no code implementations • 14 Feb 2024 • Shubham Gupta, Srikanta Bedathur
Training of these TGNNs is enumerated by uniform random sampling based unsupervised loss.
no code implementations • 21 Dec 2023 • Nishtha Madaan, Srikanta Bedathur
Generating counterfactual explanations is one of the most effective approaches for uncovering the inner workings of black-box neural network models and building user trust.
no code implementations • 13 Jul 2023 • Vinayak Gupta, Srikanta Bedathur, Abir De
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.
no code implementations • 13 Jul 2023 • Vinayak Gupta, Srikanta Bedathur
We demonstrate that this variant can learn the order in which the person or actor prefers to do their actions.
no code implementations • 6 Jun 2023 • Shubham Gupta, Sahil Manchanda, Sayan Ranu, Srikanta Bedathur
In this work, we address these limitations through a novel GNN framework called GRAFENNE.
1 code implementation • 6 Jun 2023 • Sahil Manchanda, Shubham Gupta, Sayan Ranu, Srikanta Bedathur
Despite their initial success, these techniques, like much of the existing deep generative methods, require a large number of training samples to learn a good model.
no code implementations • 23 Feb 2023 • Rajat Singh, Srikanta Bedathur
The classical learning phase consists of the models such as SVMs, linear and logistic regression, and tree-based methods.
no code implementations • 3 Nov 2022 • Nishtha Madaan, Adithya Manjunatha, Hrithik Nambiar, Aviral Kumar Goel, Harivansh Kumar, Diptikalyan Saha, Srikanta Bedathur
The goal of this work is to ensure that machine learning and deep learning-based systems are as trusted as traditional software.
no code implementations • 29 Aug 2022 • Vinayak Gupta, Srikanta Bedathur
In this paper, we present REVAMP, a sequential POI recommendation approach that utilizes the user activity on smartphone applications (or apps) to identify their mobility preferences.
no code implementations • 25 Aug 2022 • Shubham Gupta, Srikanta Bedathur
Temporal graphs represent the dynamic relationships among entities and occur in many real life application like social networks, e commerce, communication, road networks, biological systems, and many more.
1 code implementation • 23 Jun 2022 • Vinayak Gupta, Srikanta Bedathur, Sourangshu Bhattacharya, Abir De
In this work, we provide a novel unsupervised model and inference method for learning MTPP in presence of event sequences with missing events.
no code implementations • 21 Jun 2022 • Nishtha Madaan, Srikanta Bedathur, Diptikalyan Saha
We also show that the generated counterfactuals from CASPer can be used for augmenting the training data and thereby fixing and making the test model more robust.
no code implementations • 16 Jun 2022 • Nishtha Madaan, Prateek Chaudhury, Nishant Kumar, Srikanta Bedathur
In experiments, we compare with existing methods and show that our model makes significantly more accurate predictions of the word embedding than the baselines.
1 code implementation • 10 Jun 2022 • Vinayak Gupta, Srikanta Bedathur
In this paper, we present ProActive, a neural marked temporal point process (MTPP) 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.
1 code implementation • 7 Mar 2022 • Shubham Gupta, Sahil Manchanda, Srikanta Bedathur, Sayan Ranu
There has been a recent surge in learning generative models for graphs.
1 code implementation • 17 Feb 2022 • Vinayak Gupta, Srikanta Bedathur, Abir De
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.
no code implementations • 16 Jan 2022 • 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.
no code implementations • 7 Nov 2021 • Ritvik Vij, Rohit Raj, Madhur Singhal, Manish Tanwar, Srikanta Bedathur
In this paper, we present VizAI, a generative-discriminative framework that first generates various statistical properties of the data from a number of alternative visualizations of the data.
1 code implementation • 13 Sep 2021 • Vinayak Gupta, Srikanta Bedathur
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.
no code implementations • 30 Apr 2021 • Siddhant Arora, Vinayak Gupta, Garima Gaur, Srikanta Bedathur
In this paper, we address the problem of learning low dimension representation of entities on relational databases consisting of multiple tables.
no code implementations • 15 Apr 2021 • Saransh Goyal, Pratyush Pandey, Garima Gaur, Subhalingam D, Srikanta Bedathur, Maya Ramanath
We introduce TechTrack, a new dataset for tracking entities in technical procedures.
no code implementations • 29 Nov 2020 • Arindam Bhattacharya, Sumanth Varambally, Amitabha Bagchi, Srikanta Bedathur
We present Fast Random projection-based One-Class Classification (FROCC), an extremely efficient method for one-class classification.
no code implementations • 29 Sep 2020 • Pawan Kumar, Srikanta Bedathur
In section 3 we will consider systems that uses formal languages e. g. $\lambda$-calculus (Steedman, 1996), $\lambda$-DCS (Liang, 2013).
no code implementations • AKBC 2020 • Siddhant Arora, Srikanta Bedathur, Maya Ramanath, Deepak Sharma
Knowledge Graphs (KGs) extracted from text sources are often noisy and lead to poor performance in downstream application tasks such as KG-based question answering. While much of the recent activity is focused on addressing the sparsity of KGs by using embeddings for inferring new facts, the issue of cleaning up of noise in KGs through KG refinement task is not as actively studied.
no code implementations • 13 May 2020 • Siddhant Arora, Srikanta Bedathur
We address the problem of learning a distributed representation of entities in a relational database using a low-dimensional embedding.
1 code implementation • AKBC 2021 • Vaibhav Adlakha, Parth Shah, Srikanta Bedathur, Mausam
In response, we develop RotatE-Box -- a novel combination of RotatE and box embeddings.
no code implementations • 29 Jan 2020 • Prajna Upadhyay, Srikanta Bedathur, Tanmoy Chakraborty, Maya Ramanath
Often, the user is also aware of the "aspect" to retrieve a relevant document.
no code implementations • 12 Sep 2018 • Srikanta Bedathur, Indrajit Bhattacharya, Jayesh Choudhari, Anirban Dasgupta
We show using experiments on real and semi-synthetic data that HMHP is able to generalize better and recover the network strengths, topics and diffusion paths more accurately than state-of-the-art baselines.
no code implementations • 30 Jan 2018 • Aayushee Gupta, Haimonti Dutta, Srikanta Bedathur, Lipika Dey
Prosopography is an investigation of the common characteristics of a group of people in history, by a collective study of their lives.
no code implementations • 14 Nov 2017 • Rema Ananthanarayanan, Pranay Kr. Lohia, Srikanta Bedathur
Selecting the appropriate visual presentation of the data such that it preserves the semantics of the underlying data and at the same time provides an intuitive summary of the data is an important, often the final step of data analytics.