Our Publications

Click on the title for more details on the publication

2025

• Deep Representation Learning for Forecasting Recursive and Multi-Relational Events in Temporal Networks

  Tony Gracious and Ambedkar Dukkipati

  39th AAAI Conference on Artificial Intelligence (AAAI): 2025.

• Neural Temporal Point Process for Forecasting Higher Order and Directional Interactions

  Tony Gracious, Arman Gupta and Ambedkar Dukkipati

  39th AAAI Conference on Artificial Intelligence (AAAI): 2025.

• Active Reinforcement Learning Strategies for Offline Policy Improvement

  Ambedkar Dukkipati, Ranga Shaarad Ayyagari, Bodhisattwa Dasgupta, Parag Dutta and Prabhas Reddy Onteru

  39th AAAI Conference on Artificial Intelligence (AAAI): 2025 (Oral, among top 4.6%).

2024

• Learning to Switch off, Switch on, and Integrate Modalities in Large Pre-trained Transformers

  Tejas Duseja, K M Annervaz, Jeevithiesh Duggani, Shyam Zacharia, Michael Free and Ambedkar Dukkipati

  IEEE International Conference on Multimedia Information Processing and Retrieval : 2024

• Causal Feature Alignment: Learning to Ignore Spurious Background Features.

  Rahul Venkataramani, Parag Dutta, Vikram Melapudi and Ambedkar Dukkipati

  In IEEE Winter Conference on Applications of Computer Vision (WACV)

2023

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

  Parag Dutta, Kawin Mayilvaghanan, Pratyaksha Sinha and Ambedkar Dukkipati

  The 15th Asian Conference on Machine Learning (ACML)

• Risk-Aware Algorithms for Combinatorial Semi-Bandits

  Ranga Shaarad Ayyagari and Ambedkar Dukkipati

  Proceedings of International Symposium on Information Theory (ISIT)

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

  Tony Gracious and Ambedkar Dukkipati

  Proceedings of 37th AAAI Conference on Artificial Intelligence (AAAI)

• A Multi-Team Multi-Model Collaborative COVID-19 Forecasting Hub for India

  A Adiga, S Athreya, K R Bhimala, Ambedkar Dukkipati, Tony Gracious, Shubham Gupta, B Hurt, G Kaur, B Lewis, M Marathe, V Mudkavi, G K Patra, N Rathod, R Sundaresan, S Venkataramanan and S Yasodharan

  In Proceedings of Winter Simulation Conference (WSC)

2022

• Consistency of Constrained Spectral Clustering under Graph Induced Fair Planted Partitions

  Shubham Gupta and Ambedkar Dukkipati

  Advances in Neural Information Processing Systems (NeurIPS 2023)

• Learning Skills to Navigate without a Master: A Sequential Multi-Policy Reinforcement Learning Algorithm

  Ambedkar Dukkipati, Rajarshi Banerjee, Ranga Shaarad Ayyagari and Dhaval Parmar Udaybhai

  IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

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

  Shubham Gupta, Gururaj K, Ambedkar Dukkipati and Rui M Castro

  Journal of Complex Networks

2021

• Contradistinguisher: A Vapnik’s Imperative to Unsupervised Domain Adaptation

  Sourabh Balgi and Ambedkar Dukkipati

  IEEE Transactions on Pattern Analysis and Machine Intelligence

• Active² Learning: Actively reducing redundancies in Active Learning methods for Sequence Tagging and Machine Translation

  Rishi Hazra, Parag Dutta, Shubham Gupta, Mohammed Abdul Qaathir and Ambedkar Dukkipati

  In Proceedings of 2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT)

• Neural Latent Space Model for Dynamic Networks and Temporal Knowledge Graphs

  Tony Gracious, Shubham Gupta, Arun Kanthali, Rui M Castro and Ambedkar Dukkipati

  In Proceedings of 35rd AAAI Conference on Artificial Intelligence (AAAI)

• SiameseGAN: A Generative Model for Denoising of Spectral Domain Optical Coherence Tomography Images

  Nilesh A Kande, Rupali Dakhane, Ambedkar Dukkipati and Phaneendra Kumar Yalavarthy

  IEEE Transactions on Medical Imaging

2020

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

  Shubham Gupta and Ambedkar Dukkipati

  Conference on Autonomous Agents and Multi-Agent Systems

• Networked Multi-Agent Reinforcement Learning with Emergent Communication

  Shubham Gupta, Rishi Hazra and Ambedkar Dukkipati

  9th International Conference on Autonomous Agents and Multi-Agent Systems

2019

• Instance-based Inductive Deep Transfer Learning by Cross-Dataset Querying with Locality Sensitive Hashing

  Somnath basu Roy Chowdhury, K M Annervaz and Ambedkar Dukkipati

  EMNLP Workshop on Deep Learning for Low-resource NLP

• CUDA : Contradistinguisher for Unsupervised Domain Adaptation

  Sourabh Balgi and Ambedkar Dukkipati

  In Proceedings of the IEEE International Conference on Data Mining (ICDM)

• Skip Residual Pairwise Networks with Learnable Comparative Functions for Few-shot Learning

  Akshay Mehrotra and Ambedkar Dukkipati

  In IEEE Winter Conference on Applications of Computer Vision (WACV)

• A Generative Model for Dynamic Networks with Applications

  Shubham Gupta, Gaurav Sharma and Ambedkar Dukkipati

  Proceedings of the AAAI Conference on Artificial Intelligence

• Learning to segment with image-level supervision using CRF-CNN

  Gaurav Pandey and Ambedkar Dukkipati

  In IEEE Winter Conference on Applications of Computer Vision (WACV)

2018

• On Consistency of Compressive Spectral Clustering

  Muni Sreenivas Pydi and Ambedkar Dukkipati

  In Proceedings of IEEE International Symposium on Information Theory (ISIT)

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

  K M Annervaz, Somnath basu Roy Chowdhury and Ambedkar Dukkipati

  In Proceedings of NAACL HLT

2017

• Unsupervised Feature Learning with Discriminative Encoder.

  Gaurav Pandey and Ambedkar Dukkipati

  In Proceedings of the IEEE International Conference on Data Mining (ICDM)

• Uniform Hypergraph Partitioning: Provable Tensor Methods and Sampling Techniques

  Debarghya Ghoshdastidar and Ambedkar Dukkipati

  Journal of Machine Learning Research

• Attentive Recurrent Comparators

  Pranav Shyam, Shubham Gupta and Ambedkar Dukkipati

  In Proceedings of the International Conference on Machine Learning (ICML), 2017

• Consistency of Spectral Hypergraph Partitioning under Planted Partition Model

  Debarghya Ghoshdastidar and Ambedkar Dukkipati

  The Annals of Statistics

• Variational methods for conditional multimodal deep learning

  Gaurav Pandey and Ambedkar Dukkipati

  Proceedings of the International Joint Conference on Neural Networks (IJCNN

2016

• On Collapsed representations of hierarchical Completely Random Measures.

  Gaurav Pandey and Ambedkar Dukkipati

  Proceedings of the 33rd International Conference on Machine Learning (ICML):

• Mixture Modelling with Compact Support Distributions for Unsupervised Learning.

  Ambedkar Dukkipati, Debarghya Ghoshdastidar and Jinu Krishnan

  Proceedings of the International Joint Conference on Neural Networks (IJCNN)

• Learning With Jensen-Tsallis Kernels

  Debarghya Ghoshdastidar, Ajay P Adsul and Ambedkar Dukkipati

  IEEE Transactions on Neural Networks and Learning Systems

2015

• A Provable Generalized Tensor Spectral Method for Uniform Hypergraph Partitioning

  Debarghya Ghoshdastidar and Ambedkar Dukkipati

  Proceedings of the 32nd International Conference on Machine Learning (ICML)

• Spectral Clustering Using Multilinear SVD: Analysis, Approximations and Applications

  Debarghya Ghoshdastidar and Ambedkar Dukkipati

  Twenty-Ninth AAAI Conference on Artificial Intelligence

2014

• Consistency of Spectral Partitioning of Uniform Hypergraphs under Planted Partition Model

  Debarghya Ghoshdastidar and Ambedkar Dukkipati

  Advances in Neural Information Processing Systems 27 (NIPS 2014)

• Newton based Stochastic Optimization using q-Gaussian Smoothed Functional Algorithms

  Debarghya Ghoshdastidar, Ambedkar Dukkipati and Shalabh Bhatnagar

  Automatica, 50(10):2606–2614

• Smoothed Functional Algorithms for Stochastic Optimization using q-Gaussian Distributions

  Debarghya Ghoshdastidar, Ambedkar Dukkipati and Shalabh Bhatnagar

  ACM Transactions on Modeling and Computer Simulation, 24 (3), Article 17,

• Learning by Stretching Deep Networks

  Gaurav Pandey and Ambedkar Dukkipati

  Proceedings of the 31st International Conference on Machine Learning, PMLR 32(2):1719-1727

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

  Debarghya Ghoshdastidar, Ambedkar Dukkipati, Ajay P Adsul and Aparna S Vijayan

  In Proceedings of Computer Vision and Pattern Recognition

• To go deep or wide in learning?

  Gaurav Pandey and Ambedkar Dukkipati

  Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics, PMLR 33:724-732

2013

• Generative Maximum Entropy Learning for Multiclass Classification

  Ambedkar Dukkipati, Gaurav Pandey, Debarghya Ghoshdastidar, Paramita Koley and D Satya Sriram

  Proceedings of IEEE International Conference on Data Mining (ICDM'13), pp. 141-150, IEEE press

• Minimum Description Length Principle for Maximum Entropy Model Selection

  Gaurav Pandey and Ambedkar Dukkipati

  Proceedings of IEEE International Symposium on Information Theory (ISIT'13), pp. 1521-1525, IEEE press

• On Power-Law Kernels, Corresponding Reproducing Kernel Hilbert Space and Applications

  Debarghya Ghoshdastidar and Ambedkar Dukkipati

  Proceedings of the AAAI Conference on Artificial Intelligence, 27

2012

• q-Gaussian based Smoothed Functional Algorithm for Stochastic Optimization

  Debarghya Ghoshdastidar, Ambedkar Dukkipati and Shalabh Bhatnagar

  Proceedings of IEEE International Symposium on Information Theory (ISIT'12), pp. 1059-1063, IEEE press

• A two stage selective averaging LDPC decoding

  A Dinesh Kumar and Ambedkar Dukkipati

  Proceedings of IEEE International Symposium on Information Theory (ISIT'12), pp. 2866-2870, IEEE press,

2010

• On Kolmogorov-Nagumo averages and nonextensive entropy

  Ambedkar Dukkipati

  International Symposium On Information Theory & Its Applications

• Maximum Entropy Model Based Classification with Feature Selection

  Ambedkar Dukkipati, Abhay Kumar Yadav and M Narasimha Murty

  20th International Conference on Pattern Recognition