arXiv subjects

Rishi Athavale

Publications and source records attributed to Rishi Athavale.

4 recordsLinked to original sources

arXiv2026

Graph Hopfield Networks: Energy-Based Node Classification with Associative Memory

We introduce Graph Hopfield Networks, whose energy function couples associative memory retrieval with graph Laplacian smoothing for node classification. Gradient descent on this joint energy yields an iterative update interleaving Hopfield retrieval with Laplacian propagation. Memory retrieval provides regime-dependent benefits: up to 2.0~pp on sparse citation networks and up to 5 pp additional robustness under feature masking; the iterative energy-descent architecture itself is a strong inductive bias, with all variants (including the memory-disabled NoMem ablation) outperforming standard baselines on Amazon co-purchase graphs. Tuning enables graph sharpening for heterophilous benchmarks without architectural changes.

cs.LG↗

arXiv2022

One Eye is All You Need: Lightweight Ensembles for Gaze Estimation with Single Encoders

Gaze estimation has grown rapidly in accuracy in recent years. However, these models often fail to take advantage of different computer vision (CV) algorithms and techniques (such as small ResNet and Inception networks and ensemble models) that have been shown to improve results for other CV problems. Additionally, most current gaze estimation models require the use of either both eyes or an entire face, whereas real-world data may not always have both eyes in high resolution. Thus, we propose a gaze estimation model that implements the ResNet and Inception model architectures and makes predictions using only one eye image. Furthermore, we propose an ensemble calibration network that uses the predictions from several individual architectures for subject-specific predictions. With the use of lightweight architectures, we achieve high performance on the GazeCapture dataset with very low model parameter counts. When using two eyes as input, we achieve a prediction error of 1.591 cm on the test set without calibration and 1.439 cm with an ensemble calibration model. With just one eye as input, we still achieve an average prediction error of 2.312 cm on the test set without calibration and 1.951 cm with an ensemble calibration model. We also notice significantly lower errors on the right eye images in the test set, which could be important in the design of future gaze estimation-based tools.

cs.CV↗

arXiv2022

Tensor Algebra on an Optoelectronic Microchip

Tensor algebra lies at the core of computational science and machine learning. Due to its high usage, entire libraries exist dedicated to improving its performance. Conventional tensor algebra performance boosts focus on algorithmic optimizations, which in turn lead to incremental improvements. In this paper, we describe a method to accelerate tensor algebra a different way: by outsourcing operations to an optical microchip. We outline a numerical programming language developed to perform tensor algebra computations that is designed to leverage our optical hardware's full potential. We introduce the language's current grammar and go over the compiler design. We then show a new way to store sparse rank-n tensors in RAM that outperforms conventional array storage (used by C++, Java, etc.). This method is more memory-efficient than Compressed Sparse Fiber (CSF) format and is specifically tuned for our optical hardware. Finally, we show how the scalar-tensor product, rank-$n$ Kronecker product, tensor dot product, Khatri-Rao product, face-splitting product, and vector cross product can be compiled into operations native to our optical microchip through various tensor decompositions.

cs.PL↗

arXiv2022

ALLNet: A Hybrid Convolutional Neural Network to Improve Diagnosis of Acute Lymphocytic Leukemia (ALL) in White Blood Cells

Due to morphological similarity at the microscopic level, making an accurate and time-sensitive distinction between blood cells affected by Acute Lymphocytic Leukemia (ALL) and their healthy counterparts calls for the usage of machine learning architectures. However, three of the most common models, VGG, ResNet, and Inception, each come with their own set of flaws with room for improvement which demands the need for a superior model. ALLNet, the proposed hybrid convolutional neural network architecture, consists of a combination of the VGG, ResNet, and Inception models. The ALL Challenge dataset of ISBI 2019 (available here) contains 10,691 images of white blood cells which were used to train and test the models. 7,272 of the images in the dataset are of cells with ALL and 3,419 of them are of healthy cells. Of the images, 60% were used to train the model, 20% were used for the cross-validation set, and 20% were used for the test set. ALLNet outperformed the VGG, ResNet, and the Inception models across the board, achieving an accuracy of 92.6567%, a sensitivity of 95.5304%, a specificity of 85.9155%, an AUC score of 0.966347, and an F1 score of 0.94803 in the cross-validation set. In the test set, ALLNet achieved an accuracy of 92.0991%, a sensitivity of 96.5446%, a specificity of 82.8035%, an AUC score of 0.959972, and an F1 score of 0.942963. The utilization of ALLNet in the clinical workspace can better treat the thousands of people suffering from ALL across the world, many of whom are children.

cs.CV↗