arXiv subjects

Rohit Das

Publications and source records attributed to Rohit Das.

3 recordsLinked to original sources

arXiv2026

Inverse Area Corrections to Black Hole Entropy Area Formula in F(R) Gravity and Gravitational Wave Observations

We consider corrections to the Bekenstein Hawking Area Formula for black hole entropy, which have inverse powers of the horizon area for very large horizon areas, for classical spherically symmetric black hole solutions of F(R) modified gravity theory, using the Wald formula for the entropy function with modifications suggested by Jacobson, Kang and Myers. Requiring that the coefficient of such corrections be absolutely consistent with gravitational wave observational results validating the Hawking Area Theorem for binary black hole coalescences, implies constraints on parameters of F(R) gravity. For the sake of comparison, we present a computation of inverse area corrections for quantum black holes in quantum general relativity, using the It from Bit approach of Wheeler modified by some tenets of Loop Quantum Gravity.

gr-qc↗

arXiv2024

3D-GANTex: 3D Face Reconstruction with StyleGAN3-based Multi-View Images and 3DDFA based Mesh Generation

Geometry and texture estimation from a single face image is an ill-posed problem since there is very little information to work with. The problem further escalates when the face is rotated at a different angle. This paper tries to tackle this problem by introducing a novel method for texture estimation from a single image by first using StyleGAN and 3D Morphable Models. The method begins by generating multi-view faces using the latent space of GAN. Then 3DDFA trained on 3DMM estimates a 3D face mesh as well as a high-resolution texture map that is consistent with the estimated face shape. The result shows that the generated mesh is of high quality with near to accurate texture representation.

cs.CV↗

arXiv2023

STRIDE: Structure and Embedding Distillation with Attention for Graph Neural Networks

Recent advancements in Graph Neural Networks (GNNs) have led to increased model sizes to enhance their capacity and accuracy. Such large models incur high memory usage, latency, and computational costs, thereby restricting their inference deployment. GNN compression techniques compress large GNNs into smaller ones with negligible accuracy loss. One of the most promising compression techniques is knowledge distillation (KD). However, most KD approaches for GNNs only consider the outputs of the last layers and do not consider the outputs of the intermediate layers of the GNNs. The intermediate layers may contain important inductive biases indicated by the graph structure and embeddings. Ignoring these layers may lead to a high accuracy drop, especially when the compression ratio is high. To address these shortcomings, we propose a novel KD approach for GNN compression that we call Structure and Embedding Distillation with Attention (STRIDE). STRIDE utilizes attention to identify important intermediate teacher-student layer pairs and focuses on using those pairs to align graph structure and node embeddings. We evaluate STRIDE on several datasets, such as OGBN-Mag and OGBN-Arxiv, using different model architectures, including GCNIIs, RGCNs, and GraphSAGE. On average, STRIDE achieves a 2.13% increase in accuracy with a 32.3X compression ratio on OGBN-Mag, a large graph dataset, compared to state-of-the-art approaches. On smaller datasets (e.g., Pubmed), STRIDE achieves up to a 141X compression ratio with the same accuracy as state-of-the-art approaches. These results highlight the effectiveness of focusing on intermediate-layer knowledge to obtain compact, accurate, and practical GNN models.

cs.LG↗