Author name cluster

Srikanta Bedathur

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

9 papers

1 author row

AAAI Conference 2026 Conference Paper

Kernelized Edge Attention: Addressing Semantic Attention Blurring in Temporal Graph Neural Networks

Govind Waghmare
Srini Rohan Gujulla Leel
Nikhil Tumbde
Sumedh B G
Sonia Gupta
Srikanta Bedathur

Temporal Graph Neural Networks (TGNNs) aim to capture the evolving structure and timing of interactions in dynamic graphs. Although many models incorporate time through encodings or architectural design, they often compute attention over entangled node and edge representations, failing to reflect their distinct temporal behaviors. Node embeddings evolve slowly as they aggregate long-term structural context, while edge features reflect transient, timestamped interactions (e.g. messages, trades, or transactions). This mismatch results in semantic attention blurring, where attention weights cannot distinguish between slowly drifting node states and rapidly changing, information-rich edge interactions. As a result, models struggle to capture fine-grained temporal dependencies and provide limited transparency into how temporal relevance is computed. This paper introduces KEAT (Kernelized Edge Attention for Temporal Graphs), a novel attention formulation that modulates edge features using a family of continuous-time kernels, including Laplacian, RBF, and learnable MLP variant. KEAT preserves the distinct roles of nodes and edges, and integrates seamlessly with both Transformer-style (e.g., DyGFormer) and message-passing (e.g., TGN) architectures. It achieves up to 18% MRR improvement over the recent DyGFormer and 7% over TGN on link prediction tasks, enabling more accurate, interpretable and temporally aware message passing in TGNNs.

PDF Details DOI

TIST Journal 2025 Journal Article

Retrieving Continuous-Time Event Sequences Using Neural Temporal Point Processes with Learnable Hashing

Vinayak Gupta
Srikanta Bedathur
Abir De

Temporal sequences have become pervasive in various real-world applications such as finance, spatial mobility, health records, and so on. Consequently, the volume of data generated in the form of continuous-time event sequence(s) or CTES(s) has increased exponentially in the past few years. Thus, a significant fraction of the ongoing research on CTES datasets involves designing models to address downstream tasks such as next-event prediction, long-term forecasting, sequence classification, and so on. The recent developments in predictive modeling using marked temporal point processes (MTPP) have enabled an accurate characterization of several real-world applications involving the CTESs. However, due to the complex nature of these CTES datasets, the task of large-scale retrieval of temporal sequences has been overlooked by the past literature. In detail, by CTES retrieval we mean that for an input query sequence, a retrieval system must return a ranked list of relevant sequences from a large corpus. To tackle this, we propose NeuroSeqRet, a first-of-its-kind framework designed specifically for end-to-end CTES retrieval. Specifically, NeuroSeqRet introduces multiple enhancements over standard retrieval frameworks and first applies a trainable unwarping function on the query sequence which makes it comparable with corpus sequences, especially when a relevant query-corpus pair has individually different attributes. Next, it feeds the unwarped query sequence and the corpus sequence into MTPP-guided neural relevance models. We develop four variants of the relevance model for different kinds of applications based on the tradeoff between accuracy and efficiency. We also propose an optimization framework to learn binary sequence embeddings from the relevance scores, suitable for the locality-sensitive hashing leading to a significant speedup in returning top- K results for a given query sequence. Our experiments with several datasets show the significant accuracy boost of NeuroSeqRet beyond several baselines, as well as the efficacy of our hashing mechanism.

Details DOI

TIST Journal 2024 Journal Article

Tapestry of Time and Actions: Modeling Human Activity Sequences Using Temporal Point Process Flows

Vinayak Gupta
Srikanta Bedathur

Human beings always engage in a vast range of activities and tasks that demonstrate their ability to adapt to different scenarios. These activities can range from the simplest daily routines, like walking and sitting, to multi-level complex endeavors such as cooking a four-course meal. Any human activity can be represented as a temporal sequence of actions performed to achieve a certain goal. Unlike the time series datasets extracted from electronics or machines, these action sequences are highly disparate in their nature—the time to finish a sequence of actions can vary between different persons. Therefore, understanding the dynamics of these sequences is essential for many downstream tasks such as activity length prediction, goal prediction, and next action recommendation. Existing neural network based approaches that learn a continuous-time activity sequence are limited to the presence of only visual data or are designed specifically for a particular task (i.e., limited to next action or goal prediction). In this article, we present ProActive, a neural marked temporal point process framework for modeling the continuous-time distribution of actions in an activity sequence while simultaneously addressing three high-impact problems: next action prediction, sequence goal prediction, and end-to-end sequence generation. Specifically, we utilize a self-attention module with temporal normalizing flows to model the influence and the inter-arrival times between actions in a sequence. Moreover, for time-sensitive prediction, we perform an early detection of sequence goal via a constrained margin-based optimization procedure. This in turn allows ProActive to predict the sequence goal using a limited number of actions. In addition, we propose a novel addition over the ProActive model, called ProActive++, that can handle variations in the order of actions (i.e., different methods of achieving a given goal). We demonstrate that this variant can learn the order in which the person or actor prefers to do their actions. Extensive experiments on sequences derived from three activity recognition datasets show the significant accuracy boost of our ProActive and ProActive++ over the state of the art in terms of action and goal prediction, and the first-ever application of end-to-end action sequence generation.

Details DOI

TIST Journal 2022 Journal Article

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

Vinayak Gupta
Srikanta Bedathur

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 article, 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 US, Japan, and Germany, using three as source regions and nine 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.

Details DOI

AAAI Conference 2022 Conference Paper

Learning Temporal Point Processes for Efficient Retrieval of Continuous Time Event Sequences

Vinayak Gupta
Srikanta Bedathur
Abir De

Recent developments in predictive modeling using marked temporal point processes (MTPP) have enabled an accurate characterization of several real-world applications involving continuous-time event sequences (CTESs). However, the retrieval problem of such sequences remains largely unaddressed in literature. To tackle this, we propose NEUROSEQRET which learns to retrieve and rank a relevant set of continuous-time event sequences for a given query sequence, from a large corpus of sequences. More specifically, NEUROSEQRET first applies a trainable unwarping function on the query sequence, which makes it comparable with corpus sequences, especially when a relevant query-corpus pair has individually different attributes. Next, it feeds the unwarped query sequence and the corpus sequence into MTPP guided neural relevance models. We develop two variants of the relevance model which offer a tradeoff between accuracy and efficiency. We also propose an optimization framework to learn binary sequence embeddings from the relevance scores, suitable for the locality-sensitive hashing leading to a significant speedup in returning top-K results for a given query sequence. Our experiments with several datasets show the significant accuracy boost of NEUROSE- QRET beyond several baselines, as well as the efficacy of our hashing mechanism.

PDF Details

TIST Journal 2022 Journal Article

Modeling Continuous Time Sequences with Intermittent Observations using Marked Temporal Point Processes

Vinayak Gupta
Srikanta Bedathur
Sourangshu Bhattacharya
Abir De

A large fraction of data generated via human activities such as online purchases, health records, spatial mobility, etc. can be represented as a sequence of events over a continuous-time. Learning deep learning models over these continuous-time event sequences 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. In recent years, neural enhancements to marked temporal point processes (MTPP) have emerged as a powerful framework to model the underlying generative mechanism of asynchronous events localized in continuous time. However, most existing models and inference methods in the MTPP framework consider only the 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. A recent line of work which considers missing events while training MTPP utilizes supervised learning techniques that require additional knowledge of missing or observed label for each event in a sequence, which further restricts its practicability as in several scenarios the details of missing events is not known a priori. In this work, 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 by means of variational inference. Such a formulation can effectively impute the missing data among the observed events, which in turn enhances its predictive prowess, and can identify the optimal position of missing events in a sequence. Experiments with eight real-world datasets show that IMTPP outperforms the state-of-the-art MTPP frameworks for event prediction and missing data imputation, and provides stable optimization.

Details DOI

AAAI Conference 2022 Conference Paper

TIGGER: Scalable Generative Modelling for Temporal Interaction Graphs

Shubham Gupta
Sahil Manchanda
Srikanta Bedathur
Sayan Ranu

There has been a recent surge in learning generative models for graphs. While impressive progress has been made on static graphs, work on generative modeling of temporal graphs is at a nascent stage with significant scope for improvement. First, existing generative models do not scale with either the time horizon or the number of nodes. Second, existing techniques are transductive in nature and thus do not facilitate knowledge transfer. Finally, due to their reliance on oneto-one node mapping from source to the generated graph, existing models leak node identity information and do not allow up-scaling/down-scaling the source graph size. In this paper, we bridge these gaps with a novel generative model called TIGGER. TIGGER derives its power through a combination of temporal point processes with auto-regressive modeling enabling both transductive and inductive variants. Through extensive experiments on real datasets, we establish TIGGER generates graphs of superior fidelity, while also being up to 3 orders of magnitude faster than the state-of-the-art.

PDF Details

TIST Journal 2019 Journal Article

Location-Specific Influence Quantification in Location-Based Social Networks

Ankita Likhyani
Srikanta Bedathur
Deepak P.

Location-based social networks (LBSNs) such as Foursquare offer a platform for users to share and be aware of each other’s physical movements. As a result of such a sharing of check-in information with each other, users can be influenced to visit (or check-in) at the locations visited by their friends. Quantifying such influences in these LBSNs is useful in various settings such as location promotion, personalized recommendations, mobility pattern prediction, and so forth. In this article, we develop a model to quantify the influence specific to a location between a pair of users. Specifically, we develop a framework called LoCaTe, that combines (a) a user mobility model based on kernel density estimates; (b) a model of the semantics of the location using topic models; and (c) a user correlation model that uses an exponential distribution. We further develop LoCaTe+, an advanced model within the same framework where user correlation is quantified using a Mutually Exciting Hawkes Process. We show the applicability of LoCaTe and LoCaTe+ for location promotion and location recommendation tasks using LBSNs. Our models are validated using a long-term crawl of Foursquare data collected between January 2015 and February 2016, as well as other publicly available LBSN datasets. Our experiments demonstrate the efficacy of the LoCaTe framework in capturing location-specific influence between users. We also show that our models improve over state-of-the-art models for the task of location promotion as well as location recommendation.

Details DOI

IJCAI Conference 2017 Conference Paper

LoCaTe: Influence Quantification for Location Promotion in Location-based Social Networks

Ankita Likhyani
Srikanta Bedathur
Deepak P

Location-based social networks (LBSNs) such as Foursquare offer a platform for users to share and be aware of each other’s physical movements. As a result of such a sharing of check-in information with each other, users can be influenced to visit (or check-in) at the locations visited by their friends. Quantifying such influences in these LBSNs is useful in various settings such as location promotion, personalized recommendations, mobility pattern prediction etc. In this paper, we focus on the problem of location promotion and develop a model to quantify the influence specific to a location between a pair of users. Specifically, we develop a joint model called LoCaTe, consisting of (i) user mobility model estimated using kernel density estimates; (ii) a model of the semantics of the location using topic models; and (iii) a model of time-gap between check-ins using exponential distribution. We validate our model on a long-term crawl of Foursquare data collected between Jan 2015 Feb 2016, as well as on publicly available LBSN datasets. Our experiments demonstrate that LoCaTe significantly outperforms state-of-the-art models for the same task.

PDF Details