Modeling Implicit Communities from Geo-Tagged Event Traces Using Spatio-Temporal Point Processes

Likhyani, Ankita; Gupta, Vinayak; Srijith, P. K.; Deepak, P; Bedathur, Srikanta

doi:10.1007/978-3-030-62005-9_12

Cited by 13 publications

(10 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, these approaches are limited by the underlying datasets as it excludes two critical aspects of a mobility network; the social friendships and location categories. The social network is used to model the influence dynamics across different users [41,45] and the POI categories capture the different preferences of an individual [9,42]. We utilize user POI social networks for our model as these datasets provide both: a series of social dynamics for different users and location-specific interest patterns for a user.…”

Section: Related Workmentioning

confidence: 99%

Doing More with Less: Overcoming Data Scarcity for POI Recommendation via Cross-Region Transfer

Gupta

Bedathur

2022

ACM Trans. Intell. Syst. Technol.

Self Cite

View full text Add to dashboard Cite

Variability in social app usage across regions results in a high skew of the quantity and the quality of check-in data collected, which in turn is a challenge for effective location recommender systems. In this paper, we present Axolotl (Automated cross Location-network Transfer Learning), a novel method aimed at transferring location preference models learned in a data-rich region to significantly boost the quality of recommendations in a data-scarce region. Axolotl predominantly deploys two channels for information transfer, (1) a meta-learning based procedure learned using location recommendation as well as social predictions, and (2) a lightweight unsupervised cluster-based transfer across users and locations with similar preferences. Both of these work together synergistically to achieve improved accuracy of recommendations in data-scarce regions without any prerequisite of overlapping users and with minimal fine-tuning. We build Axolotl on top of a twin graph-attention neural network model used for capturing the user- and location-conditioned influences in a user-mobility graph for each region. We conduct extensive experiments on 12 user mobility datasets across the U.S., Japan, and Germany, using 3 as source regions and 9 of them (that have much sparsely recorded mobility data) as target regions. Empirically, we show that Axolotl achieves up to 18% better recommendation performance than the existing state-of-the-art methods across all metrics.

show abstract

Section: Related Workmentioning

confidence: 99%

Doing More with Less: Overcoming Data Scarcity for POI Recommendation via Cross-Region Transfer

Gupta

Bedathur

2022

ACM Trans. Intell. Syst. Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Another approach [13] is a generic model for predicting user trajectories as well as next product recommendation. Recent approaches for checkin time prediction are limited to a single dataset [5,19,37]. They also model event-times as random variables rather than sequential flows and thus cannot be used for transfer across regions.…”

Section: Related Workmentioning

confidence: 99%

“…In recent years, Marked Temporal Point Processes(MTPP) have outperformed other neural architectures for characterizing asynchronous events localized in continuous time and are even used in a wide range of applications, including healthcare [29], finance [1,39], and social networks [15,23,40]. Recent works that deploy MTPP for predicting user mobility patterns are either: (i) limited to predicting the time of user-location interactions rather than actual locations [37], (ii) restricted to one dataset without a foreseeable way to easily utilize external information [19], or (iii) disregard the opportunity to reuse trained parameters from external datasets by jointly embedding the checkin and time distributions [5]. Thus, none of these approaches can be used for designing mobility prediction models for limited data regions.…”

mentioning

confidence: 99%

Region Invariant Normalizing Flows for Mobility Transfer

Gupta

Bedathur

2021

Proceedings of the 30th ACM International Conference on Information &Amp; Knowledge Management

Self Cite

View full text Add to dashboard Cite

There exists a high variability in mobility data volumes across different regions, which deteriorates the performance of spatial recommender systems that rely on region-specific data. In this paper, we propose a novel transfer learning framework called Reformd, for continuous-time location prediction for regions with sparse checkin data. Specifically, we model user-specific checkin-sequences in a region using a marked temporal point process (MTPP) with normalizing flows to learn the inter-checkin time and geo-distributions. Later, we transfer the model parameters of spatial and temporal flows trained on a data-rich origin region for the next check-in and time prediction in a target region with scarce checkin data. We capture the evolving region-specific checkin dynamics for MTPP and spatial-temporal flows by maximizing the joint likelihood of next checkin with three channels (1) checkin-category prediction, (2) checkin-time prediction, and (3) travel distance prediction. Extensive experiments on different user mobility datasets across the U.S. and Japan show that our model significantly outperforms stateof-the-art methods for modeling continuous-time sequences. Moreover, we also show that Reformd can be easily adapted for product recommendations i.e., sequences without any spatial component. CCS CONCEPTS• Information systems → Location based services.

show abstract

“…Learning the dynamics of CTES is a non-trivial task with the neural models as it requires perpetual modeling of continuous-time and inter-event relationships [4,9,18]. Recent developments to marked temporal point processes (MTPP) [2,14] have shown an outstanding potential to characterize asynchronous events localized in continuous time that appear in a wide range of applications in healthcare [13], spatial networks [4,7,10], web and social networks [3,5,6,9], finance [1] and many more. However, modern MTPP models are limited to settings where the training data is completely observed i.e.…”

Section: Motivation and Related Workmentioning

confidence: 99%

A Neural Approach for Modeling Continuous Time Sequences with Intermittent Observations

Gupta¹,

Bedathur²

2021

Preprint

Self Cite

View full text Add to dashboard Cite

A large fraction of data generated via human activities such as online purchases, health records, spatial mobility etc. can be represented as continuous-time event sequences (CTES) i.e. sequences of discrete events over a continuous time. Learning neural models over CTES is a non-trivial task as it involves modeling the ever-increasing event timestamps, inter-event time gaps, event types, and the influences between different events within and across different sequences. Moreover, existing sequence modeling techniques consider a complete observation scenario i.e. the event sequence being modeled is completely observed with no missing events – an ideal setting that is rarely applicable in real-world applications. In this paper, we highlight our approach[8] for modeling CTES with intermittent observations. Buoyed by the recent success of neural marked temporal point processes (MTPP) for modeling the generative distribution of CTES, we provide a novel unsupervised model and inference method for learning MTPP in presence of event sequences with missing events. Specifically, we first model the generative processes of observed events and missing events using two MTPP, where the missing events are represented as latent random variables. Then, we devise an unsupervised training method that jointly learns both the MTPP using variational inference. Experiments across real-world datasets show that our modeling framework outperforms state-of-the-art techniques for future event prediction and imputation. This work appeared in AISTATS 2021.

show abstract

Modeling Implicit Communities from Geo-Tagged Event Traces Using Spatio-Temporal Point Processes

Cited by 13 publications

References 33 publications

Doing More with Less: Overcoming Data Scarcity for POI Recommendation via Cross-Region Transfer

Doing More with Less: Overcoming Data Scarcity for POI Recommendation via Cross-Region Transfer

Region Invariant Normalizing Flows for Mobility Transfer

A Neural Approach for Modeling Continuous Time Sequences with Intermittent Observations

Contact Info

Product

Resources

About