Paper Reading AI Learner

$PredDiff$: Explanations and Interactions from Conditional Expectations

2021-02-26 14:46:47
Stefan Blücher, Nils Strodthoff
arXiv_AI
       
Abstract

$PredDiff$ is a model-agnostic, local attribution method that is firmly rooted in probability theory. Its simple intuition is to measure prediction changes when marginalizing out feature variables. In this work, we clarify properties of $PredDiff$ and put forward several extensions of the original formalism. Most notably, we introduce a new measure for interaction effects. Interactions are an inevitable step towards a comprehensive understanding of black-box models. Importantly, our framework readily allows to investigate interactions between arbitrary feature subsets and scales linearly with their number. We demonstrate the soundness of $PredDiff$ relevances and interactions both in the classification and regression setting. To this end, we use different analytic, synthetic and real-world datasets.

Abstract (translated)

URL

https://arxiv.org/abs/2102.13519

PDF

https://arxiv.org/pdf/2102.13519.pdf

Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot