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/mindspore-ai/models/tree/master/research/recommend/Fat-DeepFFM

FAT-DeepFFM: Field Attentive Deep Field-aware Factorization Machine

https://github.com/mindspore-ai/models/tree/master/research/recommend/fibinet

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

https://github.com/monte-flora/scikit-explain

Grouped Feature Importance and Combined Features Effect Plot

https://github.com/myurasov/RISE

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

https://github.com/nalzok/tree.interpreter

A Debiased MDI Feature Importance Measure for Random Forests

https://github.com/nathanwang000/shapley-flow

Shapley Flow: A Graph-based Approach to Interpreting Model Predictions

https://github.com/nfelnlp/nfelnlp

Inseq: An Interpretability Toolkit for Sequence Generation Models

https://github.com/nliulab/sim-shapley

Understanding Global Feature Contributions With Additive Importance Measures

https://github.com/ojimenezn/ml-interpretability

A Unified Approach to Interpreting Model Predictions

https://github.com/omyokun/on-explaining-with-attention-matrices

Attention is not Explanation

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

Attention is not Explanation

https://github.com/openvinotoolkit/datumaro

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

https://github.com/openvinotoolkit/openvino_xai

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

https://github.com/p768lwy3/torecsys

FAT-DeepFFM: Field Attentive Deep Field-aware Factorization Machine

https://github.com/p768lwy3/torecsys/blob/master/torecsys/models/ctr/feature_importance_and_bilinear_feature_interaction_network.py

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

https://github.com/palatos/RISE_tf

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

https://github.com/poloclub/webshap

A Unified Approach to Interpreting Model Predictions

https://github.com/ptzhangAlg/RecAlg

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

https://github.com/pwc-1/Paper-9/tree/main/4/Patient2Vec-A-Personalized-Interpretable

Patient2Vec: A Personalized Interpretable Deep Representation of the Longitudinal Electronic Health Record

https://github.com/pwc-1/Paper-9/tree/main/7/Patient2Vec-A-Personalized-Interpretable

Patient2Vec: A Personalized Interpretable Deep Representation of the Longitudinal Electronic Health Record

https://github.com/qiaoguan/deep-ctr-prediction

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

https://github.com/rebelosa/feature-importance-neural-networks

https://github.com/recommendation-algorithm/fibinet

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

https://github.com/sarahwie/attention

Attention is not Explanation

https://github.com/sea-wyq/Fat-deepFFM

FAT-DeepFFM: Field Attentive Deep Field-aware Factorization Machine

https://github.com/shenweichen/DeepCTR

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

https://github.com/shenweichen/DeepCTR-Torch

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

https://github.com/slundberg/shap

A Unified Approach to Interpreting Model Predictions

https://github.com/smerdov/DataCollectionSystem

Collection and Validation of Psychophysiological Data from Professional and Amateur Players: a Multimodal eSports Dataset

https://github.com/subhobrata/Courses_ML_DL3

Nonparametric Feature Impact and Importance

https://github.com/successar/AttentionExplanation_Dev

Attention is not Explanation

https://github.com/suinleelab/vit-shapley

A Unified Approach to Interpreting Model Predictions

https://github.com/tangxyw/RecAlgorithm

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

https://github.com/timeseriesAI/tsai/tree/main/tsai/models

Self-attention for raw optical Satellite Time Series Classification

https://github.com/tristangomez44/metrics-saliency-maps

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

https://github.com/ustunb/reach-ml

Feature Responsiveness Scores: Model-Agnostic Explanations for Recourse

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