paper-with-me

홈 › Papers

Learning Interpretable Models Through Multi-Objective Neural Architecture Search

2021-12-16 · Zachariah Carmichael, Tim Moon, Sam Ade Jacobs

Monumental advances in deep learning have led to unprecedented achievements across various domains. While the performance of deep neural networks is indubitable, the architectural design and interpretability of such models are nontrivial. Research has been introduced to automate the design of neural network architectures through neural architecture search (NAS). Recent progress has made these methods more pragmatic by exploiting distributed computation and novel optimization algorithms. However, there is little work in optimizing architectures for interpretability. To this end, we propose a multi-objective distributed NAS framework that optimizes for both task performance and "introspectability," a surrogate metric for aspects of interpretability. We leverage the non-dominated sorting genetic algorithm (NSGA-II) and explainable AI (XAI) techniques to reward architectures that can be better comprehended by domain experts. The framework is evaluated on several image classification datasets. We demonstrate that jointly optimizing for task error and introspectability leads to more disentangled and debuggable architectures that perform within tolerable error.

📄 PDF Abstract BibTeX arXiv:2112.08645

Code (1)

llnl/xnas 공식 구현 tf

Tasks

Explainable Artificial Intelligence (XAI)image-classificationImage ClassificationNeural Architecture Search

Similar Papers 제목 키워드 기반

Which Hyperparameters Matter? A Game-Theoretic Framework for Interpretable Hyperparameter Sensitivity Analysis

2026-07-17 · Nyi Nyi Aung, Heepeom Shin, Abigail Lawlor, Adrian Stein arxiv

This work presents a game-theoretic framework for interpretable hyperparameter-objective interaction analysis rather than proposing a new optimization algorithm. In the proposed framework, Shapley Effects are employed fo…

Cross-Global Attention Graph Kernel Network Prediction of Drug Prescription

2020-08-04 · Hao-Ren Yao, Der-Chen Chang, Ophir Frieder, Wendy Huang 외

We present an end-to-end, interpretable, deep-learning architecture to learn a graph kernel that predicts the outcome of chronic disease drug prescription. This is achieved through a deep metric learning collaborative wi…

Graph ClassificationMetric LearningTriplet

Causal Graph Fuzzy LLMs: A First Introduction and Applications in Time Series Forecasting

2025-07-22 · Omid Orang, Patricia O. Lucas, Gabriel I. F. Paiva, Petronio C. L. Silva 외 arxiv

In recent years, the application of Large Language Models (LLMs) to time series forecasting (TSF) has garnered significant attention among researchers. This study presents a new frame of LLMs named CGF-LLM using GPT-2 co…

Time Series Forecasting

Building Optimal Neural Architectures using Interpretable Knowledge

2024-03-20 · CVPR 2024 1 · Keith G. Mills, Fred X. Han, Mohammad Salameh, Shengyao Lu 외

Neural Architecture Search is a costly practice. The fact that a search space can span a vast number of design choices with each architecture evaluation taking nontrivial overhead makes it hard for an algorithm to suffic…

image-classificationImage ClassificationNeural Architecture Search

Concept-Enhanced Multimodal RAG: Towards Interpretable and Accurate Radiology Report Generation

2026-02-17 · Marco Salmè, Federico Siciliano, Fabrizio Silvestri, Paolo Soda 외 arxiv

Radiology Report Generation (RRG) through Vision-Language Models (VLMs) promises to reduce documentation burden, improve reporting consistency, and accelerate clinical workflows. However, their clinical adoption remains …