Manik Varma — accepted AI-conference papers

2025

MOGIC: Metadata-infused Oracle Guidance for Improved Extreme Classification

Suchith Chidananda Prabhu, Bhavyajeet Singh, Anshul Mittal, Siddarth Asokan, Shikhar Mohan, Deepak Saini +8

ICML 2025poster

Retrieval-augmented classification and generation models benefit from *early-stage fusion* of high-quality text-based metadata, often called memory, but face high latency and noise sensitivity. In extreme classification (XC), where low latency is crucial, existing methods use *late-stage fusion* for…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2024

Enhancing Tail Performance in Extreme Classifiers by Label Variance Reduction

Anirudh Buvanesh, Rahul Chand, Jatin Prakash, Bhawna Paliwal, Mudit Dhawan, Neelabh Madan +7

ICLR 2024poster

Extreme Classification (XC) architectures, which utilize a massive One-vs-All (OvA) classifier layer at the output, have demonstrated remarkable performance on problems with large label sets. Nonetheless, these architectures falter on tail labels with few representative samples. This phenomenon has…

Cited by 7 Source ↗PDF ↗Scholar ↗

2024

OAK: Enriching Document Representations using Auxiliary Knowledge for Extreme Classification

Shikhar Mohan, Deepak Saini, Anshul Mittal, Sayak Ray Chowdhury, Bhawna Paliwal, Jian Jiao +2

ICML 2024poster

The objective in eXtreme Classification (XC) is to find relevant labels for a document from an exceptionally large label space. Most XC application scenarios have rich auxiliary data associated with the input documents, e.g., frequently clicked webpages for search queries in sponsored search. Unfort…

Cited by 2 Source ↗PDF ↗Scholar ↗

2022

Multi-Modal Extreme Classification

Anshul Mittal, Kunal Dahiya, Shreya Malani, Janani Ramaswamy, Seba Kuruvilla, Jitendra Ajmera +4

CVPR 2022poster

This paper develops the MUFIN technique for extreme classification (XC) tasks with millions of labels where datapoints and labels are endowed with visual and textual descriptors. Applications of MUFIN to product-to-product recommendation and bid query prediction over several millions of products are…

Cited by 16 PDF ↗code ↗Scholar ↗

2021

SiameseXML: Siamese Networks meet Extreme Classifiers with 100M Labels

Kunal Dahiya, Ananye Agarwal, Deepak Saini, Gururaj K, Jian Jiao, Amit Singh +3

ICML 2021spotlight

Deep extreme multi-label learning (XML) requires training deep architectures that can tag a data point with its most relevant subset of labels from an extremely large label set. XML applications such as ad and product recommendation involve labels rarely seen during training but which nevertheless h…

Cited by 51 Source ↗PDF ↗code ↗Scholar ↗

2020

RNNPool: Efficient Non-linear Pooling for RAM Constrained Inference

Oindrila Saha, Aditya Kusupati, Harsha Vardhan Simhadri, Manik Varma, Prateek Jain

NeurIPS 2020spotlight

Standard Convolutional Neural Networks (CNNs) designed for computer vision tasks tend to have large intermediate activation maps. These require large working memory and are thus unsuitable for deployment on resource-constrained devices typically used for inference on the edge. Aggressively downsampl…

Cited by 63 Source ↗PDF ↗code ↗Scholar ↗

2018

FastGRNN: A Fast, Accurate, Stable and Tiny Kilobyte Sized Gated Recurrent Neural Network

Aditya Kusupati, Manish Singh, Kush Bhatia, Ashish Kumar, Prateek Jain, Manik Varma

NeurIPS 2018poster

This paper develops the FastRNN and FastGRNN algorithms to address the twin RNN limitations of inaccurate training and inefficient prediction. Previous approaches have improved accuracy at the expense of prediction costs making them infeasible for resource-constrained and real-time applications. Uni…

Cited by 249 Source ↗PDF ↗code ↗Scholar ↗

2017

ProtoNN: Compressed and Accurate kNN for Resource-scarce Devices

Chirag Gupta, Arun Sai Suggala, Ankit Goyal, Harsha Vardhan Simhadri, Bhargavi Paranjape, Ashish Kumar +4

ICML 2017poster

Several real-world applications require real-time prediction on resource-scarce devices such as an Internet of Things (IoT) sensor. Such applications demand prediction models with small storage and computational complexity that do not compromise significantly on accuracy. In this work, we propose Pr…

Cited by 227 Source ↗PDF ↗code ↗Scholar ↗

2017

Resource-efficient Machine Learning in 2 KB RAM for the Internet of Things

Ashish Kumar, Saurabh Goyal, Manik Varma

ICML 2017poster

This paper develops a novel tree-based algorithm, called Bonsai, for efficient prediction on IoT devices – such as those based on the Arduino Uno board having an 8 bit ATmega328P microcontroller operating at 16 MHz with no native floating point support, 2 KB RAM and 32 KB read-only flash. Bonsai mai…

Cited by 317 Source ↗PDF ↗Scholar ↗

2015

Sparse Local Embeddings for Extreme Multi-label Classification

Kush Bhatia, Himanshu Jain, Purushottam Kar, Manik Varma, Prateek Jain

NeurIPS 2015poster

The objective in extreme multi-label learning is to train a classifier that can automatically tag a novel data point with the most relevant subset of labels from an extremely large label set. Embedding based approaches make training and prediction tractable by assuming that the training label matrix…

Cited by 562 Source ↗PDF ↗Scholar ↗