paper-with-me

Papers

Interpretability via Model Extraction

2017-06-29 · Osbert Bastani, Carolyn Kim, Hamsa Bastani

The ability to interpret machine learning models has become increasingly important now that machine learning is used to inform consequential decisions. We propose an approach called model extraction for interpreting complex, blackbox models. Our approach approximates the complex model using a much more interpretable model; as long as the approximation quality is good, then statistical properties of the complex model are reflected in the interpretable model. We show how model extraction can be used to understand and debug random forests and neural nets trained on several datasets from the UCI Machine Learning Repository, as well as control policies learned for several classical reinforcement learning problems.

📄 PDF Abstract BibTeX arXiv:1706.09773

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine LearningmodelModel extractionreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Clinical information extraction for Low-resource languages with Few-shot learning using Pre-trained language models and Prompting

2024-03-20 · Phillip Richter-Pechanski, Philipp Wiesenbach, Dominic M. Schwab, Christina Kiriakou 외

Automatic extraction of medical information from clinical documents poses several challenges: high costs of required clinical expertise, limited interpretability of model predictions, restricted computational resources a…

Domain AdaptationFew-Shot Learning

Interpretability Rules: Jointly Bootstrapping a Neural Relation Extractorwith an Explanation Decoder

2021-06-01 · NAACL (TrustNLP) 2021 6 · Zheng Tang, Mihai Surdeanu

We introduce a method that transforms a rule-based relation extraction (RE) classifier into a neural one such that both interpretability and performance are achieved. Our approach jointly trains a RE classifier with a de…

DecoderRelationRelation Extraction

Exploring Interpretability in Event Extraction: Multitask Learning of a Neural Event Classifier and an Explanation Decoder

2020-07-01 · ACL 2020 6 · Zheng Tang, Gus Hahn-Powell, Mihai Surdeanu

We propose an interpretable approach for event extraction that mitigates the tension between generalization and interpretability by jointly training for the two goals. Our approach uses an encoder-decoder architecture, w…

DecoderEvent Extraction

Mind the Gap: A Generative Approach to Interpretable Feature Selection and Extraction

2015-12-01 · NeurIPS 2015 12 · Been Kim, Julie A. Shah, Finale Doshi-Velez

We present the Mind the Gap Model (MGM), an approach for interpretable feature extraction and selection. By placing interpretability criteria directly into the model, we allow for the model to both optimize parameters r…

feature selection

Rule-Extraction Methods From Feedforward Neural Networks: A Systematic Literature Review

2023-12-20 · Sara El Mekkaoui, Loubna Benabbou, Abdelaziz Berrado

Motivated by the interpretability question in ML models as a crucial element for the successful deployment of AI systems, this paper focuses on rule extraction as a means for neural networks interpretability. Through a s…

Deep LearningSystematic Literature Review