Piyush Rai

• Home
• Publication
• Teaching
• Students
• News

Conference/Journal Publications

• VERSE: Virtual-Gradient Aware Streaming Lifelong Learning with Anytime Inference
  With:Soumya Banerjee, Vinay Verma, Avideep Mukherjee, Deepak Gupta, and Vinay Namboodiri
  ICRA 2024

• RISSOLE: Parameter-efficient Diffusion Models via Block-wise Generation and Retrieval-Guidance
  With:Avideep Mukherjee, Soumya Banerjee, and Vinay Namboodiri
  BMVC 2024

• Integrating Micro-satellite Images and Sensor Network-based Ground Measurements using Deep Learning for High-resolution Prediction of Fine Particulate Matter
  With:Vaishal Jain, Avideep Mukherjee, Soumya Banerjee, Sandeep Madhwal, Michael H Bergin, Prakash Bhave, David Carlson, Ziyang Jiang, Tongshu Zheng, and Sachchida Nand Tripathi
  Atmospheric Environment, 2024

• A Probabilistic Framework for Lifelong Test-Time Adaptation
  With:Dhanajit Brahma
  CVPR 2023

• Federated Learning with Uncertainty via Distilled Predictive Distributions
  With:Shrey Bhatt and Aishwarya Gupta
  ACML 2023

• Gradient Perturbation-based Efficient Deep Ensembles
  With:Amit Chandak and Purushottam Kar
  IKDD-CODS 2023

• DiffuseVAE: Efficient, Controllable and High-fidelity Generation from Low-dimensional Latents
  With:Kushagra Pandey, Avideep Mukherjee, and Abhishek Kumar
  TMLR 2022

• Rectification-based Knowledge Retention for Task Incremental Learning
  With:Pratik Mazumder, Pravendra, Singh, and Vinay P. Namboodiri
  IEEE TPAMI 2022

• Novel Class Discovery without Forgetting
  With:K.J. Joseph, Sujoy Paul, Gaurav Aggarwal, Soma Biswas, Kai Han, Vineeth Balasubramanian
  ECCV 2022

• CAM-GAN: Continual Adaptation Modules for Generative Adversarial Networks
  With:Sakshi Varshney, Vinay Verma, Srijith P.K., and Lawrence Carin
  NeurIPS 2021

• Bayesian Structural Adaptation for Continual Learning
  With: Abhishek Kumar and Sunabha Chatterjee
  ICML 2021

• Efficient Feature Transformations for Discriminative and Generative Continual Learning
  With:Vinay Verma, Kevin Liang, Nikhil Mehta, and Lawrence Carin
  CVPR 2021

• Generalized Adversarially Learned Inference
  With: Yatin Dandi, Homanga Bharadhwaj, and Abhishek Kumar
  AAAI 2021

• Rectification-based Knowledge Retention for Continual Learning
  With:Pravendra Singh, Pratik Mazumder, and Vinay Namboodiri
  CVPR 2021

• Few-shot Lifelong Learning
  With: Pratik Mazumder and Pravendra Singh
  AAAI 2021

• Knowledge Consolidation based Class Incremental Online Learning with Limited Data
  With: Mohammed Asad Karim, Vinay Verma, Pravendra Singh, and Vinay Namboodiri
  IJCAI 2021

• Fine-Grained Emotion Prediction by Modeling Emotion Definitions
  With:Gargi Singh, Dhanajit Brahma, and Ashutosh Modi
  ACII 2021 (best student paper award)

• Towards Zero-Shot Learning with Fewer Seen Class Examples
  With: Vinay Verma, Ashish Mishra, Anubha Pandey, and Hema A. Murthy
  WACV 2021

• Acceleration of Deep Convolutional Neural Networks using Adaptive Filter Pruning
  With: Pravendra Singh, Vinay Verma, and Vinay Namboodiri
  IEEE Journal of Selected Topics in Signal Processing (2021)

• Calibrating CNNs for Lifelong Learning
  With:Pravendra Singh, Vinay Verma, Pratik Mazumder, and Lawrence Carin
  NeurIPS 2020

• Variational Autoencoders for Sparse and Overdispersed Discrete Data
  With: He Zhao, Lan Du, Wray Buntine, Dinh Phung, and Mingyuan Zhou
  AISTATS 2020, Palermo, Sicily, Italy

• Meta-Learning for Generalized Zero-Shot Learning
  With: Vinay Verma and Dhanajit Brahma
  AAAI 2020, New York, USA

• Graph Representation Learning via Ladder Gamma Variational Autoencoders
  With: Arindam Sarkar and Nikhil Mehta
  AAAI 2020, New York, USA

• Deep Attentive Ranking Networks for Learning to Order Sentences
  With: Pawan Kumar, Dhanajit Brahma, and Harish Karnick
  AAAI 2020, New York, USA

• P-SIF: Document Embeddings using Partition Averaging
  With: Vivek Gupta, Ankit Saw, Pegah Nokhiz, Praneeth Netrapalli, and Partha Talukdar
  AAAI 2020, New York, USA

• Jointly Trained Image and Video Generation using Residual Vectors
  With: Yatin Dandi, Aniket Das, Soumye Singhal, and Vinay P. Namboodiri
  WACV 2020, Snowmass Village, CO, USA

• A Generative Framework for Zero Shot Learning with Adversarial Domain Adaptation
  With: Varun Khare, Divyat Mahajan, Homanga Bharadhwaj, and Vinay Verma
  WACV 2020, Snowmass Village, CO, USA

• A "Network Pruning Network" Approach to Deep Model Compression
  With: Vinay Verma, Pravendra Singh, and Vinay P. Namboodiri
  WACV 2020, Snowmass Village, CO, USA

• Leveraging Filter Correlations for Deep Model Compression
  With: Pravendra Singh, Vinay Verma, and Vinay P. Namboodiri
  WACV 2020, Snowmass Village, CO, USA

• Stochastic Blockmodels meet Graph Neural Networks
  With: Nikhil Mehta and Lawrence Carin
  ICML 2019, Long Beach, CA

• A Flexible Probabilistic Framework for Large-Margin Mixture of Experts
  With: Archit Sharma and Siddhartha Saxena
  Machine Learning Journal, 2019

• HetConv: Beyond Homogeneous Convolution Kernels for Deep CNNs
  With: Pravendra Singh, Vinay Verma, and Vinay Namboodiri
  International Journal of Computer Vision (pp 1-21, 2019)

• Incorporating Syntactic and Semantic Information in Word Embeddings using GCN
  With: S. Vashishth, M. Bhandari, P. Yadav, C. Bhattacharyya, and Partha Talukdar
  ACL 2019, Florence, Italy

• Play and Prune: Adaptive Filter Pruning for Deep Model Compression
  With: Pravendra Singh, Vinay Verma, and Vinay Namboodiri
  IJCAI 2019, Macao, China

• HetConv: Heterogeneous Kernel-Based Convolutions for Deep CNNs
  With: Pravendra Singh, Vinay Verma, and Vinay Namboodiri
  CVPR 2019, Long Beach, CA

• Deep Topic Models for Multi-Label Learning
  With: Ankit Pensia, Rajat Kumar Panda, Nikhil Mehta, and Mingyuan Zhou
  AISTATS 2019, Naha, Okinawa, Japan

• Distributional Semantics meets Multi-Label Learning
  With: Vivek Gupta, Rahul Wadbude, Nagarajan Natarajan, Harish Karnick, and Prateek Jain
  AAAI 2019, Honolulu, Hawaii, USA

• Small-Variance Asymptotics for Nonparametric Bayesian Overlapping Stochastic Blockmodels
  With: Gundeep Arora, Anupreet Porwal, Kanupriya Agarwal, and Avani Samdariya
  IJCAI 2018, Stockholm, Sweden

• Generalized Zero-Shot Learning via Synthesized Examples
  With: Vinay Verma, Gundeep Arora, and Ashish Mishra
  CVPR 2018, Salt Lake City, USA

• A Generative Approach to Zero-Shot and Few-Shot Action Recognition
  With: Ashish Mishra, Vinay Verma, M Shiva Krishna Reddy, Arulkumar S, and Anurag Mittal
  WACV 2018, Lake Tahoe, USA

• Bayesian Multi-label Learning with Sparse Features and Labels, and Label Co-occurrences
  With: He Zhao, Lan Du, and Wray Buntine
  AISTATS 2018, Canary Islands, Spain

• Zero-Shot Learning via Class-Conditioned Deep Generative Models
  With: Wenlin Wang, Y. Pu, Vinay Verma, K. Fan, Y. Zhang, C. Chen, and Lawrence Carin
  AAAI 2018, New Orleans, USA

• A Deep Generative Framework for Paraphrase Generation
  With: Ankush Gupta, Arvind Agarwal, and Prawaan Singh
  AAAI 2018, New Orleans, USA

• Deep Generative Models for Relational Data with Side Information
  With: Changwei Hu and Lawrence Carin
  ICML 2017, Sydney, Australia
  

• Scalable Generative Models for Multi-label Learning with Missing Labels
  With: Vikas Jain and Nirbhay Modhe
  ICML 2017, Sydney, Australia
  

• A Simple Exponential Family Framework for Zero-Shot Learning
  With: Vinay Verma
  ECML 2017, Skopje, Macedonia
  

• A Probabilistic Framework for Zero-Shot Multi-Label Learning
  With: Abhilash Gaure, Aishwarya Gupta, and Vinay Verma
  UAI 2017, Sydney, Australia
  

• Non-negative Inductive Matrix Completion for Discrete Dyadic Data
  AAAI 2017, San Francisco, USA
  

• Deep Metric Learning with Data Summarization [pdf]
  With: Wenlin Wang, Changyou Chen, Wenlin Chen, and Lawrence Carin
  ECML 2016, Riva del Garda, Italy
  

• Topic-Based Embeddings for Learning from Large Knowledge Graphs [pdf]
  With: Changwei Hu and Lawrence Carin
  AISTATS 2016, Cadiz, Spain
  

• Non-negative Matrix Factorization for Discrete Data with Hierarchical Side-Information [pdf]
  With: Changwei Hu and Lawrence Carin
  AISTATS 2016, Cadiz, Spain
  

• Architecture Adaptive Code-Variant Tuning [pdf]
  With: Saurav Muralidharan, Amit Roy, Mary Hall and Michael Garland
  ASPLOS 2016, Atlanta, Georgia
  

• Large-Scale Bayesian Multi-Label Learning via Topic-Based Label Embeddings [pdf]
  With: Changwei Hu, Ricardo Henao, and Lawrence Carin
  NIPS 2015, Montreal, Canada
  

• Zero-Truncated Poisson Tensor Factorization for Massive Binary Tensors [pdf]
  With: Changwei Hu and Lawrence Carin
  UAI 2015, Amsterdam, The Netherlands
  

• Scalable Bayesian Non-Negative Tensor Factorization for Massive Count Data [pdf]
  With: Changwei Hu, Changyou Chen, Matthew Harding, and Lawrence Carin
  ECML 2015, Porto, Portugal
  

• Integrating Features and Similarities: Flexible Models for Heterogeneous Multiview Data [pdf]
  With: Wenzhao Lian, Esther Salazar, and Lawrence Carin
  AAAI 2015, Austin, Texas
  

• Cross-Modal Similarity Learning via Pairs, Preferences, and Active Supervision [pdf]
  With: Yi Zhen, Hongyuan Zha, and Lawrence Carin
  AAAI 2015, Austin, Texas
  

• Leveraging Features and Networks for Probabilistic Tensor Decomposition [pdf]
  With: Yingjian Wang and Lawrence Carin
  AAAI 2015, Austin, Texas
  

• Scalable Probabilistic Tensor Factorization for Binary and Count Data [pdf]
  With: Changwei Hu, Matthew Harding, and Lawrence Carin
  IJCAI 2015, Buenos Aires, Argentina
  

• Scalable Bayesian Low-Rank Decomposition of Incomplete Multiway Tensors [pdf][supplementary][bib]
  With: Yingjian Wang, Shengbo Guo, Gary Chen, David Dunson, and Lawrence Carin
  ICML 2014, Beijing, China
  

• Predicting Growth Conditions from Internal Metabolic Fluxes in an In-Silico Model of E. coli [pdf coming soon]
  With: Viswanadham Sridhara, Austin Meyer, Jeffrey E. Barrick, Pradeep Ravikumar, Daniel Segre, and Claus Wilke
  PLOS ONE (2014)
  

• Stochastic Blockmodel with Cluster Overlap, Relevance Selection, and Similarity-Based Smoothing [pdf][bib]
  With: Joyce Whang and Inderjit Dhillon
  ICDM 2013, Dallas, Texas
  

• Simultaneously Leveraging Output and Task Structures for Multiple-Output Regression [pdf][bib]
  With: Abhishek Kumar and Hal Daumé III
  NIPS 2012, Lake Tahoe, Nevada
  

• Flexible Modeling of Latent Task Structures in Multitask Learning [pdf][supplementary][bib]
  With: Alexandre Passos, Jacques Wainer and Hal Daumé III
  ICML 2012, Edinburgh, Scotland
  

• Leveraging Social Bookmarks from Partially Tagged Corpus for Improved Webpage Clustering [pdf][bib]
  With: Anusua Trivedi, Hal Daumé III, and Scott L. DuVall
  ACM Transactions on Intelligent Systems and Technology 2012

• Co-regularized Multi-view Spectral Clustering [pdf][bib]
  With: Abhishek Kumar and Hal Daumé III
  NIPS 2011, Granada, Spain
  

• Message-Passing for Approximate MAP Inference with Latent Variables [pdf][bib]
  With: Jiarong Jiang and Hal Daumé III
  NIPS 2011, Granada, Spain
  

• Beam Search based MAP Estimates for the Indian Buffet Process [pdf][bib]
  With: Hal Daumé III
  ICML 2011, Bellevue, USA
  

• Online Learning of Multiple Tasks and Their Relationships [pdf][bib]
  With: Avishek Saha, Hal Daumé III, and Suresh Venkatasubramanian
  AISTATS 2011, Ft. Lauderdale, Florida

• Active Supervised Domain Adaptation [pdf][bib]
  With: Avishek Saha, Hal Daumé III, Suresh Venkatasubramanian, and Scott L. DuVall
  ECML 2011, Athens, Greece

• Distinguishing Locations Across Perimeters Using Wireless Link Measurements [pdf][bib]
  With: Junxing Zhang, Sneha Kasera and Neal Patwari
  INFOCOM 2011, Shanghai, China

• Infinite Predictor Subspace Models for Multitask Learning [pdf][bib]
  With: Hal Daumé III
  AISTATS 2010, Sardinia, Italy

• Multi-Label Prediction via Sparse Infinite CCA [pdf][bib]
  With: Hal Daumé III
  NIPS 2009, Vancouver, Canada
  

• Streamed Learning: One-Pass SVMs [pdf][bib]
  With: Hal Daumé III, and Suresh Venkatasubramanian
  IJCAI 2009, Pasadena, CA

• The Infinite Hierarchical Factor Regression Model [pdf][bib]
  With: Hal Daumé III
  NIPS 2008, Vancouver, Canada
  

ArXiv pre-prints and Refereed Workshop Papers

• SITA: Single Image Test-time Adaptation
  With:Ansh Khurana, Sujoy Paul, Gaurav Aggarwal, and Soma Biswas
  CVPR 2023 workshop on Computer Vision in the Wild

• Spacing Loss for Discovering Novel Categories
  With:K.J. Joseph, Sujoy Paul, Gaurav Aggarwal, Soma Biswas, Kai Han, Vineeth Balasubramanian
  CVPR 2022 Workshop on Continual Learning (best paper runner-up award)

• Hypernetworks for Semi-supervised Continual Learning
  With: Vinay Verma and Dhanajit Brahma
  CSSL@IJCAI 2021 (best student paper award)

• Temperature Scaling for Quantile Calibration
  With: Saiteja Utpala
  ICBINB@NeurIPS 2020

• Earliness-Aware Deep Convolutional Networks for Early Time Series Classification [pdf]
  With: Wenlin Wang, Changyou Chen, Wenqi Wang, and Lawrence Carin
  arXiv pre-print, 2016
  

• A Bayesian Framework for Multi-modality Analysis of Mental Health [pdf][supplementary]
  With: Esther Salazar, Yulia Nikolova, Wenzhao Lian, Andrienne Romar, Ahmad Hariri and Lawrence Carin
  Pre-print (2015)
  

• Bayesian Multitask Distance Metric Learning [pdf]
  With: Wenzhao Lian, and Lawrence Carin
  NIPS 2014 (Transfer and Multitask Learning Workshop), Montreal, Canada
  

• Multiple Hash Functions for Learning
  With: Amit Goyal and Hal Daumé III
  NIPS 2011: Big Learning Workshop, Sierra Nevada, Spain
  

• Domain Adaptation meets Active Learning [pdf][bib]
  With: Avishek Saha, Hal Daumé III, and Suresh Venkatasubramanian
  NAACL-HLT 2010: Active Learning for NLP Workshop , Los Angeles

• Co-regularized Spectral Clustering with Multiple Kernels [pdf][bib]
  With: Abhishek Kumar and Hal Daumé III
  NIPS 2010: Workshop on New Directions in Multiple Kernel Learning,Whistler, Canada

• Multiview Clustering with Incomplete Views [pdf][bib]
  With: Anusua Trivedi, Hal Daumé III, and Scott L. DuVall
  NIPS 2010: Workshop on Machine Learning for Social Computing, Whistler, Canada

• Active Online Multitask Learning [pdf][bib]
  With: Avishek Saha, Hal Daumé III, and Suresh Venkatasubramanian
  ICML 2010: Budgeted Learning Workshop, Haifa, Israel

• Exploiting Tag and Word Correlations for Improved Webpage Clustering [pdf][bib]
  With: Anusua Trivedi, Hal Daumé III, and Scott L. DuVall
  CIKM 2010: Workshop on Search and Mining User-Generated Content, Toronto, Canada

• Multitask Learning using Nonparametrically Learned Predictor Subspaces [pdf][bib]
  With:Hal Daumé III
  NIPS 2009: Workshop on Learning from Multiple Sources, Whistler, Canada
  

• Factor Regression Combining Heterogeneous Sources of Information [pdf][bib]
  With: Amrish Kapoor and Hal Daumé III
  NIPS 2009: Workshop on Learning from Multiple Sources, Whistler, Canada