned on an optimized latent space. Simultaneously, we define an Adversarial Net composed of a generator and critic, which generates a representation for a given query and uses a critic to distinguish the trip representation generated from TE and query representation obtained from Adversarial Net. DeepTrip enables regularizing the latent space and generalizing users' complex check-in preferences. We demonstrate, both theoretically and empirically, the effectiveness and efficiency of the proposed model, and the experimental evaluations show that DeepTrip outperforms the state-of-the-art baselines on various evaluation metrics.

Identifying the geolocation of social media users is an important problem in a wide range of applications, spanning from disease outbreaks, emergency detection, local event recommendation, to fake news localization, online marketing planning, and even crime control and prevention. Researchers have attempted to propose various models by combining different sources of information, including text, social relation, and contextual data, which indeed has achieved promising results. However, existing approaches still suffer from certain constraints, such as: 1) a very few samples are available and 2) prediction models are not easy to be generalized for users from new regions-which are challenges that motivate our study. In this article, we propose a general framework for identifying user geolocation-MetaGeo, which is a meta-learning-based approach, learning the prior distribution of the geolocation task in order to quickly adapt the prediction toward users from new locations. Different from typical meta-learning settings that only learn a new concept from few-shot samples, MetaGeo improves the geolocation prediction with conventional settings by ensembling numerous mini-tasks. In addition, MetaGeo incorporates probabilistic inference to alleviate two issues inherent in training with few samples: location uncertainty and task ambiguity. To demonstrate the effectiveness of MetaGeo, we conduct extensive experimental evaluations on three real-world datasets and compare the performance with several state-of-the-art benchmark models. The results demonstrate the superiority of MetaGeo in both the settings where the predicted locations/regions are known or have not been seen during training.

Discovering interesting yet unvisited point-of-interests (POIs) is among the most practical applications but challenging problems in location-based social networks (LBSNs). Popular approaches face several issues, such as data sparsity and difficulties in modeling latent nonlinearity between users and POIs. Furthermore, the uncertainty in LBSNs poses additional obstacles to learning good representations of users’ general and current interests. To effectively address these issues, we postulate that fusing multiple sources of information is paramount. Toward that, we propose a novel deep generative recommender system—Wasserstein autoencoder for POI recommendation (WaPOIR). It unifies the information from users’ personal preference, social influence, and geographical data, and captures users’ general interests from historical check-ins, while modeling users’ current interests from recently visited POIs. Unlike previous methods, WaPOIR learns the latent distribution of data in the Wasserstein space as a potential representation for each POI and each user in LBSNs. This enables simultaneous maintenance of social and POI interactions and modeling the uncertainty of their relationships. WaPOIR is a stochastic recommendation approach that allows Bayesian inference and approximation of variational posterior distribution. Extensive experiments conducted on real-world LBSN datasets demonstrate that WaPOIR achieves better performance over the state-of-the-art approaches.

Landslides refer to occurrences of massive ground movements due to geological (and meteorological) factors, and can have disastrous impact on property, economy, and even lead to loss of life. The advances of remote sensing provide accurate and continuous terrain monitoring, enabling the study and analysis of land deformation which, in turn, can be used for possible landslides forecast. Prior studies either rely on independent observations for displacement prediction or model static land characteristics without considering the subtle interactions between different locations and the dynamic changes of the surface conditions. We present DyLand -- Dynamic Manifold Learning with Normalizing Flows for Land deformation prediction -- a novel framework for learning dynamic structures of terrain surface and improving the performance of land deformation prediction. DyLand models the spatial connections of InSAR measurements and estimates conditional distributions of deformations on the terrain manifold with a novel normalizing flow-based method. Instead of modeling the stable terrains, it incorporates surface permutations and captures the innate dynamics of the land surface while allowing for tractable likelihood estimates on the manifold. Our extensive evaluations on curated InSAR datasets from continuous monitoring of slopes prone to landslides show that DyLand outperforms existing bechmarking models.

The development of InSAR (satellite Interferometric Synthetic Aperture Radar) enables accurate monitoring of land surface deformations, and has led to advances of deformation forecast for preventing landslide, which is one of the severe geological disasters. Despite the unparalleled success, existing spatio-temporal models typically make predictions on static adjacency relationships, simplifying the conditional dependencies and neglecting the distributions of variables. To overcome those limitations, we propose a Distribution Aware Probabilistic Framework (DAPF), which learns manifold embeddings while maintaining the distribution of deformations. We obtain a dynamic adjacency matrix upon which we approximate the true posterior while emphasizing the spatio-temporal characteristics. Experimental results on real-world dataset validate the superior performance of our method.

Electricity forecasting has important implications for the key decisions in modern electricity systems, ranging from power generation, transmission, distribution and so on. In the literature, traditional statistic approaches, machine-learning methods and deep learning (e.g., recurrent neural network) based models are utilized to model the trends and patterns in electricity time-series data. However, they are restricted either by their deterministic forms or by independence in probabilistic assumptions -- thereby neglecting the uncertainty or significant correlations between distributions of electricity data. Ignoring these, in turn, may yield error accumulation, especially when relying on historical data and aiming at multi-step prediction. To overcome these, we propose a novel method named Probabilistic Electricity Forecasting (PrEF) by proposing a non-linear neural state space model (SSM) and incorporating copula-augmented mechanism into that, which can learn uncertainty-dependencies knowledge and understand interactive relationships between various factors from large-scale electricity time-series data. Our method distinguishes itself from existing models by its traceable inference procedure and its capability of providing high-quality probabilistic distribution predictions. Extensive experiments on two real-world electricity datasets demonstrate that our method consistently outperforms the alternatives.

Information cascade is typically formalized as a process of (simplified) discrete sequence of events, and recent approaches have tackled its prediction via variants of recurrent neural networks. However, the information diffusion process is essentially an evolving directed acyclic graph (DAG) in the continuous-time domain. In this paper, we propose a transformer enhanced Hawkes process (Hawkesformer), which links the hierarchical attention mechanism with Hawkes process to model the arrival stream of discrete events continuously. A two-level attention architecture is used to parameterize the intensity function of Hawkesformer, which captures the long-term dependencies between nodes in graph and better embeds the cascade evolution rate for modeling short-term outbreaks. Experimental results demonstrate the significant improvements of Hawkesformer over the state-of-the-art.

Drone simulators are often used to reduce training costs and prepare operators for various ad-hoc scenarios, as well as to test the quality of algorithmic and communication aspects in collaborative scenarios. An important aspect of drone missions in simulated (as well as real life) environments is the operational lifetime of a given drone, in both solo and collaborative fleet settings. Its importance stems from the fact that the capacity of the on-board batteries in untethered (i.e., free-flying) drones determines the range and/or the length of the trajectory that a drone can travel in the course of its surveilance or delivery missions. Most of the existing simulators incorporate some kind of a consumption model based on different parameters of the drone and its flight trajectory. However, to our knowledge, the existing simulators are not capable of incorporating data obtained from actual physical measurements/observations into the consumption model. In this work, we take a first step towards enabling the (users of) drones simulator to incorporate the speed and direction of the wind into the model and monitor its impact on the battery consumption as the direction of the flight changes relative to the wind. We have also developed a proof-of-concept implementation with DJI Mavic 3 and Parrot ANAFI drones.

Modeling complex spatial and temporal dependencies are indispensable for location-bound time series learning. Existing methods, typically relying on graph neural networks (GNNs) and temporal learning modules based on recurrent neural networks, have achieved significant performance improvements. However, their representation capabilities and prediction results are limited when pre-defined graphs are unavailable. Unlike spatio-temporal GNNs focusing on designing complex architectures, we propose a novel adaptive graph construction strategy: Self-Paced Graph Contrastive Learning (SPGCL). It learns informative relations by maximizing the distinguishing margin between positive and negative neighbors and generates an optimal graph with a self-paced strategy. Specifically, the existing neighborhoods iteratively absorb more reliable nodes with the highest affinity scores as new neighbors to generate the next-round neighborhoods, and augmentations are applied to improve the transferability and robustness. As the adaptively self-paced graph approaches the optimized graph for prediction, the mutual information between nodes and the corresponding neighbors is maximized. Our work provides a new perspective of addressing spatio-temporal learning problems beyond information aggregation in Euclidean space and can be generalized to different tasks. Extensive experiments conducted on two typical spatio-temporal learning tasks (traffic forecasting and land displacement prediction) demonstrate the superior performance of SPGCL against the state-of-the-art.

Pinpointing the geographic location of an IP address is important for a range of location-aware applications spanning from targeted advertising to fraud prevention. The majority of traditional measurement-based and recent learning-based methods either focus on the efficient employment of topology or utilize data mining to find clues of the target IP in publicly available sources. Motivated by the limitations in existing works, we propose a novel framework named GraphGeo, which provides a complete processing methodology for street-level IP geolocation with the application of graph neural networks. It incorporates IP hosts knowledge and kinds of neighborhood relationships into the graph to infer spatial topology for high-quality geolocation prediction. We explicitly consider and alleviate the negative impact of uncertainty caused by network jitter and congestion, which are pervasive in complicated network environments. Extensive evaluations across three large-scale real-world datasets demonstrate that GraphGeo significantly reduces the geolocation errors compared to the state-of-the-art methods. Moreover, the proposed framework has been deployed on the web platform as an online service for 6 months.

In addition to the multiple sensors to measure parameters that can be used to improve both safety and efficiency, modern vehicles also gather information about external data (e.g., traffic conditions, weather) which, if properly used, could further improve the overall trip experience. Specifically, when it comes to navigation, one source that can provide increased context awareness, especially for autonomous driving, are the High Definition (HD) maps, which have recently witnessed a tremendous growth of popularity in vehicular technology and use. As they are limited to a particular geographic area, different portions need to be downloaded (and processed) on multiple occasions throughout a given trip, along with the other data from other internal and external sources. In this paper, we provide an effective deep learning approach for the recently introduced problem of Predicting Map Data Consumption (PMDC) in the future time instants for a given trip. We propose a novel methodology that integrates multiple data sources (road network, traffic, historic trips, HD maps) and, for a given trip, enables prediction of the map data consumption. Our experimental observations demonstrate the benefits of the proposed approach over the candidate baselines.

Forecasting complex time series is ubiquitous and vital in a range of applications but challenging. Recent advances endeavor to achieve progress by incorporating various deep learning techniques (e.g., RNN and Transformer) into sequential models. However, clear patterns are still hard to extract since time series are often composed of several intricately entangled components. Motivated by the success of disentangled variational autoencoder in computer vision and classical time series decomposition, we plan to infer a couple of representations that depict seasonal and trend components of time series. To achieve this goal, we propose LaST, which, based on variational inference, aims to disentangle the seasonal-trend representations in the latent space. Furthermore, LaST supervises and disassociates representations from the perspectives of themselves and input reconstruction, and introduces a series of auxiliary objectives. Extensive experiments prove that LaST achieves state-of-the-art performance on time series forecasting task against the most advanced representation learning and end-to-end forecasting models. For reproducibility, our implementation is publicly available on Github.

We present HydroFlow, a novel deep generative model for predicting the electricity generation demand of large-scale hydropower stations. HydroFlow uses a latent stochastic recurrent neural network to capture the dependencies in the multivariate time series. It not only utilizes the hidden state of the neural network, but also considers the uncertainty of variables related to natural and social factors. We also introduce an end-to-end approach based on generative flows to approximate the posterior distribution of time series with exact likelihoods. Our model is powerful as adding stochasticity to different factors (e.g., reservoir capacity and water-flow measurements) and thus overcomes the expressiveness limitations of deterministic prediction methods. It also enables trainable latent transformations that can improve the model interpretability. We evaluate HydroFlow on the data collected from the hydropower stations of a large-scale hydropower development company. Experimental results show that our model significantly outperforms the state-of-the-art baseline methods while providing explainable results.

Despite offering efficient solutions to a plethora of novel challenges, existing approaches on mobility modeling require a large amount of labeled data when training effective and application-specific models. This renders them inapplicable to certain scenarios, where only a few samples are observed, and data types are unseen during training. To address these issues, we present a novel mobility learning method-MetaMove, the first metalearning-based model generalizing mobility prediction and classification in a unified framework. MetaMove deals with the problem of training for unseen mobility patterns by generalizing from the known patterns. It trains the model over a variety of patterns sampled from different users and optimizes it on their distribution. To update and fine tune the individual pattern learners, we employ a fast adapting model-agnostic method for very few available trajectory samples. MetaMove exploits unlabeled trajectory data at both metatraining and adaptation levels, thereby alleviating the problem of data sparsity while enforcing less sensitivity to negative samples. We conducted extensive experiments to demonstrate its effectiveness and efficiency on two practical applications-motion trace discrimination and next check-in prediction. The results demonstrated significant improvements of MetaMove over the state-of-the-art benchmarks.

The main objective of Personalized Tour Recommendation (PTR) is to generate a sequence of point-of-interest (POIs) for a particular tourist, according to the user-specific constraints such as duration time, start and end points, the number of attractions planned to visit, and so on. Previous PTR solutions are based on either heuristics for solving the orienteering problem to maximize a global reward with a specified budget or approaches attempting to learn user visiting preferences and transition patterns with the stochastic process or recurrent neural networks. However, existing learning methodologies rely on historical trips to train the model and use the next visited POI as the supervised signal, which may not fully capture the coherence of preferences and thus recommend similar trips to different users, primarily due to the data sparsity problem and long-tailed distribution of POI popularity. This work presents a novel tour recommendation model by distilling knowledge and supervision signals from the trips in a self-supervised manner. We propose Contrastive Trajectory Learning for Tour Recommendation (CTLTR), which utilizes the intrinsic POI dependencies and traveling intent to discover extra knowledge and augments the sparse data via pre-training auxiliary self-supervised objectives. CTLTR provides a principled way to characterize the inherent data correlations while tackling the implicit feedback and weak supervision problems by learning robust representations applicable for tour planning. We introduce a hierarchical recurrent encoder-decoder to identify tourists’ intentions and use the contrastive loss to discover subsequence semantics and their sequential patterns through maximizing the mutual information. Additionally, we observe that a data augmentation step as the preliminary of contrastive learning can solve the overfitting issue resulting from data sparsity. We conduct extensive experiments on a range of real-world datasets and demonstrate that our model can significantly improve the recommendation performance over the state-of-the-art baselines in terms of both recommendation accuracy and visiting orders.

We introduce a slope-aware graph neural network (SA-GNN) to leverage continuously monitored data and predict the land displacement. Unlike general GNNs tackling tasks in the plain graphs, our method is capable of generalizing 3D spatial knowledge from InSAR point clouds. Specifically, we structure of the land surface, while preserving the spatial correlations among adjacent points. The point cloud can then be efficiently converted to a near-neighbor graph where general GNN methods can be applied to predict the displacement of the slope surface. We conducted experiments on real-world datasets and the results demonstrate that SA-GNN outperforms existing 3D CNN and point GNN methods.

Traditionally, clustering of multivariate data aims at grouping objects described with multiple heterogeneous attributes based on a suitable similarity (conversely, distance) function. One of the main challenges is due to the fact that it is not straightforward to directly apply mathematical operations (e.g., sum, average) to the feature values, as they stem from heterogeneous contexts.

One of the most popular applications of Location Based Services (LBS) is recommending a Point of Interest (POI) based on user's preferences and geo-locations. However, the existing approaches have not tackled the problem of jointly determining: (a) a sequence of POIs that can be traversed within certain budget (i.e., limit on distance) and simultaneously provide a high-enough diversity; and (b) recommend the best origin (i.e., the hotel) for a given user, so that the desired route of POIs can be traversed within the specified constraints. In this work, we take a first step towards identifying this new problem and formalizing it as a novel type of a query. Subsequently, we present naïve solutions and experimental observations over a real-life datasets, illustrating the trade-offs in terms of (dis)associating the initial location from the rest of the POIs.

We consider surveillance of a geographic region by a collaborative system of drones. The drones assist each other in identifying and managing activities of interest on the ground. We also consider an adversary who can create both genuine and fake activities on the ground. The objective of the adversary is to use fake activities, in order to maximize the response time to genuine activities. We present two collaboration algorithms and analyze their response times, as well as the adversary's efforts in terms of the number of fake activities required to achieve a certain response time.

One of the main objectives of information cascade popularity prediction is to forecast the future size of a cascade given the observed propagation information. It is an enabling step for many practical applications (e.g., advertisement, academic writing, etc.). Recent advances in neural networks have spurred a few deep learning-based cascade models, which preserve the structural features of information cascades with node embedding and graph neural networks. However, efforts in cascade graph learning as well as its internal temporal dependency, existing methods mainly focus on node-level similarity learning, ignoring the structural equivalence among different sub-graphs that are more informative for information diffusion prediction. Towards this, we present a kernel-based structural-temporal cascade learning model, called CasKernel, to explicitly estimate and encode the structural similarity of cascades with the graph kernels. Moreover, we employ a non sequential process to address the temporal dependency, which can be used to facilitate information popularity prediction. Experiments conducted on both tweets propagation network and academic citation network demonstrate the effectiveness of our method.

Cross-network alignment aims at identifying users who participate in different social networks, which benefits a variety of downstream social applications such as precise content delivery, fraud detection, and content/user recommender systems. Recent advances in network representations and graph neural networks have spurred various network structure-based methods for capturing underlying node similarities across social networks, thereby addressing the network alignment problem. However, most of the existing solutions rely on embedding methods that compute node similarity in Euclidean space, resulting in severe distortion or semantic loss when representing real-world social networks, which are usually scale free and with hierarchical structures. We address these issues by presenting a novel model: Hyperbolic Graph Embedding for Network Alignment (HGENA), which learns the structural semantics more efficiently by embedding nodes in hyperbolic space instead of Euclidean. HGENA overcomes the scalability issue since it requires far fewer dimensions in Riemannian manifolds and increases the capability of learning hierarchical structures, while enabling smaller distortion for tree-liked networks to facilitate node alignment. We also introduce alternative network mapping functions to compute node similarity across-network based on its distance on the Poincare ball. Experimental evaluations conducted on real world datasets demonstrate that HGENA achieves superior performance on social network alignment, especially for more tree-liked networks.

We present a prototype system for planning shopping-related trips in the settings in which an individual may need to purchase a collection of items for which the requests originate from different categories of groups. Specifically, we consider scenarios in which the user is affiliated with a family and other (multiple) social circles - with varying temporal duration (e.g., from a specific party/event, to longer lasting preference-based memberships such as chess playing, reading club, etc.). Each of the groups may have its separate list of items to be purchased at a given time - e.g., grocery for the family; wine and cheese for a social event - however: (1) a particular individual may be a member of multiple (different) groups; (2) a particular group may have different shopping list (for different purposes); and (3) a user may be at different location at times when different requests originate. Our UGASP (User and Group Aware Shopping Planner) system aims at: (1) Generating trajectories for individuals to complete part of the purchase list, based on their group memberships; (2) Calculating new trajectories, based on updates of the purchase assignments to different users.

Combining in-car multiple sensors measuring parameters that can be used to improve both safety and efficiency with a plethora of external data sources (e.g., traffic conditions, weather) which, if properly used, can significantly improve the overall trip experience. One source that can help the navigation and provide "context awareness", especially for autonomous driving, are the High Definition (HD) maps, which have recently witnessed a tremendous growth of popularity in vehicular technology and use. As they are limited to a particular geographic area with respect to a given point along a trip, different portions need to be downloaded (and processed) on multiple occasions throughout a given trip, along with the other data from internal and external sources. We take a first step towards formalizing the problem of Predicting Map Data Consumption (PMDC) in the future time instants for a given trip, based on a (time) window from its history, and investigate the use of Long Short-Term Memory (LSTM) networks - a special type of Recurrent Neural Networks (RNN). Significant efforts were focused on generating an appropriate dataset for this study, towards which we fused the information available in multiple heterogeneous data sources. We conducted experimental observations demonstrating the benefits of the proposed approach.

Effectively predicting the size of information cascades is crucial for understanding the evolution of many social applications, such as influence maximization and fake news detection. Conventional methods face the challenge of data imbalance which, in turn, yields unsatisfactory prediction performance. To prevent the loss functions or metrics from being affected by extreme values and assure numerical stability, previous works reformulate the problem definitions or adopt other types of evaluation metrics. However, solving the regression prediction of information cascades from a long-tailed distribution perspective is under explored. In this paper, we propose a general decoupling prediction solution -- first extracting the representation, then fine-tuning the regressor, which combines the original prediction value and weighted bias generated by a sub-network (SUB) that we designed. Our experiments conducted on long-tailed benchmarks demonstrate that our method significantly improves the prediction accuracy over state-of-the-art methods and mitigates the long-tailed cascade prediction problem.

We present CACSE – a system for Context Aware Clustering of Stellar Evolution – for datasets corresponding to temporal evolution of stars, which are multivariate time series, usually with a large number of attributes (e.g., ≥ 40). Typically, the datasets are obtained by simulation and are relatively large in size (5 ∼ 10 GB per certain interval of values for various initial conditions). Investigating common evolutionary trends in these datasets often depends on the context – i.e., not all the attributes are always of interest, and among the subset of the context-relevant attributes, some may have more impact than others. To enable such context-aware clustering, our CACSE system provides functionalities allowing the domain experts to dynamically select attributes that matter, and assign desired weights/priorities. Our system consists of a PostgreSQL database, Python-based middleware with RESTful and Django framework, and a web-based user interface as frontend. The user interface provides multiple interactive options, including selection of datasets and preferred attributes along with the corresponding weights. Subsequently, the users can select a time instant or a time range to visualize the formed clusters. Thus, CACSE enables a detection of changes in the the set of clusters (i.e., convoys) of stellar evolution tracks. Current version provides two of the most popular clustering algorithms – k-means and DBSCAN.

Network alignment (NA) aims to link common nodes across multiple networks and is an essential task in many graph mining applications. Despite the progress achieved by many recent works, several fundamental limitations have eluded the proper cohesive way of addressing, including matching confusion, lack of the formal treatment of uncertainty, and Point-to-Point (P2P) constraint. This study proposes a novel framework UANA (Uncertainty-Aware Network Alignment) to tackle the limitations of the existing works. By embedding nodes as Gaussian distributions rather than point vectors, UANA enables to capture the uncertainty of a node representation, while being able to discriminate the anchor nodes from the potentially confusing neighbors. We address the P2P matching constraint by introducing an adversarial learning paradigm, which relaxes the exact matching assumption during training with an across-domain generative procedure to reduce the matching errors on testing nodes. In the end, interpretability methods are included to explain the aligning results made by our UANA based on the robust statistics, which enables the explanation of the effect of individual training sample on the NA performance without the need of retraining the model. Extensive experiments conducted on real-world data sets demonstrate that UANA significantly outperforms existing state-of-the-art baselines while providing explainable results.

Mining knowledge from human mobility, such as discriminating motion traces left by different anonymous users, also known as the trajectory-user linking (TUL) problem, is an important task in many applications requiring location-based services (LBSs). However, it inevitably raises an issue that may be aggravated by TUL, i.e., how to defend against location attacks (e.g., deanonymization and location recovery). In this work, we present a Semisupervised Trajectory- User Linking model with Interpretable representation and Gaussian mixture prior (STULIG)-a novel deep probabilistic framework for jointly learning disentangled representation of user trajectories in a semisupervised manner and tackling the location recovery problem. STULIG characterizes multiple latent aspects of human trajectories and their labels into separate latent variables, which can be then used to interpret user check-in styles and improve the performance of trace classification. It can also generate synthetic yet plausible trajectories, thus protecting users' actual locations while preserving the meaningful mobility information for various machine learning tasks. We analyze and evaluate STULIG's ability to learn disentangled representations, discriminating human traces and generating realistic motions on several real-world mobility data sets. As demonstrated by extensive experimental evaluations, in addition to outperforming the state-of-the-art methods, our method provides intuitive explanations of the classification and generation and sheds lights on the interpretable mobility mining.

Identifying user geolocation in online social networks is an essential task in many locationbased applications.Existing methods rely on the similarity of text and network structure, however, they suffer from a lack of interpretability on the corresponding results, which is crucial for understanding model behavior.In this work, we adopt influence functions to interpret the behavior of GNN-based models by identifying the importance of training users when predicting the locations of the testing users.This methodology helps with providing meaningful explanations on prediction results.Furthermore, it also initiates an attempt to uncover the so-called "black-box" GNN-based models by investigating the effect of individual nodes.

In this paper, we present the CET-LATS (Compressing Evolution of TINs from Location Aware Time Series) system, which enables testing the impacts of various compression approaches on evolving Triangulated Irregular Networks (TINs). Specifically, we consider the settings in which values measured in distinct locations and at different time instants, are represented as time series of the corresponding measurements, generating a sequence of TINs. Different compression techniques applied to location-specific time series may have different impacts on the representation of the global evolution of TINs - depending on the distance functions used to evaluate the distortion. CET-LATS users can view and analyze compression vs. (im)precision trade-offs over multiple compression methods and distance functions, and decide which method works best for their application. We also provide an option to investigate the impact of the choice of a compression method on the quality of prediction. Our prototype is a web-based system using Flask, a lightweight Python framework, relying on Apache Spark for data management and JSON files to communicate with the front-end, enabling extensibility in terms of adding new data sources as well as compression techniques, distance functions and prediction methods.

Geospatial data integration combines two or more data layers to facilitate advanced querying, analysis, reasoning, and visualization. In general, different layers (e.g., ZIP codes, census blocks, school districts, and land use parcels) have different spatial partitions and different types of associated semantic descriptors. In addition, geospatial data may contain errors (e.g., due to imprecision in the measurements or to representation constraints) causing uncertainty that needs to be incorporated and quantified in the query answers. In this paper, we leverage semantic descriptors in heterogeneous information layers to build a data structure that enables efficient processing of geospatial range queries by returning an estimate of the answer together with an error bound. We present the processing algorithms and evaluate our approach by means of experiments that encompass large datasets, demonstrating the benefits of our approach.

Modeling the information diffusion process is an essential step towards understanding the mechanisms driving the success of information. Existing methods either exploit various features associated with cascades to study the underlying factors governing information propagation, or leverage graph representation techniques to model the diffusion process in an end-to-end manner. Current solutions are only valid for a static and fixed observation scenario and fail to handle increasing observations due to the challenge of catastrophic forgetting problems inherent in the machine learning approaches used for modeling and predicting cascades. To remedy this issue, we propose a novel dynamic information diffusion model CICP (Continual Information Cascades Prediction). CICP employs graph neural networks for modeling information diffusion and continually adapts to increasing observations. It is capable of capturing the correlations between successive observations while preserving the important parameters regarding cascade evolution and transition. Experiments conducted on real-world cascade datasets demonstrate that our method not only improves the prediction performance with accumulated data but also prevents the model from forgetting previously trained tasks.

Predicting the potential user interest on topics in online social networks is important for many practical applications such as advertising, recommendation and malicious account identification. Previous methods on such topic prediction problem mainly focus on learning user preference from historical posting content, and/or rely on the interest of friends to infer the topics a user may be interested in. However, these methods fail to take full advantage of high-order interactions between users and topics and the implicit relations among users, which may result in limited performance. In addition, existing approaches usually require a large amount of samples to train the model and therefore have poor prediction performance for the users who have few content and/or rarely follow the topics. To overcome these limitations, we present a novel method MetaTP (Meta learning based Topic Prediction) for exploiting the complex preference of users over the topics and identify the potential topics for cold-start users. MetaTP is built on a fast graph convolutional network to estimate the user interest through extracting user posting behavior from historical posting content and recursively aggregating the interest from the social friends of a user. Moreover, MetaTP introduces a new way of training prediction model in a meta-learning manner, which not only improves the performance on topic prediction but also can effectively and efficiently adapt to users with a few records. We validate our MetaTP model on real-world datasets crawled from popular social platforms and the empirical results show that our approach significantly outperforms the state-of-the-art baselines.

User identity linkage (UIL) aims to link identical users engaging in multiple social networks. It has received considerable attention in both academia and industry due to its profound implications for multiple applications. Although existing approaches have achieved promising progress in UIL using various graph learning methods, they usually require a large number of labeled anchor nodes which, however, are difficult to obtain in real-world social platforms due to privacy issues. We introduce a novel UIL model NWUIL (Network Wasserstein learning for UIL) to identify anchor users across social networks in a fully unsupervised manner. Instead of point vector embedding of nodes as in previous methods, NWUIL captures node distribution in Wasserstein space with graph neural networks. We also propose to reformulate the UIL task as an optimal network transport problem, and then introduce an unsupervised mapping process based on the network Wasserstein distance for UIL. In this way, our method not only improves the anchor node aligning accuracy but also alleviates the issues caused by insufficient labeled anchor nodes. We conduct extensive experiments using real-world datasets, and demonstrate that NWUIL significantly outperforms existing unsupervised baselines while showing competitive performance as some state-of-the-art supervised approaches.

The ubiquity of mobile devices use has generated huge volumes of location-aware contextual data, providing opportunities enriching various location-based social network (LBSN) applications - e.g., trip recommendation, ride-sharing allocation and taxi demand prediction etc. Trajectory-based social circle inference (TSCI), which aims at inferring the social relationships among users based on the human mobility data, has received great attention in recent years due to its importance in many LBSN applications. However, existing solutions suffer from three key challenges, including (1) lack of modeling contextual feature in user check-ins; (2) cannot capture the structural information in user motion patterns; (3) and fail to consider the underlying mobility distribution. In this paper, we propose a novel framework ASCI-CAM (Adversity-based Social Circles Inference via Context-Aware Mobility) to address the above challenges. ASCI-CAM is a graph-based model taking into account the contextual information associated with check-ins which, combined with an attentive auto-encoder, allows for semantic trajectory representation. We regularize the learned trajectory embedding with an adversarial learning procedure, which allows us to better understand the user mobility patterns and personalized trajectory distribution. Our extensive experiments on real-world mobility datasets demonstrate that our model achieves significant improvement over the state-of-the-art baselines.

Flow super-resolution (FSR) enables inferring fine-grained urban flows with coarse-grained observations and plays an important role in traffic monitoring and prediction. The existing FSR solutions rely on deep CNN models (e.g., ResNet) for learning spatial correlation, incurring excessive memory cost and numerous parameter updates. We propose to tackle the urban flows inference using dynamic systems paradigm and present a new method FODE -- FSR with Ordinary Differential Equations (ODEs). FODE extends neural ODEs by introducing an affine coupling layer to overcome the problem of numerically unstable gradient computation, which allows more accurate and efficient spatial correlation estimation, without extra memory cost. In addition, FODE provides a flexible balance between flow inference accuracy and computational efficiency. A FODE-based augmented normalization mechanism is further introduced to constrain the flow distribution with the influence of external factors. Experimental evaluations on two real-world datasets demonstrate that FODE significantly outperforms several baseline approaches.

Network alignment (NA) - i.e., linking entities from different networks (also known as identity linkage) - is a fundamental problem in many application domains. Recent advances in deep graph learning have inspired various auspicious approaches for tackling the NA problem. However, most of the existing works suffer from efficiency and generalization, due to complexities and redundant computations.We approach the NA from a different perspective, tackling it via meta-learning in a semi-supervised manner, and propose an effective and efficient approach called Meta-NA - a novel, conceptually simple, flexible, and general framework. Specifically, we reformulate NA as a one-shot classification problem and address it with a graph meta-learning framework. Meta-NA exploits the meta-metric learning from known anchor nodes to obtain latent priors for linking unknown anchor nodes. It contains multiple sub-networks corresponding to multiple graphs, learning a unified metric space, where one can easily link entities across different graphs. In addition to the performance lift, Meta-NA greatly improves the anchor linking generalization, significantly reduces the computational overheads, and is easily extendable to multi-network alignment scenarios. Extensive experiments conducted on three real-world datasets demonstrate the superiority of Meta-NA over several state-of-the-art baselines in terms of both alignment accuracy and learning efficiency.

Understanding in-network information diffusion is a fundamental problem in many application domains and one of the primary challenges is to predict the size of the information cascade. Most of the existing models rely either on hypothesized point process (e.g., Poisson and Hawkes process), or simply predict the information propagation via deep neural networks. However, they fail to simultaneously capture the underlying structure of a cascade graph and the propagation of uncertainty in the diffusion, which may result in unsatisfactory prediction performance. To address these, in this work we propose a novel probabilistic cascade prediction framework: Variational Cascade (VaCas) graph learning networks. VaCas allows a non-linear information diffusion inference and models the information diffusion process by learning the latent representation of both the structural and temporal information. It is a pattern-agnostic model leveraging variational inference to learn the node-level and cascade-level latent factors in an unsupervised manner. In addition, VaCas is capable of capturing both the cascade representation uncertainty and node infection uncertainty, while enabling hierarchical pattern learning of information diffusion. Extensive experiments conducted on real-world datasets demonstrate that VaCas significantly improves the prediction accuracy, compared to state-of-the-art approaches, while also enabling interpretability.

Hydropower is the largest renewable energy source for electricity generation in the world, with numerous benefits in terms of: environment protection (near-zero air pollution and climate impact), cost-effectiveness (long-term use, without significant impacts of market fluctuation), and reliability (quickly respond to surge in demand). However, the effectiveness of hydropower plants is affected by multiple factors such as reservoir capacity, rainfall, temperature and fluctuating electricity demand, and particularly their complicated relationships, which make the prediction/recommendation of station operational output a difficult challenge. In this paper, we present DeepHydro, a novel stochastic method for modeling multivariate time series (e.g., water inflow/outflow and temperature) and forecasting power generation of hydropower stations. DeepHydro captures temporal dependencies in co-evolving time series with a new conditioned latent recurrent neural networks, which not only considers the hidden states of observations but also preserves the uncertainty of latent variables. We introduce a generative network parameterized on a continuous normalizing flow to approximate the complex posterior distribution of multivariate time series data, and further use neural ordinary differential equations to estimate the continuous-time dynamics of the latent variables constituting the observable data. This allows our model to deal with the discrete observations in the context of continuous dynamic systems, while being robust to the noise. We conduct extensive experiments on real-world datasets from a large power generation company consisting of cascade hydropower stations. The experimental results demonstrate that the proposed method can effectively predict the power production and significantly outperform the possible candidate baseline approaches.

Location-Based Services are often used to find proximal Points of Interest PoI - e.g., nearby restaurants and museums, police stations, hospitals, etc. - in a plethora of applications. An important recently addressed variant of the problem not only considers the distance/proximity aspect, but also desires semantically diverse locations in the answer-set. For instance, rather than picking several close-by attractions with similar features - e.g., restaurants with similar menus; museums with similar art exhibitions - a tourist may be more interested in a result set that could potentially provide more diverse types of experiences, for as long as they are within an acceptable distance from a given (current) location. Towards that goal, in this work we propose a novel approach to efficiently retrieve a path that will maximize the semantic diversity of the visited PoIs that are within distance limits along a given road network. We introduce a novel indexing structure - the Diversity Aggregated R-tree, based on which we devise efficient algorithms to generate the answer-set - i.e., the recommended locations among a set of given PoIs - relying on a greedy search strategy. Our experimental evaluations conducted on real datasets demonstrate the benefits of proposed methodology over the baseline alternative approaches.

Our ability to extract knowledge from evolving spatial phenomena and make it actionable is often impaired by unreliable, erroneous, obsolete, imprecise, sparse, and noisy data. Integrating the impact of this uncertainty is a paramount when estimating the reliability/confidence of any time-varying query result from the underlying input data. The goal of this advanced seminar is to survey solutions for managing, querying and mining uncertain spatial and spatio-temporal data. We survey different models and show examples of how to efficiently enrich query results with reliability information. We discuss both analytical solutions as well as approximate solutions based on geosimulation.

The advances in the Internet of Things (IoT) and increased availability of the road sensors allow for fine-grained traffic forecasting, which is of particular importance toward building an intelligent transportation system. In the literature, recent efforts have applied various deep learning methods for traffic forecasting, e.g., leveraging graph convolutional networks (GCNs) for spatial dependency modeling, and utilizing recurrent neural networks (RNNs) for capturing temporal dynamics. However, most of the existing approaches assume that spatial correlations are static and temporal correlations have only sequential dependencies and do not consider temporal periodicity of traffic across multiple time steps. The real challenge lies in using the dynamic spatiotemporal correlations while also considering the influence of the nontraffic-related factors, such as time-of-day and weekday-or-weekend in the learning architectures. We propose a novel framework titled “reinforced spatial-temporal attention graph (RSTAG) neural networks” for traffic prediction. Our method captures dynamic spatial correlations through diffusion network graphs, while temporal dependencies are represented through the sequence-to-sequence model with an attention mechanism. In addition, we utilize the policy gradient to update the model parameters while largely alleviating the exposure bias issue that exists in previous traffic prediction models. We conduct extensive experiments on two large-scale traffic data sets collected from the road sensor networks in Los Angles and Bay Area of California. The results demonstrate that our method significantly outperforms the state-of-the-art baselines.

Meta-learning has received a tremendous recent attention as a possible approach for mimicking human intelligence, i.e., acquiring new knowledge and skills with little or even no demonstration. Most of the existing meta-learning methods are proposed to tackle few-shot learning problems such as image and text, in rather Euclidean domain. However, there are very few works applying meta-learning to non-Euclidean domains, and the recently proposed graph neural networks (GNNs) models do not perform effectively on graph few-shot learning problems. Towards this, we propose a novel graph meta-learning framework -- Meta-GNN -- to tackle the few-shot node classification problem in graph meta-learning settings. It obtains the prior knowledge of classifiers by training on many similar few-shot learning tasks and then classifies the nodes from new classes with only few labeled samples. Additionally, Meta-GNN is a general model that can be straightforwardly incorporated into any existing state-of-the-art GNN. Our experiments conducted on three benchmark datasets demonstrate that our proposed approach not only improves the node classification performance by a large margin on few-shot learning problems in meta-learning paradigm, but also learns a more general and flexible model for task adaption.

In this work we propose DeepTrip -- an end-to-end method for better understanding of the underlying human mobility and improved modeling of the POIs' transitional distribution in human moving patterns. DeepTrip consists of: a Trip Encoder to embed a given route into a latent variable with a recurrent neural network (RNN); and a Trip Decoder to reconstruct this route conditioned on an optimized latent space. Simultaneously, we define an Adversarial Net composed of a generator and critic, which generates a representation for a given query and uses a critic to distinguish the trip representation generated from Trip Encoder and query representation obtained from Adversarial Net. DeepTrip enables regularizing the latent space and generalizing users' complex check-in preference. We demonstrate the effectiveness and efficiency of the proposed model, and the experimental evaluations show that DeepTrip outperforms the state-of-the-art baselines on various evaluation metrics.

One of the greatest challenges in automated driving is the ability to acquire, access and query the data pertaining to high resolution 3D objects from multiple heterogeneous sources. Specifically, the information extraction needs to be done by fusing data from both sensors and databases, and with real-time constraints. Existing structures and algorithmic approaches designed for regular maps - or even regular features in High Definition maps - are not optimal to handle the various challenges. In this paper, we review the importance and roles of high resolution 3D objects in High Definition maps being used in autonomous driving applications and summarize the characteristics of 3D objects compared to other regular map features. We also describe an end-to-end pipeline of a system targeting such problems and emphasize the challenges and feasible solutions to each part of the pipeline. Last but not least, we define the quantified evaluation metrics for each task and introduce the dataset that we built for this objective.

Effectively predicting the size of an information cascade is critical for many applications spanning from identifying viral marketing and fake news to precise recommendation and online advertising. Traditional approaches either heavily depend on underlying diffusion models and are not optimized for popularity prediction, or use complicated hand-crafted features that cannot be easily generalized to different types of cascades. Recent generative approaches allow for understanding the spreading mechanisms, but with unsatisfactory prediction accuracy. To capture both the underlying structures governing the spread of information and inherent dependencies between re-tweeting behaviors of users, we propose a semi-supervised method, called Recurrent Cascades Convolutional Networks (CasCN), which explicitly models and predicts cascades through learning the latent representation of both structural and temporal information, without involving any other features. In contrast to the existing single, undirected and stationary Graph Convolutional Networks (GCNs), CasCN is a novel multi-directional/dynamic GCN. Our experiments conducted on real-world datasets show that CasCN significantly improves the prediction accuracy and reduces the computational cost compared to state-of-the-art approaches.

Training a neural network model can be a lifelong learning process and is a computationally intensive one. A severe adverse effect that may occur in deep neural network models is that they can suffer from catastrophic forgetting during retraining on new data. To avoid such disruptions in the continuous learning, one appealing property is the additive nature of ensemble models. In this paper, we propose two generic ensemble approaches, gradient boosting and meta-learning, to solve the catastrophic forgetting problem in tuning pre-trained neural network models.

Network alignment (NA) is a fundamental problem in many application domains - from social networks, through biology and communications, to neuroscience. The main objective is to identify common nodes and most similar connections across multiple networks (resp. graphs). Many of the existing efforts focus on efficient anchor node linkage by leveraging various features and optimizing network mapping functions with the pairwise similarity between anchor nodes. Despite the recent advances, there still exist two kinds of challenges: (1) entangled node embeddings, arising from the contradictory goals of NA: embedding proximal nodes in a closed form for representation in a single network vs. discriminating among them when mapping the nodes across networks; and (2) lack of interpretability about the node matching and alignment, essential for understanding prediction tasks. We propose d NAME (disentangled Network Alignment with Matching Explainability) - a novel solution for NA in heterogeneous networks settings, based on a matching technique that embeds nodes in a disentangled and faithful manner. The NA task is cast as an adversarial optimization problem which learns a proximity-preserving model locally around the anchor nodes, while still being discriminative. We also introduce a method to explain our semi-supervised model with the theory of robust statistics, by tracing the importance of each anchor node and its explanations on the NA performance. This is extensible to many other NA methods, as it provides model interpretability. Experiments conducted on several public datasets show that d NAME outperforms the state-of-the-art methods in terms of both network alignment precision and node matching ranking.

We present a prototype system for effective management of a delivery fleet in the settings in which the traffic abnormalities may necessitate rerouting of (some of) the trucks. Unforeseen congestions (e.g., due to accidents) may affect the average speed along road segments that were used to calculate the routes of a particular truck. Complementary to the traditional (re) routing approaches where the main objective is to find the new shortest route to the same destination but under the changed traffic circumstances, we incorporate two additional constraints. Namely, we aim at striking a balance between minimizing the additional expenses due to drivers overtime pay and maximizing the delivery of the goods still available on the truck's load, possibly by changing the original destinations. The project is developed with an actual industry partner with main business of managing supplies for office pantries, kitchens and cafés.

Effectively modeling and predicting the information cascades is at the core of understanding the information diffusion, which is essential for many related downstream applications, such as fake news detection and viral marketing identification. Conventional methods for cascade prediction heavily depend on the hypothesis of diffusion models and hand-crafted features. Owing to the significant recent successes of deep learning in multiple domains, attempts have been made to predict cascades by developing neural networks based approaches. However, the existing models are not capable of capturing both the underlying structure of a cascade graph and the node sequence in the diffusion process which, in turn, results in unsatisfactory prediction performance. In this paper, we propose a deep multi-task learning framework with a novel design of shared-representation layer to aid in explicitly understanding and predicting the cascades. As it turns out, the learned latent representation from the shared-representation layer can encode the structure and the node sequence of the cascade very well. Our experiments conducted on real-world datasets demonstrate that our method can significantly improve the prediction accuracy and reduce the computational cost compared to state-of-the-art baselines.

Proximity-oriented spatial queries, such as range queries and k-nearest neighbors (kNNs), are common in many applications, notably in Location Based Services (LBS). However, in many settings, users may also desire that the returned proximal objects exhibit (likely) maximal and fine-grained semantic diversity. For instance, nearby restaurants with different menu items are more interesting than close ones offering similar menus. Towards that goal, we propose a topic modeling approach based on the Latent Dirichlet Allocation, a generative statistical model, to effectively model and exploit a fine-grained notion of diversity, namely based on sets of keywords (e.g., menu items) instead of a coarser user-given category (e.g., a restaurant's cuisine). In addition, and relying on the notion of Distance Signatures, we propose an index structure that can be used to effectively extract the k objects that are within a range distance from a given query location, and which are also semantically diverse. Our experimental evaluations using real datasets demonstrate that the proposed methodology is able to provide highly diversified answers to cardinality-wise constrained range queries much more efficiently than a straightforward alternative solution.

We present a novel generative Session-Based Recommendation (SBR) framework, called VAriational SEssion-based Recommendation (VASER) - a non-linear probabilistic methodology allowing Bayesian inference for flexible parameter estimation of sequential recommendations. Instead of directly applying extended Variational AutoEncoders (VAE) to SBR, the proposed method introduces normalizing flows to estimate the probabilistic posterior, which is more effective than the agnostic presumed prior approximation used in existing deep generative recommendation approaches. VASER explores soft attention mechanism to upweight the important clicks in a session. We empirically demonstrate that the proposed model significantly outperforms several state-of-the-art baselines, including the recently-proposed RNN/VAE-based approaches on real-world datasets.

Unveiling human mobility patterns is an important task for many downstream applications like point-of-interest (POI) recommendation and personalized trip planning. Compelling results exist in various sequential modeling methods and representation techniques. However, discovering and exploiting the context of trajectories in terms of abstract topics associated with the motion can provide a more comprehensive understanding of the dynamics of patterns. We propose a new paradigm for moving pattern mining based on learning trajectory context, and a method - Context-Aware Variational Trajectory Encoding and Human Mobility Inference (CATHI) - for learning user trajectory representation via a framework consisting of: (1) a variational encoder and a recurrent encoder; (2) a variational attention layer; (3) two decoders. We simultaneously tackle two subtasks: (T1) recovering user routes (trajectory reconstruction); and (T2) predicting the trip that the user would travel (trajectory prediction). We show that the encoded contextual trajectory vectors efficiently characterize the hierarchical mobility semantics, from which one can decode the implicit meanings of trajectories. We evaluate our method on several public datasets and demonstrate that the proposed CATHI can efficiently improve the performance of both subtasks, compared to state-of-the-art approaches.

Point-of-interest (POI) recommendation is essential to a variety of services for both users and business. An extensive number of models have been developed to improve the recommendation performance by exploiting various characteristics and relations among POIs (e.g., spatio-temporal, social, etc.). However, very few studies closely look into the underlying mechanism accounting for why users prefer certain POIs to others. In this work, we initiate the first attempt to learn the distribution of user latent preference by proposing an Adversarial POI Recommendation (APOIR) model, consisting of two major components: (1) the recommender (R) which suggests POIs based on the learned distribution by maximizing the probabilities that these POIs are predicted as unvisited and potentially interested; and (2) the discriminator (D) which distinguishes the recommended POIs from the true check-ins and provides gradients as the guidance to improve R in a rewarding framework. Two components are co-trained by playing a minimax game towards improving itself while pushing the other to the boundary. By further integrating geographical and social relations among POIs into the reward function as well as optimizing R in a reinforcement learning manner, APOIR obtains significant performance improvement in four standard metrics compared to the state of the art methods.

An important task in Location based Social Network applications is to predict mobility - specifically, user's next point-of-interest (POI) - challenging due to the implicit feedback of footprints, sparsity of generated check-ins, and the joint impact of historical periodicity and recent check-ins. Motivated by recent success of deep variational inference, we propose VANext (Variational Attention based Next) POI prediction: a latent variable model for inferring user's next footprint, with historical mobility attention. The variational encoding captures latent features of recent mobility, followed by searching the similar historical trajectories for periodical patterns. A trajectory convolutional network is then used to learn historical mobility, significantly improving the efficiency over often used recurrent networks. A novel variational attention mechanism is proposed to exploit the periodicity of historical mobility patterns, combined with recent check-in preference to predict next POIs. We also implement a semi-supervised variant - VANext-S, which relies on variational encoding for pre-training all current trajectories in an unsupervised manner, and uses the latent variables to initialize the current trajectory learning. Experiments conducted on real-world datasets demonstrate that VANext and VANext-S outperform the state-of-the-art human mobility prediction models.

Recent advances in network representation learning have enabled significant improvements in the link prediction task, which is at the core of many downstream applications. As an increasing amount of mobility data becoming available due to the development of location technologies, we argue that this resourceful user mobility data can be used to improve link prediction performance. In this paper, we propose a novel link prediction framework that utilizes user offline check-in behavior combined with user online social relations. We model user offline location preference via probabilistic factor model and represent user social relations using neural network embedding. Furthermore, we employ locality-sensitive hashing to project the aggregated user representation into a binary matrix, which not only preserves the data structure but also speeds up the followed convolutional network learning. By comparing with several baseline methods that solely rely on social network or mobility data, we show that our unified approach significantly improves the performance.

Learning explicit and implicit patterns in human trajectories plays an important role in many Location-Based Social Networks (LBSNs) applications, such as trajectory classification (e.g., walking, driving, etc.), trajectory-user linking, friend recommendation, etc. A particular problem that has attracted much attention recently - and is the focus of our work - is the Trajectory-based Social Circle Inference (TSCI), aiming at inferring user social circles (mainly social friendship) based on motion trajectories and without any explicit social networked information. Existing approaches addressing TSCI lack satisfactory results due to the challenges related to data sparsity, accessibility and model efficiency. Motivated by the recent success of machine learning in trajectory mining, in this paper we formulate TSCI as a novel multi-label classification problem and develop a Recurrent Neural Network (RNN)-based framework called DeepTSCI to use human mobility patterns for inferring corresponding social circles. We propose three methods to learn the latent representations of trajectories, based on: (1) bidirectional Long Short-Term Memory (LSTM); (2) Autoencoder; and (3) Variational autoencoder. Experiments conducted on real-world datasets demonstrate that our proposed methods perform well and achieve significant improvement in terms of macro-R, macro-F1 and accuracy when compared to baselines.

We study the problem of continuous maintenance of range sum heat maps over dynamically updating data objects. The range sum (RS) here refers to the sum of the weights of the data objects enclosed by a given range (rectangle) R. Range sum problems are useful in spatio-temporal data analytics and decision making processes. Recent studies on range sum problems focus on computing the MaxRS query, which finds a location to place a rectangle R such that its RS is maximized. In real applications, knowing only the location with the maximum RS may be insufficient, because decision making is a multi-factor process where maximizing the RS may just be one of the factors. It is also important to gain an overview of the RS distribution at different locations, so that decisions can be made based on global knowledge. We therefore propose to compute a range-sum heat map that visualizes the RS value for every location in a data space. Considering that data objects may be inserted into or removed from the data space dynamically, we further study the continuous maintenance of range-sum heat maps over dynamically updating data objects. We adapt algorithms to compute range-sum heat maps and to perform heat map updates. We build a demo system to showcase the usefulness of range sum heat maps and the effectiveness of the adapted algorithms.

Trajectory-User Linking (TUL) is an essential task in Geo-tagged social media (GTSM) applications, enabling personalized Point of Interest (POI) recommendation and activity identification. Existing works on mining mobility patterns often model trajectories using Markov Chains (MC) or recurrent neural networks (RNN) -- either assuming independence between non-adjacent locations or following a shallow generation process. However, most of them ignore the fact that human trajectories are often sparse, high-dimensional and may contain embedded hierarchical structures. We tackle the TUL problem with a semi-supervised learning framework, called TULVAE (TUL via Variational AutoEncoder), which learns the human mobility in a neural generative architecture with stochastic latent variables that span hidden states in RNN. TULVAE alleviates the data sparsity problem by leveraging large-scale unlabeled data and represents the hierarchical and structural semantics of trajectories with high-dimensional latent variables. Our experiments demonstrate that TULVAE improves efficiency and linking performance in real GTSM datasets, in comparison to existing methods.

The typical aim of User Identity Linkage (UIL) is to detect when users from across different social platforms are actually one and the same individual. Existing efforts to address this problem of practical relevance span from user-profile-based, through user-generated-content-based, user-behavior-based approaches to supervised or unsupervised learning frameworks, to subspace learning-based models. Most of them often require extraction of relevant features (e.g., profile, location, biography, networks, behavior, etc.) to model the user consistently across different social networks. However, these features are mainly derived based on prior knowledge and may vary for different platforms and applications. Inspired by the recent successes of deep learning in different tasks, especially in automatic feature extraction and representation, we propose a deep neural network based algorithm for UIL, called DeepLink. It is a novel end-to-end approach in a semi-supervised learning manner, without involving any hand-crafting features. Specifically, DeepLink samples the networks and learns to encode network nodes into vector representation to capture local and global network structures which, in turn, can be used to align anchor nodes through deep neural networks. A dual learning based paradigm is exploited to learn how to transfer knowledge and update the linkage using the policy gradient method. Experiments conducted on several public datasets show that DeepLink outperforms the state-of-the-art methods in terms of both linking precision and identity-match ranking.

The topics of tracking moving objects and moving shapes have been extensively researched in multiple communities – from Moving Objects Databases (MOD) and spatio-temporal data management, through image/video processing and traffic management, to environmental and ecology studies. This paper gives a summary of the topics discussed in the advanced seminar on tracking objects and shapes, as well as an overview of its proposed structure. After a brief introduction and motivation-survey of different research fields and societal applications, the first part of the seminar will give a historic survey of the fundamental techniques for tracking mobile objects. The second part will give an overview of the approaches popular in MOD and spatiotemporal data management communities (tracking and querying, streaming data, map-matching, etc.). The third part is the central one – discussing the issues and solutions in distributed tracking of moving objects and shapes: from topological predicates and trends detection, through tracking deformable shapes, to specifics of indoor tracking. The fourth major part is intended to be a "potpourri-style" review of different application contexts and the popular approaches for tracking individual objects and shapes – spanning from collective motion analysis in social networks and animal herds, through toxic elements, pollutants, and geoprocesses (landslides), to different approaches for visual analytics in this context. The main objective of this advanced seminar is to provide a cohesive overview of the different perspectives on motion tracking; the corresponding approaches for its effective management; and possibilities for other research directions

We investigate a novel variant of the well-known MaxRS (Maximizing Range Sum) problem - namely, the MAxRS3 (Maximizing Area-Range Sum for Spatial Shapes). The MaxRS problem amounts to detecting a location where a fixed-size rectangle R should be placed, so that it covers a maximum number of points - or sum of weights, if the points are weighted - from a given input set of 2D points. While variants have tackled the settings in which the input set to MaxRS problem consists of polygons instead of points - the solution is still based on (weighted) count. We postulate that in many practical applications it is of interest to determine where to place the input rectangle so that the total area-coverage in its interior is maximized. In this paper, we formalize the MAxRS3 problem and propose (to our knowledge) the first solution to this new problem.

We address the problem of efficient maintenance of the answer to a new type of query: Continuous Maximizing Range- Sum (Co-MaxRS) for moving objects trajectories. The traditional static/spatial MaxRS problem finds a location for placing the centroid of a given (axes-parallel) rectangle R so that the sum of the weights of the point-objects from a given set O inside the interior of R is maximized. However, moving objects continuously change their locations over time, so the MaxRS solution for a particular time instant need not be a solution at another time instant. In this paper, we devise the conditions under which a particular MaxRS solution may cease to be valid and a new optimal location for the query-rectangle R is needed. More specifically, we solve the problem of maintaining the trajectory of the centroid of R. In addition, we propose efficient pruning strategies (and corresponding data structures) to speed-up the process of maintaining the accuracy of the Co-MaxRS solution. We prove the correctness of our approach and present experimental evaluations over both real and synthetic datasets, demonstrating the benefits of the proposed methods.

An inherent challenge arising in any dataset containing information of space and/or time is uncertainty due to various sources of imprecision. Integrating the impact of the uncertainty is a paramount when estimating the reliability (confidence) of any query result from the underlying input data. To deal with uncertainty, solutions have been proposed independently in the geo-science and the data-science research community. This interdisciplinary tutorial bridges the gap between the two communities by providing a comprehensive overview of the different challenges involved in dealing with uncertain geo-spatial data, by surveying solutions from both research communities, and by identifying similarities, synergies and open research problems.

Understanding human trajectory patterns is an important task in many location based social networks (LBSNs) applications, such as personalized recommendation and preference-based route planning. Most of the existing methods classify a trajectory (or its segments) based on spatio-temporal values and activities, into some predefined categories, e.g., walking or jogging. We tackle a novel trajectory classification problem: we identify and link trajectories to users who generate them in the LBSNs, a problem called Trajectory-User Linking (TUL). Solving the TUL problem is not a trivial task because: (1) the number of the classes (i.e., users) is much larger than the number of motion patterns in the common trajectory classification problems; and (2) the location based trajectory data, especially the check-ins, are often extremely sparse. To address these challenges, a Recurrent Neural Networks (RNN) based semi-supervised learning model, called TULER (TUL via Embedding and RNN) is proposed, which exploits the spatio-temporal data to capture the underlying semantics of user mobility patterns. Experiments conducted on real-world datasets demonstrate that TULER achieves better accuracy than the existing methods.

We address the problem of incorporating uncertain location data in the generation of speed profiles for vehicles on roads with multiple lanes. Moving objects' location data can be obtained from different/multiple sources - e.g., GPS on-board the moving objects, roadside sensors, cameras. However, each source has inherent limitations that affect the precision - from pure measurement-errors, to sparsity of their distribution. Incorporating such imprecision is paramount in any query/analytics oriented system that deals with location data. The difficulties multiply when one needs to reason about localization with lane-awareness and attempts to use the location-in-time data to enable effective navigation systems. To tackle this problem, we take a step towards: (a) incorporating uncertainty of the objects' locations into traditional map-matching processes, thereby augmenting them with its impact on different lanes, (b) introducing an information theoretic distance function that can be used to decide when two "units" qualify to belong to a same cluster. Our experiments demonstrate that the proposed approach offers a more effective way to generate spatio-temporal clusters with similar speed profiles which, in turn, enables more efficient routes generation.

We address the problem of maintaining the correct answer-sets to the Conditional Maximizing Range-Sum (C-MaxRS) query in spatial data streams. Given a set of (possibly weighted) 2D point objects, the traditional MaxRS problem determines an optimal placement for an axes-parallel rectangle r so that the number -- or, the weighted sum -- of objects in its interior is maximized. In many practical settings, the objects from a particular set -- e.g., restaurants -- can be of distinct types -- e.g., fast-food, Asian, etc. The C-MaxRS problem deals with maximizing the overall sum, given class-based existential constraints, i.e., a lower bound on the count of objects of interests from particular classes. We first propose an efficient algorithm to the static C-MaxRS query, and extend the solution to handle dynamic (data streams) settings. Our experiments over datasets of up to 100,000 objects show that the proposed solutions provide significant efficiency benefits.

Digital Elevation Modeling (DEM) has been a widely used methodology in plethora of application domains, ranging from climate and geological studies, through temporal evolution of various migration patterns, to Geographic Information Systems (GIS) broadly. However, the existing DEM methodologies and systems cannot quite straightforwardly be extended to catch up with the demands due to recent developments in autonomous driving, vehicle localization, drone and dynamically evolving high-definition smart city modeling. The new challenges are the demand of higher precision, sparse(r) elevation data compression, real-time efficient retrieval and intra-sources data integration. Motivated by this, we take a first step towards developing a tile based, multi-layer high precision DEM system, which aims at seamlessly integrating (and aligning) DEM from different sources, and enables context-driven variations in zoom levels. In addition, to further improve the efficiency of the focused-retrieval of the data necessary to construct the DEM with the desired quality assurance, our vision targets the collaborative compression among heterogeneous data sources.

We address the problem of efficient spatio-temporal clustering of speed data in road segments with multiple lanes. We postulate that the navigation/route plans typically reported by different providers as a single-value need not be accurate in multi-lane networks. Our methodology generates lane-aware distribution of speed from GPS data and agglomerates the basic space and time units into larger clusters. Thus, we achieve a compact description of speed variations which can be subsequently used for more accurate trips planning. We provide experiments that demonstrate the benefits of our proposed approaches.

This work presents a system for augmenting the functionality of Yelp-like recommendation sites by enabling users to search for places bounded by travel-time when using public transportation, and modifying recommendations based on updated weather conditions. Using public transport, although is cheaper and efficient, entails that only fixed places of boarding/exiting may be used which, in turn, implies walking to (from) a particular location from (to) a given station. Given the impact of the weather on the mood and activities, preferences for a certain type of services may need to be dynamically adjusted based on the current weather or the near-future forecast, modulo travel-routes to preferred locations. In this work, we develop a model to predict a user's preferred mode of transport (car, or public transit) from their old check-ins and incorporate the weather context into the recommendation process. We use event-based modeling to control the extent of walking depending on user-defined tolerance information and live weather conditions. We implemented a web application (both desktop and mobile platforms), utilizing existing tools such as Google Maps Direction API and Open Weather Map API for retrieving real-time information.

This work presents a distributed implementation for processing Maximizing Range Sum (MaxRS) query in Wireless Sensor Networks (WSN). MaxRS query is useful in many spatially-distributed event monitoring and target tracking applications. Given the location and current readings of the nodes, and a rectangle R, MaxRS finds a location of R that maximizes the sum of the readings of all the nodes covered by R. Our system performs MaxRS query in a user-specified time-interval γ and using the result obtained, attempts to maintain a certain degree of energy conservation in the WSN, based on a user-defined threshold δ. Since centralized processing of the raw readings and subsequently determining the MaxRS may incur significant communication overheads, we developed a distributed algorithm to compute MaxRS. We implemented our system in a heterogeneous WSN consisting of TelosB and SunSPOT motes, and illustrate the end-user tools: GUI for specifying required parameters, and real-time visualization of MaxRS solutions and estimated network energy consumption.

This work addresses the problem of fusing spatio-temporal uncertainties obtained from heterogeneous location sources: on-board GPS devices and roadside sensors. We develop a model for combining the uncertain location-values from the different sources, which further narrows the possible locations of a given object. Our experiments demonstrate that the proposed model may eliminate significant amount of the false positives, compared to the traditional space-time prism (bead) uncertainty models.

Location-related data has a tremendous impact in many applications of high societal relevance and its growing volume from heterogeneous sources is one true example of a Big Data [1]. An inherent property of any spatio-temporal dataset is uncertainty due to various sources of imprecision. This tutorial provides a comprehensive overview of the different challenges involved in managing uncertain spatial and spatio-temporal data and presents state-of-the-art techniques for addressing them.

We address the problem of large scale probabilistic association rule mining and consider the trade-offs between accuracy of the mining results and quest of scalability on modest hardware infrastructure. We demonstrate how extensions and adaptations of research findings can be integrated in an industrial application, and we present the commercially deployed SILVERBACK framework, developed at Voxsup Inc. SILVERBACK tackles the storage efficiency problem by proposing a probabilistic columnar infrastructure and using Bloom filters and reservoir sampling techniques. In addition, a probabilistic pruning technique has been introduced based on Apriori for mining frequent item-sets. The proposed target-driven technique yields a significant reduction on the size of the frequent item-set candidates. We present extensive experimental evaluations which demonstrate the benefits of a context-aware incorporation of infrastructure limitations into corresponding research techniques. The experiments indicate that, when compared to the traditional Hadoop-based approach for improving scalability by adding more hosts, SILVERBACK - which has been commercially deployed and developed at Voxsup Inc. since May 2011 - has much better run-time performance with negligible accuracy sacrifices.

This work addresses the problem of energy efficient management of mobile resource distribution in Wireless Sensor Networks (WSN), subject to Quality of Service (QoS) constraints. Monitored phenomena may require an increased coverage within a particular area and we present novel methodologies for optimizing the "bargaining stage" when deciding how to select the mobile resources to be re-located in response to such events. Our experimental results demonstrate significant energy savings, both in terms of communication overheads and maintenance of the hierarchical routing structures, as well as the quality assurances in terms of the turnaround time.

We present an implementation of a system for managing evolving shapes in Wireless Sensor Networks (WSN). A shape is a contiguous region in which the measurements of the sensors detect values above a given threshold. Our system, in its current version, solves two important problems: (1) Detecting and tracking the changes of boundaries; (2) Detecting an occurrence of within distance predicate for two (or more) shapes. A centralized approach (transmitting raw measurements to a dedicated sink) incurs communication overhead, so we developed distributed algorithms for managing the predicates related to evolving shapes. This demo will present the implementation of our solutions in a heterogeneous WSN consisting of TelosB and SunSPOT motes. It will also illustrate the end-user tools: interface for specifying the parameters of the predicates, along with real-time visualization of their evaluation.

This work addresses the problem of efficient distributed detection and tracking of mobile and evolving/deformable spatial shapes in Wireless Sensor Networks (WSN). The shapes correspond to contiguous regions bounding the locations of sensors in which the readings of the sensors satisfy a particular threshold-based criterion related to the values of a physical phenomenon that they measure. We formalize the predicates representing the shapes in such settings and present detection algorithms. In addition, we provide a light-weight protocol and aggregation methods for energy-efficient distributed execution of those algorithms. Another contribution of this work is that we developed efficient techniques for detecting a co-occurrence of shapes within a given proximity from each other. Our experiments demonstrate that, when compared to the centralized techniques -- which is, predicates being detected in a dedicated sink -- as well as distributed periodic contours construction, our methodologies yield significant energy/communication savings.

This paper addresses the problem of efficient intrusion detection for mobile devices via correlating the user’s location and time data. We developed two statistical profiling approaches for modeling the normal spatio–temporal behavior of the users: one based on an empirical cumulative probability measure and the other based on the Markov properties of trajectories. An anomaly is detected when the probability of a particular (location, time) evolution matching the normal behavior of a given user becomes lower than a certain threshold, determined by controlling the recall rate of the model of the normal user’s behavior. We used compression techniques to reduce processing overhead while maintaining high accuracy. Our evaluation based on the Reality Mining and Geolife data sets shows that the proposed system is capable of detecting a potential intrusion within 15 min and with 94 % accuracy.

This work tackles the management of novel types of inconsistencies in Spatio-Temporal Databases, different from traditional database settings where integrity constraints pertain to the explicitly stored (or, defined via views and aggregates) values. We observe that spatio-temporal data has its specific types of ßemanticconstraints and we aim at minimization of the changes needed for repairing their violations.

We address the problem of spatial queries in Wireless Sensor Networks (WSN) via hybrid overlays, where the data values may correspond to different physical phenomena and sensors may be correlated with spatial constraints. We show how hierarchical data and space abstractions can be used to represent Voronoi Cell based partitions of the sensing field and use Voronoi Trees to efficiently map the hierarchical abstractions for energy-efficient processing. The proposed scheme is simulated on the SidNET, a JiST/SWANS based sensor network simulation platform. The performance results show significant advantages in terms of accurate field representation at different levels of the tree hierarchy with a trade-off in query processing delay.

Similarity among mobile entities is an important type of query for many application domains. This tutorial provides a comprehensive overview of the different challenges related to assessing the similarity of spatio-temporal objects, along with the corresponding results/techniques.

We tackle two important problems that arise in simulation-based studies of various data-related properties in the context of Wireless Sensor Networks (WSNs): (1) reducing the turnaround time for completing the simulations in a large-scale parameter space; (2) providing database functionalities for a more detailed insight into the simulation's evolution. Towards these goals, we have developed the DiSSIDnet (Distributed System for Simulation and Integrated Development for Wireless Sensor Networks). Leveraging upon our earlier works on the SIDnet-SWANS tool [3], DiSSIDnet not only provides the ability of a synchronized execution of the simulations in a distributed environment, but also maintains the simulation data over the parameter-space in a relational database. In addition to post-simulation queries that can be posed to the database, we also provide the feature of specifying triggers that can generate notifications upon detecting certain events of interest during the simulation process.

We address the problem of efficient in-network processing of hybrid spatial queries in Wireless Sensor Networks (WSN), where the data may correspond to different physical phenomena in different regions. We propose space and communication efficient schemes capable of correlating spatial dimension with different physical values. To trade-off (im)precision vs. energy consumption, the proposed schemes combine rank order statistics, regular sampling, and bitmap representation. We present a proof of concept implementation of the proposed methodology and quantify the benefits of our approach through simulations.

We address the problem of efficient detection of destination-related motion trends in Wireless Sensor Networks (WSN) where tracking is done in collaborative manner among the sensor nodes participating in location detection. In addition to determining a single location, applications may need to detect whether certain properties are true for the (portion of the) entire trajectories. Transmitting the sequence of (location, time) values to a dedicated sink and relying on the sink to detect the validity of the desired properties is a brute-force approach that generates a lot of communication overhead. We present an in-network distributed algorithm for efficient detecting of the Continuously Moving Towards predicate with respect to a given destination that is either a point or a region with polygonal boundary. Our experiments demonstrate that the proposed approaches yield substantial savings when compared to the brute-force one.

Wireless Sensor Networks (WSN) which contain heterogeneous nodes and monitor multiple phenomena present a unique set of challenges in regards to efficient management of reactive behavior. The ECA (on Event if Condition then Action) paradigm from Active Databases offers a solution via event-based synchronization which provides reduced energy consumption compared to continuous monitoring. In our demo, we show how to utilize this approach via compilation of system-level ECA triggers to mote-specific trigger code. We also demonstrate the practicality of the approach by constructing a heterogeneous WSN of TelosB/SunSPOT motes and using our tools to implement reactive behaviors based on temperature/luminance data.

This paper addresses the problem of efficient and effective parameter variation modeling and sampling in computer architecture simulations. While there has been substantial progress in accelerating simulation time for circuit designs subject to manufacturing variations, these approaches are not generally suitable for architectural studies. Toward this we investigated two complementary avenues: (1) adapting low-discrepancy sampling methods for use in Monte Carlo architectural simulations. We apply techniques previously developed for gate-level circuit models to higher level component models and in so doing drastically reduce the number of samples needed for detailed simulation; (2) applying multi-resolution analysis to appropriately decompose geometric regions of a chip, and achieve more effective description of parameter variations without increasing computational complexity. Our experimental results demonstrate that the combined techniques can reduce the number of Monte Carlo trials by a factor of 3.3, maintaining the same accuracy while significantly reducing the overall simulation run-time.

Trajectories representing the motion of moving objects are typically obtained via location sampling, e.g. using GPS or road-side sensors, at discrete time-instants. In-between consecutive samples, nothing is known about the whereabouts of a given moving object. Various models have been proposed (e.g., sheared cylinders; spacetime prisms) to represent the uncertainty of the moving objects both in unconstrained Euclidian space, as well as road networks. In this paper, we focus on representing the uncertainty of the objects moving along road networks as time-dependent probability distribution functions, assuming availability of a maximal speed on each road segment. For these settings, we introduce a novel indexing mechanism -- UTH (Uncertain Trajectories Hierarchy), based upon which efficient algorithms for processing spatio-temporal range queries are proposed. We also present experimental results that demonstrate the benefits of our proposed methodologies.

This work addresses the problem of geographic routing in the presence of holes or voids in wireless sensor networks. We postulate that, once the boundary of the hole has been established, relying on the existing algorithms for bypassing it may cause severe depletion of the energy reserves among the nodes at (or near) that boundary. This, in turn, may soon render some of those nodes useless for any routing (and/or sensing) purposes, thereby effectively enlarging the size of the pre-existing hole. To extend the lifetime of the nodes along the boundary of a given hole, we propose two heuristic approaches which aim at relieving some of the routing load of the boundary nodes. Towards that, our approaches propose that some of the routes that would otherwise need to bypass the hole along the boundary, should instead start to deviate from their original path further from the hole. Our experiments demonstrate that the proposed approaches not only increase the lifetime of the nodes along the boundary of a given hole, but also yield a more uniform depletion of the energy reserves in its vicinity.

We investigate the benefits of incorporating the semantics of the problem into the query processing algorithms in multicore settings. We present and evaluate three heuristics for processing spatio-temporal range queries in multicore settings, and demonstrate that significant speed-ups can be achieved, when compared to the (semi) naive approach which relies on the compiler to generate the multicore-compatible code.

This work addresses the problem of managing the sensor-coverage and organizing the epochs in a manner that balances the trades-offs between the accuracy and energy consumptions during target tracking in Wireless Sensor Networks (WSN). While the typical target tracking approaches are based on movement prediction, we only assume a knowledge of some maximal speed of the target during certain time-intervals. This, in turn, restricts its whereabouts to a disk-bound area throughout such intervals. In such settings, we seek to determine a sensor cover, a subset of all the nodes that need to be awake, which ensures that the target can be detected during the given epoch. Towards this, we propose sensor-cover selection methodologies, Greedy Uncertain Moving Object coverage sensor set selection (GUMO) and PAttern Based coverage sensor set selection (PAB). GUMO is a heuristic maximizing the coverage gain at each step, while PAB is an approach based on optimal deployment pattern of sensor nodes achieving coverage of the disk area bounding the target's whereabouts. We conduct extensive simulations to evaluate the performance of the algorithms, and the results reveal that GUMO and PAB not only provide substantial energy saving due to reduction in the communications involved in selecting tracking participant-nodes and principal(s), while assuring a bounded error on the target's location.

We address the problem of extending the lifetime of wireless sensor networks using multi-path routing based on a family of flexible routes with soft quality of service guarantees in terms of the packets’ delivery latency. We introduce a methodology based on Bezier curves as guiding trajectories in the routing process and we address the balancing of the workload among neighboring nodes. An added benefit, due to the flexibility of the Bezier curves, is that the shapes of the (alternate) routes can be constructed in a manner that prolongs the lifetime of the nodes in the vicinity of a given source/sink. We describe a forwarding algorithm, where the relay nodes can determine locally the Bezier curve they belong to and which requires only the transmission of the so-called control points that determine the shape of one (boundary) curve. We also show how our forwarding algorithm can be adapted to incorporate the sleep-schedule of the individual nodes, thereby further prolonging the networks’ lifetime. Our simulations demonstrate that the Bezier-based routing algorithms can yield significant improvements in the networks’ overall lifetime.

This work addresses the problem of principal node selection during the tracking process in Wireless Sensor Networks (WSNs). In a typical tracking scenario, the location of a mobile unit is determined via collaborative trilateration by the nodes that have the tracked object within their sensing range. One of the participants in the trilateraion---the tracking principal---is in charge of transmitting the location and time information to a designated sink. However, as the moving object changes its location, a new principal needs to be determined and handed off the task of the subsequent sensing, trilateration and transmission to the sink. We observe that in many WSN applications in which sensing/sampling needs to be combined with multihop transmission and, possibly, in-network aggregation, the typical processing is organized in synchronized intervals, called epochs. We postulate that taking the semantics of the epoch into consideration is important when selecting tracking principals and we present efficient algorithmic solutions towards this goal. Our experiments demonstrate that the proposed approach can yield significant reduction in the number of hand-offs between consecutive tracking principals, when compared to previous works.

For high-density networks, several studies have proposed field-based routing paradigms to uniformly distribute the traffic load throughout the network. However, as network density decreases, we observe major shortcomings of the current state-of-the-art: (i) fewer number of neighbors reduce the number of available paths and leads to path merging and (ii) the paths directed towards the border of the network merge into a single path. These path merging effects decrease significantly the energy balance, and as consequence, the lifetime of the network. In this paper, we propose a novel mechanism to enable a better load balancing for single-source and multiple-source scenarios. Our evaluations demonstrate that by using the proposed methodology, the network lifetime can be prolonged between 30% and 40%.

Processing spatio-temporal queries pertaining to the whereabouts of a large number of mobile entities has traditionally been the topic of the Moving Objects Databases (MOD)research. More recently, due to the advances in sensing and communication technologies, part of the Wireless Sensor Networks(WSN) applications have focused on tracking of mobile objects. These two observations are enough of to warrant a "call" for a confluence of two relatively new but established disciplines. However we observe that a research field of its own right and, historically older than both MOD and WSN - traffic/transportation management - can also capitalize on merging the existing experiences for its own information fusion desiderata In this talk, we will overview applications from seemingly disparate domains and identify their commonalities in terms of the spatio-temporal contexts, and we will discuss how a reactive behavior with pro-active consequences can be efficiently used for large-scale management of mobile data and meta-data.

We address the problem of efficient processing of spatio-temporal range queries for moving objects whose whereabouts in time are not known exactly. The fundamental question tackled by such queries is, given a spatial region and a temporal interval, retrieve the objects that were inside the region during the given interval. As earlier works have demonstrated, when the location, time information is uncertain, syntactic constructs are needed to capture the impact of the uncertainty, along with the corresponding processing algorithms. In this work, we focus on the uncertainty model that represents the whereabouts in-between two known locations as a bead and an uncertain trajectory is represented as a necklace -- a sequence of beads. For each syntactic variant of the range query, we present the respective processing algorithms and, in addition, we propose pruning strategies that speed up the generation of the queries' answers. We also present the experimental observations that quantify the benefits of our proposed methodologies.

This work addresses the problem of processing continuous nearest neighbor (NN) queries for moving objects trajectories when the exact position of a given object at a particular time instant is not known, but is bounded by an uncertainty region. As has already been observed in the literature, the answers to continuous NN-queries in spatio-temporal settings are time parameterized in the sense that the objects in the answer vary over time. Incorporating uncertainty in the model yields additional attributes that affect the semantics of the answer to this type of queries. In this work, we formalize the impact of uncertainty on the answers to the continuous probabilistic NN-queries, provide a compact structure for their representation and efficient algorithms for constructing that structure. We also identify syntactic constructs for several qualitative variants of continuous probabilistic NN-queries for uncertain trajectories and present efficient algorithms for their processing.

This work addresses the problem of processing spatio-temporal range queries when the mobile entities are tracked in Wireless Sensor Network (WSN). We demonstrate that in many realistic settings, depending on the parameters of a given range query, the tracking of a particular moving object may not be needed past certain thresholds in space and/or time. We also propose and analyze distributed data-reduction techniques for the purpose of reducing the energy consumption due to communication.

This work addresses the problem of managing the reactive behavior in Wireless Sensor Networks (WSN). We consider settings in which the occurrence of a particular event, detected in a state that satisfies a given condition, should fire the execution of an action. We observe that in WSN settings, both the event and condition may pertain to some continuous phenomena that are monitored by distinct groups of nodes and, in addition, their respective detection may impose an extra communication overhead, if a correct executional behavior is desired in terms of firing the action. Towards that end, we propose the concept of a {\it meta trigger},which essentially translates a particular request, so that the communication overhead among the entities participating in its processing is minimized. We discuss a proof-of-concept implementation which demonstrates the benefits of the proposed methodology on an actual small-size network, and we present a detailed simulation-based experimental evaluation in large-scale networks. Our experiments indicate that the meta-triggers can yield substantial savings in the energy (and bandwidth) expenditures of the network, while preserving the intended executional correctness.

This work presents the SIDnet, a simulation-based environment for applications development in wireless sensor networks settings. It enables run-time interactions with the network for the purpose of observing the behavior of algorithms protocols in the presence of various conditions such as phenomena fluctuations, or a sudden loss of service both at an individual node, as well as a collection of nodes.

We address the problem of performing efficient similarity join for large sets of moving objects trajectories. Unlike previous approaches which use a dedicated index in a transformed space, our premise is that in many applications of location-based services, the trajectories are already indexed in their native space, in order to facilitate the processing of common spatio-temporal queries, e.g., range, nearest neighbor etc. We introduce a novel distance measure adapted from the classic Frechet distance, which can be naturally extended to support lower/upper bounding using the underlying indices of moving object databases in the native space. This, in turn, enables efficient implementation of various trajectory similarity joins. We report on extensive experiments demonstrating that our methodology provides performance speed-up of trajectory similarity join by more than 50% on average, while maintaining effectiveness comparable to the well-known approaches for identifying trajectory similarity based on time-series analysis.

The last decade has witnessed a tremendous growths of interests in applications that deal with querying and mining of time series data. Numerous representation methods for dimensionality reduction and similarity measures geared towards time series have been introduced. Each individual work introducing a particular method has made specific claims and, aside from the occasional theoretical justifications, provided quantitative experimental observations. However, for the most part, the comparative aspects of these experiments were too narrowly focused on demonstrating the benefits of the proposed methods over some of the previously introduced ones. In order to provide a comprehensive validation, we conducted an extensive set of time series experiments re-implementing 8 different representation methods and 9 similarity measures and their variants, and testing their effectiveness on 38 time series data sets from a wide variety of application domains. In this paper, we give an overview of these different techniques and present our comparative experimental findings regarding their effectiveness. Our experiments have provided both a unified validation of some of the existing achievements, and in some cases, suggested that certain claims in the literature may be unduly optimistic.

This work addresses the problem of obtaining the degree of similarity between trajectories of moving objects. Typically, a Moving Objects Database (MOD) contains sequences of (location, time) points describing the motion of individual objects, however, they also implicitly storethe velocity -- an important attribute describing the dynamics the motion. Our main goal is to extend the MOD capability with reasoning about how similar are the trajectories of objects, possibly moving along geographically different routes. We use a distance function which balances the lack of temporal-awareness of the Hausdorff distance with the generality (and complexity of calculation) of the Fréchet distance. Based on the observation that in practice the individual segments of trajectories are assumed to have constant speed, we provide efficient algorithms for: (1) optimal matching between trajectories; and (2) approximate matching between trajectories, both under translations and rotations, where the approximate algorithm guarantees a bounded error with respect to the optimal one.

This work tackles the problem of answer-aggregation for continuous spatio-temporal range queries in distributed settings. We assume a grid-like coverage of the spatial universe of discourse, in which each cell is governed by a Base Station (BS) that communicates with the mobile users in its zone, and is also equipped with a server that has Moving Objects Database (MOD) capabilities. The MOD server stores the data for the moving objects in a given cell, processes the continuous queries pertaining to that cell, and is connected to the MOD servers in the neighboring cells. We demonstrate that, when a range query that spans over more than one cell needs to have its answer computed for a user located in a particular cell, by intelligently combining the transmission and the aggregation of the partial results, substantial improvements can be achieved at the global level. Towards this end, we present the BORA (Bresenham-based Overlay for Routing and Aggregation) tree, which is used to combine the transmission and local data aggregation along the routes to the destination of the query's answer.

This work addresses the problem of extending the lifetime of a wireless sensor network, when a bounded delay on receiving the packets is acceptable for a given sink node. The temporal threshold for the Quality of Data (QoD) tolerance is specified with respect to the time that it takes for the packets to travel from the source to the sink along an optimal route. For these settings, we propose a methodology that enables controlling the spatio-temporal load balancing among the sensors around the optimal route. Given the QoD threshold, we use it to derive a set of parameterized Bezier curves which serve as alternate routes between the (source,sink) pair, relieving the nodes along the optimal route, while ensuring a bound on the delay of packets delivery. We provide experimental results which demonstrate that our proposed methodology can prolong the sensor networks’ lifetime for various definitions of the concept of a "lifetime" in the existing literature.

We present our prototype system, OMCAT, which optimizes the reevaluation of a set of pending continuous spatio-temporal queries on trajectory data, when some of the trajectories are affected by traffic abnormalities reported. The key observation that motivates OMCAT is that an abnormality in a given geographical region may cause changes to the answers of queries pertaining to future portions of affected trajectories. We investigate the sources of context-switching costs at various levels and propose solutions that utilize the correlation of several context dimensions to orchestrate the reevaluation of the queries. OMCAT, fully implemented on top of an existing Object Relational Database Management System - Oracle 9i, demonstrates that our techniques can substantially reduce the response time during query answer update.

This work addresses the problem of efficient reactive management of topological predicates in MOD (Moving Objects Databases) settings. Detecting the satisfiability of such predicates in mobile and dynamic environments requires management of continuous and persistent conditions. We introduce two dynamical topological predicates: moving-along and moving-towards and we present efficient algorithmic solutions for their processing. Based on this, we subsequently take a deeper insight in the behavioral aspects of a MOD which manages them and we argue that the traditional ECA (Event Condition Action) paradigm, while it may ensure correct behavior, is not well-suited for enabling the users to declaratively specify some of the parameters that may affect the efficiency aspect of the reactive behavior. Towards this end, we introduce the (ECA)2 (Evolving and Context-Aware Event-Condition-Action) paradigm as a tool for specification of the triggers used by a MOD that handles requests which span over a time-interval in dynamic environments.

This article addresses the problem of managing Moving Objects Databases (MODs) which capture the inherent imprecision of the information about the moving object's location at a given time. We deal systematically with the issues of constructing and representing the trajectories of moving objects and querying the MOD. We propose to model an uncertain trajectory as a three-dimensional (3D) cylindrical body and we introduce a set of novel but natural spatio-temporal operators which capture the uncertainty and are used to express spatio-temporal range queries. We devise and analyze algorithms for processing the operators and demonstrate that the model incorporates the uncertainty in a manner which enables efficient querying, thus striking a balance between the modeling power and computational efficiency. We address some implementation aspects which we experienced in our DOMINO project, as a part of which the operators that we introduce have been implemented. We also report on some experimental observations of a practical relevance.

This work addresses the problem of workflow requirements specifications considering the realistic assumptions that, it involves experts from different domains (i.e. representatives of different business policies); not all the possible execution scenarios are known beforehand, during the early stage of specification. In particular, since the main purpose of a workflow is to achieve a certain (bussiness) goal, we propose a formalism which enables the users to specify their requirements (and expectations) and test if the information that they have provided is, in a sense, sufficient for the workflow to behave "as desired", in terms of the goal. Our methodology allows domain experts to express not only their knowledge, but also the "ignorance" (the semantics allows for unknown values to reflect a realistic situation of agents dealing with incomplete information) and the possibility of occurrence of exceptional situations. As a basis for formalizing the process of equirements specifications, we are using the recent results on reasoning about actions. We propose a high level language AW which enables specifying the effects that activites have on the environment and how they should be coordinated. We also describe our prototype tool for process specification. Strictly speaking, in this work we go "one step" before actual analysis and design, and offer a formalism which enables the involved partners to see if the extent to which they have expressed their domain knowledge (which may sometimes be subject to a proprietary restricions) can satisfy the intended needs and behaviour of their product_to_be. We define an entailment relation which enables reasoning about the correctness of the specification, in terms of achieving a desired goal and, also testing about consequences of modifications in the workflow descriptions.

Presents the design of an interactive tool for minimal updates of views in knowledge bases, while maintaining the consistency, expressed by a set of integrity constraints. Minimality is based on a partial order which captures the distance between the old state, before the update request, and the new state, in which the request is satisfied. On the user interface part, once the schema and the database are selected from the initial menu, the system automatically generates the selection menus and communication boxes to guide the user through the update.