Papers with Code 아카이브

Feature Importance

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

0

평가표

6

보존된 평가 기록

12

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/uzaymacar/comparatively-finetuning-bert

Attention is not Explanation

https://github.com/vlue-c/PyTorch-Explanations

RISE: Randomized Input Sampling for Explanation of Black-box Models

https://github.com/vlue-c/Visual-Explanation-Methods-PyTorch

RISE: Randomized Input Sampling for Explanation of Black-box Models

https://github.com/whw199833/gbiz_torch/blob/main/example/model/FiBiNetModel_test.py

FiBiNET: Combining Feature Importance and Bilinear feature Interaction for Click-Through Rate Prediction

https://github.com/wickstrom/relax

RISE: Randomized Input Sampling for Explanation of Black-box Models

https://github.com/xiaomingaaa/GNNApp-Papers

CXPlain: Causal Explanations for Model Interpretation under Uncertainty

https://github.com/xiuyu0000/new_papers_codes/tree/main/fibinet

FiBiNET: Combining Feature Importance and Bilinear feature Interaction for Click-Through Rate Prediction

https://github.com/xue-pai/FuxiCTR

FiBiNET: Combining Feature Importance and Bilinear feature Interaction for Click-Through Rate Prediction

https://github.com/yaroslav-moiseev/evidence-based-possibly-best-practices-in-classical-ML

A Unified Approach to Interpreting Model Predictions

https://github.com/yiskw713/RISE

RISE: Randomized Input Sampling for Explanation of Black-box Models

https://github.com/yramon/ShapCounterfactual

A Unified Approach to Interpreting Model Predictions

https://github.com/zhongqiangwu960812/AI-RecommenderSystem

FiBiNET: Combining Feature Importance and Bilinear feature Interaction for Click-Through Rate Prediction

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.