A survey on Concept-based Approaches For Model Improvement
A Gupta, PJ Narayanan - arXiv preprint arXiv:2403.14566, 2024 - arxiv.org
The focus of recent research has shifted from merely increasing the Deep Neural Networks
(DNNs) performance in various tasks to DNNs, which are more interpretable to humans. The …
(DNNs) performance in various tasks to DNNs, which are more interpretable to humans. The …
OCIE: Augmenting model interpretability via Deconfounded Explanation-Guided Learning
Deep neural networks (DNNs) often encounter significant challenges related to opacity,
inherent biases, and shortcut learning, which undermine their practical reliability. In this …
inherent biases, and shortcut learning, which undermine their practical reliability. In this …
LG-CAV: Train Any Concept Activation Vector with Language Guidance
Concept activation vector (CAV) has attracted broad research interest in explainable AI, by
elegantly attributing model predictions to specific concepts. However, the training of CAV …
elegantly attributing model predictions to specific concepts. However, the training of CAV …
Global explanation supervision for Graph Neural Networks
N Etemadyrad, Y Gao… - Frontiers in big …, 2024 - frontiersin.org
With the increasing popularity of Graph Neural Networks (GNNs) for predictive tasks on
graph structured data, research on their explainability is becoming more critical and …
graph structured data, research on their explainability is becoming more critical and …
KTCR: Improving Implicit Hate Detection with Knowledge Transfer driven Concept Refinement
S Garg, VH Kavuri, G Shroff, R Mishra - arXiv preprint arXiv:2410.15314, 2024 - arxiv.org
The constant shifts in social and political contexts, driven by emerging social movements
and political events, lead to new forms of hate content and previously unrecognized hate …
and political events, lead to new forms of hate content and previously unrecognized hate …