Author name cluster

Aditya Sinha

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

2 author rows

EAAI Journal 2025 Journal Article

From image processing to artificial intelligence-driven tools: A comprehensive survey on the evolution of feature extraction methods in paintings

Rekha Sharma
Rishi Gupta
Aditya Sinha

This study explores the computational process of converting qualitative elements of paintings, such as shape, color, texture, and line, into quantitative numerical values, which aid in identifying and extracting features from painting images. These identified features are then used to classify paintings based on artist, art style, genre, and art movements. This review employs a systematic literature review methodology, examining approximately 80 research papers to track trends in this field from 2015 to 2025. With the increasing presence of paintings in online media, museums, and galleries, artificial intelligence (AI) plays a significant role in interpreting these subjective elements. This review examines various image processing techniques in conjunction with AI implementations to extract the local and global features of a painting. These methods are combined with AI models, such as deep learning and computer vision algorithms, to improve feature extraction and provide a more thorough and accurate paintings analysis.

Details DOI

NeurIPS Conference 2024 Conference Paper

Learning Structured Representations with Hyperbolic Embeddings

Aditya Sinha
Siqi Zeng
Makoto Yamada
Han Zhao

Most real-world datasets consist of a natural hierarchy between classes or an inherent label structure that is either already available or can be constructed cheaply. However, most existing representation learning methods ignore this hierarchy, treating labels as permutation invariant. Recent work [Zeng et al. , 2022] proposes using this structured information explicitly, but the use of Euclidean distance may distort the underlying semantic context [Chen et al. , 2013]. In this work, motivated by the advantage of hyperbolic spaces in modeling hierarchical relationships, we propose a novel approach HypStructure: a Hyperbolic Structured regularization approach to accurately embed the label hierarchy into the learned representations. HypStructure is a simple-yet-effective regularizer that consists of a hyperbolic tree-based representation loss along with a centering loss, and can be combined with any standard task loss to learn hierarchy-informed features. Extensive experiments on several large-scale vision benchmarks demonstrate the efficacy of HypStructure in reducing distortion and boosting generalization performance especially under low dimensional scenarios. For a better understanding of structured representation, we perform eigenvalue analysis that links the representation geometry to improved Out-of-Distribution (OOD) detection performance seen empirically.

PDF Details DOI

ICLR Conference 2022 Conference Paper

IGLU: Efficient GCN Training via Lazy Updates

S. Deepak Narayanan
Aditya Sinha
Prateek Jain 0002
Purushottam Kar
Sundararajan Sellamanickam

Training multi-layer Graph Convolution Networks (GCN) using standard SGD techniques scales poorly as each descent step ends up updating node embeddings for a large portion of the graph. Recent attempts to remedy this sub-sample the graph that reduces compute but introduce additional variance and may offer suboptimal performance. This paper develops the IGLU method that caches intermediate computations at various GCN layers thus enabling lazy updates that significantly reduce the compute cost of descent. IGLU introduces bounded bias into the gradients but nevertheless converges to a first-order saddle point under standard assumptions such as objective smoothness. Benchmark experiments show that IGLU offers up to 1.2% better accuracy despite requiring up to 88% less compute.

Details

NeurIPS Conference 2022 Conference Paper

Matryoshka Representation Learning

Aditya Kusupati
Gantavya Bhatt
Aniket Rege
Matthew Wallingford
Aditya Sinha
Vivek Ramanujan
William Howard-Snyder
Kaifeng Chen

Learned representations are a central component in modern ML systems, serving a multitude of downstream tasks. When training such representations, it is often the case that computational and statistical constraints for each downstream task are unknown. In this context rigid, fixed capacity representations can be either over or under-accommodating to the task at hand. This leads us to ask: can we design a flexible representation that can adapt to multiple downstream tasks with varying computational resources? Our main contribution is Matryoshka Representation Learning (MRL) which encodes information at different granularities and allows a single embedding to adapt to the computational constraints of downstream tasks. MRL minimally modifies existing representation learning pipelines and imposes no additional cost during inference and deployment. MRL learns coarse-to-fine representations that are at least as accurate and rich as independently trained low-dimensional representations. The flexibility within the learned Matryoshka Representations offer: (a) up to $\mathbf{14}\times$ smaller embedding size for ImageNet-1K classification at the same level of accuracy; (b) up to $\mathbf{14}\times$ real-world speed-ups for large-scale retrieval on ImageNet-1K and 4K; and (c) up to $\mathbf{2}\%$ accuracy improvements for long-tail few-shot classification, all while being as robust as the original representations. Finally, we show that MRL extends seamlessly to web-scale datasets (ImageNet, JFT) across various modalities -- vision (ViT, ResNet), vision + language (ALIGN) and language (BERT). MRL code and pretrained models are open-sourced at https: //github. com/RAIVNLab/MRL.

PDF Details

NeurIPS Conference 2022 Conference Paper

S3GC: Scalable Self-Supervised Graph Clustering

Fnu Devvrit
Aditya Sinha
Inderjit Dhillon
Prateek Jain

We study the problem of clustering graphs with additional side-information of node features. The problem is extensively studied, and several existing methods exploit Graph Neural Networks to learn node representations. However, most of the existing methods focus on generic representations instead of their cluster-ability or do not scale to large scale graph datasets. In this work, we propose S3GC which uses contrastive learning along with Graph Neural Networks and node features to learn clusterable features. We empirically demonstrate that S3GC is able to learn the correct cluster structure even when graph information or node features are individually not informative enough to learn correct clusters. Finally, using extensive evaluation on a variety of benchmarks, we demonstrate that S3GC is able to significantly outperform state-of-the-art methods in terms of clustering accuracy -- with as much as 5% gain in NMI -- while being scalable to graphs of size 100M.

PDF Details