Search Results for author: Ambedkar Dukkipati

Found 45 papers, 5 papers with code

Interaction Event Forecasting in Multi-Relational Recursive HyperGraphs: A Temporal Point Process Approach

no code implementations27 Apr 2024 Tony Gracious, Ambedkar Dukkipati

This is done using a dynamic graph representation learning framework that can capture complex relationships involving multiple entities.

Decoder Graph Representation Learning +1

Deep Representation Learning for Prediction of Temporal Event Sets in the Continuous Time Domain

1 code implementation29 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.

Computational Efficiency Point Processes +1

Markov Decision Process with an External Temporal Process

no code implementations25 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.


Neural Temporal Point Process for Forecasting Higher Order and Directional Interactions

no code implementations28 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.

On consistency of constrained spectral clustering under representation-aware stochastic block model

no code implementations3 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 $\mathcal{R}$.

Clustering Computational Efficiency +1

An Inference Approach To Question Answering Over Knowledge Graphs

no code implementations21 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.

Knowledge Graphs Question Answering

Dynamic Representation Learning with Temporal Point Processes for Higher-Order Interaction Forecasting

no code implementations19 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.

Hyperedge Prediction Point Processes +1

Risk-Aware Algorithms for Combinatorial Semi-Bandits

no code implementations2 Dec 2021 Shaarad Ayyagari, Ambedkar Dukkipati

In this paper, we study the stochastic combinatorial multi-armed bandit problem under semi-bandit feedback.

Consistency of Constrained Spectral Clustering under Graph Induced Fair Planted Partitions

no code implementations8 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}.

Attribute Clustering +3

Active$^2$ Learning: Actively reducing redundancies in Active Learning methods for Sequence Tagging and Machine Translation

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.

Active Learning Machine Translation +1

A Regret bound for Non-stationary Multi-Armed Bandits with Fairness Constraints

no code implementations24 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.

Decision Making Fairness +1

Adversarial Context Aware Network Embeddings for Textual Networks

no code implementations5 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.

Node Classification Representation Learning

Contradistinguisher: A Vapnik's Imperative to Unsupervised Domain Adaptation

no code implementations25 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.

Unsupervised Domain Adaptation

Neural Latent Space Model for Dynamic Networks and Temporal Knowledge Graphs

no code implementations26 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.

Knowledge Graphs Representation Learning +1

Equipping SBMs with RBMs: An Explainable Approach for Analysis of Networks with Covariates

no code implementations11 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.

Community Detection Link Prediction

Active$^2$ Learning: Actively reducing redundancies in Active Learning methods for Sequence Tagging and Machine Translation

1 code implementation1 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.

Active Learning Machine Translation +1

Probabilistic View of Multi-agent Reinforcement Learning: A Unified Approach

no code implementations25 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

CUDA: Contradistinguisher for Unsupervised Domain Adaptation

1 code implementation8 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.

domain classification Unsupervised Domain Adaptation

Winning an Election: On Emergent Strategic Communication in Multi-Agent Networks

no code implementations19 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.

Deep Discriminative Learning for Unsupervised Domain Adaptation

no code implementations17 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.

General Classification Image Classification +3

Learning beyond datasets: Knowledge Graph Augmented Neural Networks for Natural language Processing

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.

Knowledge Graphs Natural Language Inference +3

A Generative Model for Dynamic Networks with Applications

no code implementations11 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.

Community Detection Link Prediction

Unsupervised feature learning with discriminative encoder

1 code implementation3 Sep 2017 Gaurav Pandey, Ambedkar Dukkipati

How can one use the same discriminative models for learning useful features in the absence of labels?

Learning to segment with image-level supervision

no code implementations3 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.

Image Segmentation Semantic Segmentation

Generative Adversarial Residual Pairwise Networks for One Shot Learning

no code implementations23 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.

General Classification One-Shot Learning

On Consistency of Compressive Spectral Clustering

no code implementations12 Feb 2017 Muni Sreenivas Pydi, Ambedkar Dukkipati

Spectral clustering is one of the most popular methods for community detection in graphs.

Clustering Community Detection +1

Discriminative Neural Topic Models

no code implementations24 Jan 2017 Gaurav Pandey, Ambedkar Dukkipati

We propose a neural network based approach for learning topics from text and image datasets.

Topic Models

Image Generation and Editing with Variational Info Generative AdversarialNetworks

no code implementations17 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.

Image Generation

Deep Variational Inference Without Pixel-Wise Reconstruction

no code implementations16 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.

Variational Inference

A Neural Architecture Mimicking Humans End-to-End for Natural Language Inference

no code implementations15 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.

Natural Language Inference Representation Learning

Uniform Hypergraph Partitioning: Provable Tensor Methods and Sampling Techniques

no code implementations21 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.

Clustering hypergraph partitioning +1

On collapsed representation of hierarchical Completely Random Measures

no code implementations6 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.

Consistency of Spectral Partitioning of Uniform Hypergraphs under Planted Partition Model

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.

graph partitioning

Spectral Clustering with Jensen-type kernels and their multi-point extensions

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.

Clustering Image Segmentation +2

To go deep or wide in learning?

no code implementations23 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.

Generative Maximum Entropy Learning for Multiclass Classification

no code implementations3 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.

Binary Classification Classification +2

On Power-law Kernels, corresponding Reproducing Kernel Hilbert Space and Applications

no code implementations9 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.

General Classification regression

Cannot find the paper you are looking for? You can Submit a new open access paper.