Balaraman Ravindran

Causality in Bandits: A Survey
A drop-out mechanism for active learning based on one-attribute heuristics
CIAMS: clustering indices-based automatic classification model selection
Line Conversation Graphs for Effective Emotion Recognition Using Graph Neural Networks
LineConGraphs: Line Conversation Graphs for Effective Emotion Recognition Using Graph Neural Networks
PURE: Policy-guided Unbiased REpresentations for structure-constrained molecular generation
LExT: Towards Evaluating Trustworthiness of Natural Language Explanations
Systematic literature review – unpacking values. How values change over time and link with personality traits and behaviours
Causal contextual bandits with one-shot data integration
Active learning with human heuristics: an algorithm robust to labeling bias
Deception in Reinforced Autonomous Agents: The Unconventional Rabbit Hat Trick in Legislation
TOMBoost: a topic modeling based boosting approach for learning with class imbalance
InSaAF: Incorporating Safety through Accuracy and Fairness | Are LLMs ready for the Indian Legal Domain?
Hybrid self-supervised learning-based architecture for construction progress monitoring
A Learning Approach for Discovering Cost-Efficient Integrated Sourcing and Routing Strategies in E-Commerce
Cost-Sensitive Trees for Interpretable Reinforcement Learning
Guiding Offline Reinforcement Learning Using a Safety Expert
Deception in Reinforced Autonomous Agents: The Unconventional Rabbit Hat Trick in Legislation
PolicyClusterGCN: Identifying Efficient Clusters for Training Graph Convolutional Networks
GAN-MPC: Training Model Predictive Controllers with Parameterized Cost Functions using Demonstrations from Non-identical Experts
RePReL: a unified framework for integrating relational planning and reinforcement learning for effective abstraction in discrete and continuous domains
Hypergraph partitioning using tensor eigenvalue decomposition
A deep network-based model of hippocampal memory functions under normal and Alzheimer’s disease conditions
Systemic Literature Review - Unpacking values. How values change over time and link with personality traits and behaviours
Optimizing Traffic Control with Model-Based Learning: A Pessimistic Approach to Data-Efficient Policy Inference
MultiCens: Multilayer network centrality measures to uncover molecular mediators of tissue-tissue communication
Financial exclusion of internal migrant workers of India during COVID-19: can digital financial inclusion be facilitated by AI?
A Survey of Adversarial Defences and Robustness in NLP
Physics-Informed Model-Based Reinforcement Learning
Multi-Variate Time Series Forecasting on Variable Subsets
Evolutionary Approach to Security Games with Signaling
Benchmarking and Analysing Unsupervised Network Representation Learning and the Illusion of Progress
Detecting Vehicles on the Edge: Knowledge Distillation to Improve Performance in Heterogeneous Road Traffic
Causal Contextual Bandits with Targeted Interventions
Scaling Graph Propagation Kernels for Predictive Learning
On Combining Bags to Better Learn from Label Proportions
Accurate and Interpretable AI models: Towards Deployable AI
Scalable multi-product inventory control with lead time constraints using reinforcement learning
Scalable multi-product inventory control with lead time constraints using reinforcement learning
An Active Learning Framework for Efficient Robust Policy Search
Automated Incident Location Identification for EMS from Ambulance Geospatial Data
Smooth Imitation Learning via Smooth Costs and Smooth Policies
A Causal Approach for Unfair Edge Prioritization and Discrimination Removal
NetGenes: A Database of Essential Genes Predicted Using Features From Interaction Networks
NetGenes: A Database of Essential Genes Predicted Using Features From Interaction Networks
CombSGPO: A new algorithm to protect wildlife
Semi-Supervised Deep Learning for Multiplex Networks
Corrective Filter Based on Kinematics of Human Hand for Pose Estimation
Corrective Filter Based on Kinematics of Human Hand for Pose Estimation
RePReL: Integrating Relational Planning and Reinforcement Learning for Effective Abstraction
Sequence Neighborhoods Enable Reliable Prediction of Pathogenic Mutations in Cancer Genomes
Sequence Neighborhoods Enable Reliable Prediction of Pathogenic Mutations in Cancer Genomes
MADRaS : Multi Agent Driving Simulator
Revisiting Link Prediction on Heterogeneous Graphs with A Multi-view Perspective
Hyperedge Prediction using Tensor Eigenvalue Decomposition
A semi-supervised approach to growing classification trees
Inferring customer occupancy status in for-hire vehicles using PU Learning
Is it hard to learn a classifier on this dataset?
GrabQC: Graph Based Query Contextualization for Automated ICD Coding
Option Encoder: A Framework for Discovering a Policy Basis in Reinforcement Learning
Hypergraph clustering by iteratively reweighted modularity maximization
Towards Accurate Vehicle Behaviour Classification With Multi-Relational Graph Convolutional Networks
Understanding Dynamic Scenes using Graph Convolution Networks
HPRA: Hyperedge Prediction using Resource Allocation
Reinforcement Learning for Multi-Product Multi-Node Inventory Management in Supply Chains
D y VED eep
On Incorporating Structural Information to improve Dialogue Response Generation
Interpretability With Accurate Small Models
Influence Maximization in Unknown Social Networks: Learning Policies for Effective Graph Sampling
A New Measure of Modularity in Hypergraphs: Theoretical Insights and Implications for Effective Clustering
A Unified Non-Negative Matrix Factorization Framework for Semi Supervised Learning on Graphs
Rate of change analysis for interestingness measures
Temporal Analysis of a Bus Transit Network
Towards Transparent and Explainable Attention Models
Generalized random Surfer-Pair models
Effect of Inter-layer Coupling on Multilayer Network Centrality Measures
Edge Replacement Grammars : A Formal Language Approach for Generating Graphs
Adapting Community Detection Algorithms for Disease Module Identification in Heterogeneous Biological Networks
Adapting Community Detection Algorithms for Disease Module Identification in Heterogeneous Biological Networks
Studying the plasticity in deep convolutional neural networks using random pruning
Pack and Detect
Let’s Ask Again: Refine Network for Automatic Question Generation
Learning to Prevent Monocular SLAM Failure using Reinforcement Learning
Network-based features enable prediction of essential genes across diverse organisms
Network-based features enable prediction of essential genes across diverse organisms
Improved Insights on Financial Health through Partially Constrained Hidden Markov Model Clustering on Loan Repayment Data
Overtaking Maneuvers in Simulated Highway Driving using Deep Reinforcement Learning
Recovering from Random Pruning: On the Plasticity of Deep Convolutional Neural Networks
A neural attention based approach for clickstream mining
A novel topic modeling based weighting framework for class imbalance learning
A Partial Parameter HMM Based Clustering on Loan Repayment Data: Insights into Financial Behavior and Intent to Repay
Tracking and stabilization of mechanical systems using reinforcement learning
Training a deep learning architecture for vehicle detection using limited heterogeneous traffic data
Using Linear Stochastic Bandits to extend traditional offline Designed Experiments to online settings
DCEIL: Distributed Community Detection with the CEIL Score
Thresholding Bandits with Augmented UCB
Role Discovery in Graphs Using Global Features: Algorithms, Applications and a Novel Evaluation Strategy
Diversity driven attention model for query-based abstractive summarization
Correlational Neural Networks
Bridge Correlational Neural Networks for Multilingual Multimodal Representation Learning
Nonparametric Poisson Factorization Machine
COMMIT
Measuring network centrality using hypergraphs
Hierarchical activity recognition for dementia care using Markov Logic Network
An autoencoder approach to learning bilingual word representations
Multi-label collective classification in multi-attribute multi-relational network data
RRTPI: Policy iteration on continuous domains using rapidly-exploring random trees
An extended reinforcement learning model of basal ganglia to understand the contributions of serotonin and dopamine in risk-based decision making, reward prediction, and punishment learning
Activity Recognition for Natural Human Robot Interaction
Studying Indian Railways Network using hypergraphs
Temporal analysis of telecom call graphs