Srinivasan Parthasarathy
YOU?
Author Swipe
View article: $$\texttt {DiffER}$$: categorical diffusion ensembles for single-step chemical retrosynthesis
$$\texttt {DiffER}$$: categorical diffusion ensembles for single-step chemical retrosynthesis Open
Methods for automatic chemical retrosynthesis have found recent success through the application of models traditionally built for natural language processing, primarily through transformer neural networks. These models have demonstrated si…
View article: DiffER: Categorical Diffusion for Chemical Retrosynthesis
DiffER: Categorical Diffusion for Chemical Retrosynthesis Open
Methods for automatic chemical retrosynthesis have found recent success through the application of models traditionally built for natural language processing, primarily through transformer neural networks. These models have demonstrated si…
View article: PURE: Policy-guided Unbiased REpresentations for structure-constrained molecular generation
PURE: Policy-guided Unbiased REpresentations for structure-constrained molecular generation Open
Structure-constrained molecular generation (SCMG) generates novel molecules that are structurally similar to a given molecule and have optimized properties. Deep learning solutions for SCMG are limited in that they are pre-disposed towards…
View article: ISOSNet: a unified framework for cone photoreceptor detection and inner segment and outer segment length measurement from AO-OCT B-scans
ISOSNet: a unified framework for cone photoreceptor detection and inner segment and outer segment length measurement from AO-OCT B-scans Open
Adaptive optics-optical coherence tomography (AO-OCT) enables cellular-level in vivo visualization of cone photoreceptors in the human retina. Cone biomarkers, such as density, inner segment (IS), and outer segment (OS) lengths, are potent…
View article: A Generic Framework for Conformal Fairness
A Generic Framework for Conformal Fairness Open
Conformal Prediction (CP) is a popular method for uncertainty quantification with machine learning models. While conformal prediction provides probabilistic guarantees regarding the coverage of the true label, these guarantees are agnostic…
View article: Ranking Free RAG: Replacing Re-ranking with Selection in RAG for Sensitive Domains
Ranking Free RAG: Replacing Re-ranking with Selection in RAG for Sensitive Domains Open
Traditional Retrieval-Augmented Generation (RAG) pipelines rely on similarity-based retrieval and re-ranking, which depend on heuristics such as top-k, and lack explainability, interpretability, and robustness against adversarial content. …
View article: Adapting a LAMP Plasmodium vivax Malaria Diagnostic for Use in Low Resource Settings
Adapting a LAMP Plasmodium vivax Malaria Diagnostic for Use in Low Resource Settings Open
Malaria caused by the P. vivax parasite can be difficult to diagnose due to dormant phases and genetic variants. Regions such as Sub-Saharan Africa, South America, and Southeast Asia experience diagnostic accessibility issues due to the ‘g…
View article: Effectiveness of Coenzyme Q10 in Uncontrolled Diabetes Mellitus: A Double-blinded Randomized Controlled Trial
Effectiveness of Coenzyme Q10 in Uncontrolled Diabetes Mellitus: A Double-blinded Randomized Controlled Trial Open
Introduction: Diabetes mellitus is one of the metabolic disorders of the body, marked with persistent hyperglycemia, which leads to acute complications. Coenzyme Q10 (CoQ10) is a liposoluble antioxidant that might benefit in lowering blood…
View article: Intraoperative Episodic Paroxysmal Atrial Tachycardia in a Patient with Structurally Normal Heart with Fracture Femur – A Technical Report
Intraoperative Episodic Paroxysmal Atrial Tachycardia in a Patient with Structurally Normal Heart with Fracture Femur – A Technical Report Open
A 70-year-old female with a left femur fracture underwent percutaneous pinning surgery. Her medical history included controlled diabetes without other notable comorbidities. Preoperative evaluations, including electrocardiogram and echocar…
View article: A systematic review on the novel drug delivery system in the development of antimicrobial drug
A systematic review on the novel drug delivery system in the development of antimicrobial drug Open
Background The growing global concern over antimicrobial resistance necessitates the development of new and efficient antimicrobial drugs. Traditional methods of drug delivery often face challenges such as poor bioavailability, rapid clear…
View article: Graph Sparsification for Enhanced Conformal Prediction in Graph Neural Networks
Graph Sparsification for Enhanced Conformal Prediction in Graph Neural Networks Open
Conformal Prediction is a robust framework that ensures reliable coverage across machine learning tasks. Although recent studies have applied conformal prediction to graph neural networks, they have largely emphasized post-hoc prediction s…
View article: Severe Anaphylaxis Following Intradermal Test Dose of Ceftriaxone
Severe Anaphylaxis Following Intradermal Test Dose of Ceftriaxone Open
Ceftriaxone is a third-generation cephalosporin antibiotic used commonly for treating infections; however, hypersensitivity reactions, including anaphylaxis, occur in approximately 1%–3% of patients. Anaphylaxis can vary from minor skin ra…
View article: Conformal Prediction: A Theoretical Note and Benchmarking Transductive Node Classification in Graphs
Conformal Prediction: A Theoretical Note and Benchmarking Transductive Node Classification in Graphs Open
Conformal prediction has become increasingly popular for quantifying the uncertainty associated with machine learning models. Recent work in graph uncertainty quantification has built upon this approach for conformal graph prediction. The …
View article: Transformer-Based Sequence Modeling Short Answer Assessment Framework
Transformer-Based Sequence Modeling Short Answer Assessment Framework Open
Automated subjective assessment presents a significant challenge due to the complex nature of human language and reasoning characterized by semantic variability, subjectivity, language ambiguity, and judgment levels. Unlike objective exams…
View article: Masked LoGoNet: Fast and Accurate 3D Image Analysis for Medical Domain
Masked LoGoNet: Fast and Accurate 3D Image Analysis for Medical Domain Open
Standard modern machine-learning-based imaging methods have faced challenges in medical applications due to the high cost of dataset construction and, thereby, the limited labeled training data available. Additionally, upon deployment, the…
View article: Modeling Sequences as Star Graphs to Address Over-Smoothing in Self-Attentive Sequential Recommendation
Modeling Sequences as Star Graphs to Address Over-Smoothing in Self-Attentive Sequential Recommendation Open
Self-attention (SA) mechanisms have been widely used in developing sequential recommendation (SR) methods, and demonstrated state-of-the-art performance. However, in this article, we show that self-attentive SR methods substantially suffer…
View article: Retinal Diabetopathy? Sleep Disorders, Retinal Changes, and Insulin Resistance: A Synthesized Systematic Review
Retinal Diabetopathy? Sleep Disorders, Retinal Changes, and Insulin Resistance: A Synthesized Systematic Review Open
A BSTRACT Sleep disturbances, particularly prevalent in modern lifestyles, have been increasingly associated with metabolic disorders such as insulin resistance and type 2 diabetes mellitus (DM) (T2DM). Epidemiological evidence underscores…
View article: Reducing manual labeling requirements and improved retinal ganglion cell identification in 3D AO-OCT volumes using semi-supervised learning
Reducing manual labeling requirements and improved retinal ganglion cell identification in 3D AO-OCT volumes using semi-supervised learning Open
Adaptive optics-optical coherence tomography (AO-OCT) allows for the three-dimensional visualization of retinal ganglion cells (RGCs) in the living human eye. Quantitative analyses of RGCs have significant potential for improving the diagn…
View article: Intention enhanced mixed attentive model for session-based recommendation
Intention enhanced mixed attentive model for session-based recommendation Open
Session-based recommendation aims to generate recommendations for the next item of users’ interest based on a given session. In this manuscript, we develop intention enhanced mixed attentive model () to generate session-based recommendatio…
View article: HORCRUX: Accurate Cross Band Channel Prediction
HORCRUX: Accurate Cross Band Channel Prediction Open
Recent advancement in Frequency Domain Duplexing (FDD) enables wireless systems to use different frequency bands for uplink and downlink communication without explicit channel feedback information. The current state-of-the-art approaches e…
View article: An Online Probabilistic Distributed Tracing System
An Online Probabilistic Distributed Tracing System Open
Distributed tracing has become a fundamental tool for diagnosing performance issues in the cloud by recording causally ordered, end-to-end workflows of request executions. However, tracing in production workloads can introduce significant …
View article: Attribution in Scientific Literature: New Benchmark and Methods
Attribution in Scientific Literature: New Benchmark and Methods Open
Large language models (LLMs) present a promising yet challenging frontier for automated source citation in scientific communication. Previous approaches to citation generation have been limited by citation ambiguity and LLM overgeneralizat…
View article: HeteroMILE: a Multi-Level Graph Representation Learning Framework for Heterogeneous Graphs
HeteroMILE: a Multi-Level Graph Representation Learning Framework for Heterogeneous Graphs Open
Heterogeneous graphs are ubiquitous in real-world applications because they can represent various relationships between different types of entities. Therefore, learning embeddings in such graphs is a critical problem in graph machine learn…
View article: Grounding From an AI and Cognitive Science Lens
Grounding From an AI and Cognitive Science Lens Open
Grounding is a challenging problem, requiring a formal definition and different levels of abstraction. This article explores grounding from both cognitive science and machine learning perspectives. It identifies the subtleties of grounding…