no code implementations • 27 Apr 2024 • Tony Gracious, Ambedkar Dukkipati
This is done using a dynamic graph representation learning framework that can capture complex relationships involving multiple entities.
1 code implementation • 29 Sep 2023 • Parag Dutta, Kawin Mayilvaghanan, Pratyaksha Sinha, Ambedkar Dukkipati
To the best of our knowledge, this is the first work that solves the problem of predicting event set intensities in the continuous time domain by using TPPs.
no code implementations • 25 May 2023 • Ranga Shaarad Ayyagari, Ambedkar Dukkipati
Most reinforcement learning algorithms treat the context under which they operate as a stationary, isolated and undisturbed environment.
no code implementations • 28 Jan 2023 • Tony Gracious, Arman Gupta, Ambedkar Dukkipati
We believe that this is the first work that solves the problem of forecasting higher-order directional interactions.
no code implementations • 3 Mar 2022 • Shubham Gupta, Ambedkar Dukkipati
Our work leads to an interesting stochastic block model that not only plants the given partitions in $\mathcal{G}$ but also plants the auxiliary information encoded in the representation graph $\mathcal{R}$.
no code implementations • 21 Dec 2021 • Aayushee Gupta, K. M. Annervaz, Ambedkar Dukkipati, Shubhashis Sengupta
The query conversion models and direct models both require specific training data pertaining to the domain of the knowledge graph.
no code implementations • 19 Dec 2021 • Tony Gracious, Ambedkar Dukkipati
As far as our knowledge, this is the first work that uses the temporal point process to forecast hyperedges in dynamic networks.
no code implementations • 2 Dec 2021 • Shaarad Ayyagari, Ambedkar Dukkipati
In this paper, we study the stochastic combinatorial multi-armed bandit problem under semi-bandit feedback.
no code implementations • 8 Sep 2021 • Ambedkar Dukkipati, Tony Gracious, Shubham Gupta
Lockdowns are one of the most effective measures for containing the spread of a pandemic.
no code implementations • 8 May 2021 • Shubham Gupta, Ambedkar Dukkipati
This graph specifies node pairs that can represent each other with respect to sensitive attributes and is observed in addition to the usual \textit{similarity graph}.
no code implementations • NAACL 2021 • Rishi Hazra, Parag Dutta, Shubham Gupta, Mohammed Abdul Qaathir, Ambedkar Dukkipati
We empirically demonstrate that the proposed approach is further able to reduce the data requirements of state-of-the-art AL strategies by an absolute percentage reduction of $\approx\mathbf{3-25\%}$ on multiple NLP tasks while achieving the same performance with no additional computation overhead.
no code implementations • 30 Jan 2021 • Ambedkar Dukkipati, Rajarshi Banerjee, Ranga Shaarad Ayyagari, Dhaval Parmar Udaybhai
We demonstrate the utility of our approach on navigation and goal-based tasks in a flexible simulated 3D navigation environment that we have developed.
Autonomous Navigation Hierarchical Reinforcement Learning +2
no code implementations • 24 Dec 2020 • Shaarad A. R, Ambedkar Dukkipati
The multi-armed bandits' framework is the most common platform to study strategies for sequential decision-making problems.
no code implementations • 5 Nov 2020 • Tony Gracious, Ambedkar Dukkipati
In this paper we propose an approach that achieves both modality fusion and the capability to learn embeddings of unseen nodes.
no code implementations • 25 May 2020 • Sourabh Balgi, Ambedkar Dukkipati
To address this, we follow Vapnik's imperative of statistical learning that states any desired problem should be solved in the most direct way rather than solving a more general intermediate task and propose a direct approach to domain adaptation that does not require domain alignment.
no code implementations • 6 Apr 2020 • Shubham Gupta, Rishi Hazra, Ambedkar Dukkipati
One way to coordinate is by learning to communicate with each other.
Multi-agent Reinforcement Learning reinforcement-learning +1
no code implementations • 26 Nov 2019 • Tony Gracious, Shubham Gupta, Arun Kanthali, Rui M. Castro, Ambedkar Dukkipati
These techniques are different for homogeneous and heterogeneous networks because heterogeneous networks can have multiple types of edges and nodes as opposed to a homogeneous network.
no code implementations • 11 Nov 2019 • Shubham Gupta, Gururaj K., Ambedkar Dukkipati, Rui M. Castro
Networks with node covariates offer two advantages to community detection methods, namely, (i) exploit covariates to improve the quality of communities, and more importantly, (ii) explain the discovered communities by identifying the relative importance of different covariates in them.
1 code implementation • 1 Nov 2019 • Rishi Hazra, Parag Dutta, Shubham Gupta, Mohammed Abdul Qaathir, Ambedkar Dukkipati
We empirically demonstrate that the proposed approach is further able to reduce the data requirements of state-of-the-art AL strategies by $\approx \mathbf{3-25\%}$ on an absolute scale on multiple NLP tasks while achieving the same performance with virtually no additional computation overhead.
no code implementations • 25 Sep 2019 • Shubham Gupta, Ambedkar Dukkipati
In this paper, we pose the problem of multi-agent reinforcement learning as the problem of performing inference in a particular graphical model.
Multi-agent Reinforcement Learning reinforcement-learning +2
1 code implementation • 8 Sep 2019 • Sourabh Balgi, Ambedkar Dukkipati
In this paper, we propose a simple model referred as Contradistinguisher (CTDR) for unsupervised domain adaptation whose objective is to jointly learn to contradistinguish on unlabeled target domain in a fully unsupervised manner along with prior knowledge acquired by supervised learning on an entirely different domain.
no code implementations • 19 Feb 2019 • Shubham Gupta, Ambedkar Dukkipati
To the best of our knowledge, we are the first to explore emergence of communication for discovering and implementing strategies in a setting where agents communicate over a network.
no code implementations • 17 Nov 2018 • Rohith AP, Ambedkar Dukkipati, Gaurav Pandey
In contrast, we propose an approach that directly addresses the problem of learning a classifier in the unlabeled target domain.
no code implementations • WS 2019 • Somnath Basu Roy Chowdhury, K. M. Annervaz, Ambedkar Dukkipati
With our proposed cross dataset learning procedure we show that one can achieve competitive/better performance than learning from a single dataset.
no code implementations • NAACL 2018 • K. M. Annervaz, Somnath Basu Roy Chowdhury, Ambedkar Dukkipati
In this work, we propose to enhance learning models with world knowledge in the form of Knowledge Graph (KG) fact triples for Natural Language Processing (NLP) tasks.
no code implementations • 11 Feb 2018 • Shubham Gupta, Gaurav Sharma, Ambedkar Dukkipati
Networks observed in real world like social networks, collaboration networks etc., exhibit temporal dynamics, i. e. nodes and edges appear and/or disappear over time.
1 code implementation • 3 Sep 2017 • Gaurav Pandey, Ambedkar Dukkipati
How can one use the same discriminative models for learning useful features in the absence of labels?
no code implementations • 3 May 2017 • Gaurav Pandey, Ambedkar Dukkipati
In this paper, we propose a model that generates auxiliary labels for each image, while simultaneously forcing the output of the CNN to satisfy the mean-field constraints imposed by a conditional random field.
no code implementations • 23 Mar 2017 • Akshay Mehrotra, Ambedkar Dukkipati
Towards overcoming that, we propose a network design inspired by deep residual networks that allows the efficient computation of this more expressive pairwise similarity objective.
1 code implementation • ICML 2017 • Pranav Shyam, Shubham Gupta, Ambedkar Dukkipati
Rapid learning requires flexible representations to quickly adopt to new evidence.
no code implementations • 12 Feb 2017 • Muni Sreenivas Pydi, Ambedkar Dukkipati
Spectral clustering is one of the most popular methods for community detection in graphs.
no code implementations • 24 Jan 2017 • Gaurav Pandey, Ambedkar Dukkipati
We propose a neural network based approach for learning topics from text and image datasets.
no code implementations • 17 Jan 2017 • Mahesh Gorijala, Ambedkar Dukkipati
We evaluate our model on Labeled Faces in the Wild (LFW), celebA and a modified version of MNIST datasets and demonstrate the ability of our model to generate new images as well as to modify a given image by changing attributes.
no code implementations • 16 Nov 2016 • Siddharth Agrawal, Ambedkar Dukkipati
Variational autoencoders (VAEs), that are built upon deep neural networks have emerged as popular generative models in computer vision.
no code implementations • 15 Nov 2016 • Biswajit Paria, K. M. Annervaz, Ambedkar Dukkipati, Ankush Chatterjee, Sanjay Podder
In this work we use the recent advances in representation learning to propose a neural architecture for the problem of natural language inference.
no code implementations • 6 Mar 2016 • Gaurav Pandey, Ambedkar Dukkipati
We use the proposed model to generate faces from attributes.
no code implementations • 21 Feb 2016 • Debarghya Ghoshdastidar, Ambedkar Dukkipati
This work is motivated by two issues that arise when a hypergraph partitioning approach is used to tackle computer vision problems: (i) The uniform hypergraphs constructed for higher-order learning contain all edges, but most have negligible weights.
no code implementations • 6 Sep 2015 • Gaurav Pandey, Ambedkar Dukkipati
The aim of the paper is to provide an exact approach for generating a Poisson process sampled from a hierarchical CRM, without having to instantiate the infinitely many atoms of the random measures.
no code implementations • 7 May 2015 • Debarghya Ghoshdastidar, Ambedkar Dukkipati
Hypergraph partitioning lies at the heart of a number of problems in machine learning and network sciences.
no code implementations • NeurIPS 2014 • Debarghya Ghoshdastidar, Ambedkar Dukkipati
Spectral graph partitioning methods have received significant attention from both practitioners and theorists in computer science.
no code implementations • CVPR 2014 • Debarghya Ghoshdastidar, Ambedkar Dukkipati, Ajay P. Adsul, Aparna S. Vijayan
Motivated by multi-distribution divergences, which originate in information theory, we propose a notion of `multi-point' kernels, and study their applications.
no code implementations • 23 Feb 2014 • Gaurav Pandey, Ambedkar Dukkipati
To achieve acceptable performance for AI tasks, one can either use sophisticated feature extraction methods as the first layer in a two-layered supervised learning model, or learn the features directly using a deep (multi-layered) model.
no code implementations • 21 Jun 2012 • Debarghya Ghoshdastidar, Ambedkar Dukkipati, Shalabh Bhatnagar
This motivates us to study SF schemes for gradient estimation using the q-Gaussian distribution.
no code implementations • 3 May 2012 • Ambedkar Dukkipati, Gaurav Pandey, Debarghya Ghoshdastidar, Paramita Koley, D. M. V. Satya Sriram
In this paper, we introduce a maximum entropy classification method with feature selection for large dimensional data such as text datasets that is generative in nature.
no code implementations • 9 Apr 2012 • Debarghya Ghoshdastidar, Ambedkar Dukkipati
Motivated by the importance of power-law distributions in statistical modeling, in this paper, we propose the notion of power-law kernels to investigate power-laws in learning problem.