Ambuj K. Singh
YOU?
Author Swipe
View article: Normalized Space Alignment: A Versatile Metric for Representation Analysis
Normalized Space Alignment: A Versatile Metric for Representation Analysis Open
View article: A scalable organoid model of urothelial aging for metabolic interrogation, infection modeling, and reversal of age-associated changes
A scalable organoid model of urothelial aging for metabolic interrogation, infection modeling, and reversal of age-associated changes Open
Aging leads to a progressive decline in overall bladder function resulting in lower urinary tract symptoms and increased susceptibility to infections. However, tissue-specific mechanisms of aging, specifically the contributions of the aged…
View article: Phytotherapy as a natural alternative to antibiotics in aquaculture
Phytotherapy as a natural alternative to antibiotics in aquaculture Open
View article: APEX: Empowering LLMs with Physics-Based Task Planning for Real-time Insight
APEX: Empowering LLMs with Physics-Based Task Planning for Real-time Insight Open
Large Language Models (LLMs) demonstrate strong reasoning and task planning capabilities but remain fundamentally limited in physical interaction modeling. Existing approaches integrate perception via Vision-Language Models (VLMs) or adapt…
View article: Efficient Multi Subject Visual Reconstruction from fMRI Using Aligned Representations
Efficient Multi Subject Visual Reconstruction from fMRI Using Aligned Representations Open
This work introduces a novel approach to fMRI-based visual image reconstruction using a subject-agnostic common representation space. We show that the brain signals of the subjects can be aligned in this common space during training to for…
View article: Dynamic Gradient Influencing for Viral Marketing Using Graph Neural Networks
Dynamic Gradient Influencing for Viral Marketing Using Graph Neural Networks Open
View article: Learning to Lie: Reinforcement Learning Attacks Damage Human-AI Teams and Teams of LLMs
Learning to Lie: Reinforcement Learning Attacks Damage Human-AI Teams and Teams of LLMs Open
As artificial intelligence (AI) assistants become more widely adopted in safety-critical domains, it becomes important to develop safeguards against potential failures or adversarial attacks. A key prerequisite to developing these safeguar…
View article: Are LLMs Truly Graph-Savvy? A Comprehensive Evaluation of Graph Generation
Are LLMs Truly Graph-Savvy? A Comprehensive Evaluation of Graph Generation Open
View article: GraphEval36K: Benchmarking Coding and Reasoning Capabilities of Large Language Models on Graph Datasets
GraphEval36K: Benchmarking Coding and Reasoning Capabilities of Large Language Models on Graph Datasets Open
View article: Attribute-Enhanced Similarity Ranking for Sparse Link Prediction
Attribute-Enhanced Similarity Ranking for Sparse Link Prediction Open
Link prediction is a fundamental problem in graph data. In its most realistic setting, the problem consists of predicting missing or future links between random pairs of nodes from the set of disconnected pairs. Graph Neural Networks (GNNs…
View article: Normalized Space Alignment: A Versatile Metric for Representation Analysis
Normalized Space Alignment: A Versatile Metric for Representation Analysis Open
We introduce a manifold analysis technique for neural network representations. Normalized Space Alignment (NSA) compares pairwise distances between two point clouds derived from the same source and having the same size, while potentially p…
View article: Global Human-guided Counterfactual Explanations for Molecular Properties via Reinforcement Learning
Global Human-guided Counterfactual Explanations for Molecular Properties via Reinforcement Learning Open
Counterfactual explanations of Graph Neural Networks (GNNs) offer a powerful way to understand data that can naturally be represented by a graph structure. Furthermore, in many domains, it is highly desirable to derive data-driven global e…
View article: GraphEval36K: Benchmarking Coding and Reasoning Capabilities of Large Language Models on Graph Datasets
GraphEval36K: Benchmarking Coding and Reasoning Capabilities of Large Language Models on Graph Datasets Open
Large language models (LLMs) have achieved remarkable success in natural language processing (NLP), demonstrating significant capabilities in processing and understanding text data. However, recent studies have identified limitations in LL…
View article: Global Human-guided Counterfactual Explanations for Molecular Properties via Reinforcement Learning
Global Human-guided Counterfactual Explanations for Molecular Properties via Reinforcement Learning Open
Counterfactual explanations of Graph Neural Networks (GNNs) offer a powerful way to understand data that can naturally be represented by a graph structure. Furthermore, in many domains, it is highly desirable to derive data-driven global e…
View article: Application of Transformers in Cheminformatics
Application of Transformers in Cheminformatics Open
By accelerating time-consuming processes with high efficiency, computing has become an essential part of many modern chemical pipelines. Machine learning is a class of computing methods that can discover patterns within chemical data and u…
View article: DGCLUSTER: A Neural Framework for Attributed Graph Clustering via Modularity Maximization
DGCLUSTER: A Neural Framework for Attributed Graph Clustering via Modularity Maximization Open
Graph clustering is a fundamental and challenging task in the field of graph mining where the objective is to group the nodes into clusters taking into consideration the topology of the graph. It has several applications in diverse domains…
View article: Learning Neural Contracting Dynamics: Extended Linearization and Global Guarantees
Learning Neural Contracting Dynamics: Extended Linearization and Global Guarantees Open
Global stability and robustness guarantees in learned dynamical systems are essential to ensure well-behavedness of the systems in the face of uncertainty. We present Extended Linearized Contracting Dynamics (ELCD), the first neural networ…
View article: DGCLUSTER: A Neural Framework for Attributed Graph Clustering via Modularity Maximization
DGCLUSTER: A Neural Framework for Attributed Graph Clustering via Modularity Maximization Open
Graph clustering is a fundamental and challenging task in the field of graph mining where the objective is to group the nodes into clusters taking into consideration the topology of the graph. It has several applications in diverse domains…
View article: IDKM: Memory Efficient Neural Network Quantization via Implicit, Differentiable k-Means
IDKM: Memory Efficient Neural Network Quantization via Implicit, Differentiable k-Means Open
Compressing large neural networks with minimal performance loss is crucial to enabling their deployment on edge devices. (Cho et al., 2022) proposed a weight quantization method that uses an attention-based clustering algorithm called diff…
View article: XplainLLM: A Knowledge-Augmented Dataset for Reliable Grounded Explanations in LLMs
XplainLLM: A Knowledge-Augmented Dataset for Reliable Grounded Explanations in LLMs Open
Large Language Models (LLMs) have achieved remarkable success in natural language tasks, yet understanding their reasoning processes remains a significant challenge. We address this by introducing XplainLLM, a dataset accompanying an expla…
View article: Issue Information
Issue Information Open
View article: Fragment-based Pretraining and Finetuning on Molecular Graphs
Fragment-based Pretraining and Finetuning on Molecular Graphs Open
Property prediction on molecular graphs is an important application of Graph Neural Networks. Recently, unlabeled molecular data has become abundant, which facilitates the rapid development of self-supervised learning for GNNs in the chemi…
View article: GNNX-BENCH: Unravelling the Utility of Perturbation-based GNN Explainers through In-depth Benchmarking
GNNX-BENCH: Unravelling the Utility of Perturbation-based GNN Explainers through In-depth Benchmarking Open
Numerous explainability methods have been proposed to shed light on the inner workings of GNNs. Despite the inclusion of empirical evaluations in all the proposed algorithms, the interrogative aspects of these evaluations lack diversity. A…
View article: Graph Encoding and Neural Network Approaches for Volleyball Analytics: From Game Outcome to Individual Play Predictions
Graph Encoding and Neural Network Approaches for Volleyball Analytics: From Game Outcome to Individual Play Predictions Open
This research aims to improve the accuracy of complex volleyball predictions and provide more meaningful insights to coaches and players. We introduce a specialized graph encoding technique to add additional contact-by-contact volleyball c…
View article: Learning Prototype Classifiers for Long-Tailed Recognition
Learning Prototype Classifiers for Long-Tailed Recognition Open
The problem of long-tailed recognition (LTR) has received attention in recent years due to the fundamental power-law distribution of objects in the real-world. Most recent works in LTR use softmax classifiers that are biased in that they c…
View article: Robust Ante-hoc Graph Explainer using Bilevel Optimization
Robust Ante-hoc Graph Explainer using Bilevel Optimization Open
Explaining the decisions made by machine learning models for high-stakes applications is critical for increasing transparency and guiding improvements to these decisions. This is particularly true in the case of models for graphs, where de…
View article: Link Prediction without Graph Neural Networks
Link Prediction without Graph Neural Networks Open
Link prediction, which consists of predicting edges based on graph features, is a fundamental task in many graph applications. As for several related problems, Graph Neural Networks (GNNs), which are based on an attribute-centric message-p…
View article: LMExplainer: Grounding Knowledge and Explaining Language Models
LMExplainer: Grounding Knowledge and Explaining Language Models Open
Language models (LMs) like GPT-4 are important in AI applications, but their opaque decision-making process reduces user trust, especially in safety-critical areas. We introduce LMExplainer, a novel knowledge-grounded explainer that clarif…
View article: Global Counterfactual Explainer for Graph Neural Networks
Global Counterfactual Explainer for Graph Neural Networks Open
Graph neural networks (GNNs) find applications in various domains such as computational biology, natural language processing, and computer security. Owing to their popularity, there is an increasing need to explain GNN predictions since GN…
View article: Learning Prototype Classifiers for Long-Tailed Recognition
Learning Prototype Classifiers for Long-Tailed Recognition Open
The problem of long-tailed recognition (LTR) has received attention in recent years due to the fundamental power-law distribution of objects in the real-world. Most recent works in LTR use softmax classifiers that are biased in that they c…