Learning Spatiotemporal Manifold Representation for Probabilistic Land Deformation Prediction.

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.

Adversarial Human Trajectory Learning for Trip Recommendation.

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.

MetaGeo: A General Framework for Social User Geolocation Identification With Few-Shot Learning.

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.

MetaMove: On Improving Human Mobility Classification and Prediction via Metalearning.

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.

Toward Discriminating and Synthesizing Motion Traces Using Deep Probabilistic Generative Models.

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.

Recommendation via Collaborative Autoregressive Flows.

Although it is one of the most widely used methods in recommender systems, Collaborative Filtering (CF) still has difficulties in modeling non-linear user-item interactions. Complementary to this, recently developed deep generative model variants (e.g., Variational Autoencoder (VAE)) allowing Bayesian inference and approximation of the variational posterior distributions in these models, have achieved promising performance improvement in many areas. However, the choices of variation distribution - e.g., the popular diagonal-covariance Gaussians - are insufficient to recover the true distributions, often resulting in biased maximum likelihood estimates of the model parameters. Aiming at more tractable and expressive variational families, in this work we extend the flow-based generative model to CF for modeling implicit feedbacks. We present the Collaborative Autoregressive Flows (CAF) for the recommender system, transforming a simple initial density into more complex ones via a sequence of invertible transformations, until a desired level of complexity is attained. CAF is a non-linear probabilistic approach allowing uncertainty representation and exact tractability of latent-variable inference in item recommendations. Compared to the agnostic-presumed prior approximation used in existing deep generative recommendation approaches, CAF is more effective in estimating the probabilistic posterior and achieves better recommendation accuracy. We conducted extensive experimental evaluations demonstrating that CAF can capture more effective representation of latent factors, resulting in a substantial gain on recommendation compared to the state-of-the-art approaches.

Conditional MaxRS Query for Evolving Spatial Data.

We address the problem of maintaining the correct answer-sets to a novel query-Conditional Maximizing Range-Sum (C-MaxRS)-for spatial data. Given a set of 2D point objects, possibly with associated weights, the traditional MaxRS problem determines an optimal placement for an axes-parallel rectangle r so that the number-or, the weighted sum-of the objects in its interior is maximized. The peculiarities of C-MaxRS is that in many practical settings, the objects from a particular set-e.g., restaurants-can be of different types-e.g., fast-food, Asian, etc. The C-MaxRS problem deals with maximizing the overall sum-however, it also incorporates class-based constraints, i.e., placement of r such that a lower bound on the count/weighted-sum of objects of interests from particular classes is ensured. We first propose an efficient algorithm to handle the static C-MaxRS query and then extend the solution to handle dynamic settings, where new data may be inserted or some of the existing data deleted. Subsequently we focus on the specific case of bulk-updates, which is common in many applications-i.e., multiple data points being simultaneously inserted or deleted. We show that dealing with events one by one is not efficient when processing bulk updates and present a novel technique to cater to such scenarios, by creating an index over the bursty data on-the-fly and processing the collection of events in an aggregate manner. Our experiments over datasets of up to 100,000 objects show that the proposed solutions provide significant efficiency benefits over the naïve approaches.