Papers › Interpreting and improving deep-learning models with reality checks

Interpreting and improving deep-learning models with reality checks

16 Aug 2021arXiv:2108.06847archive 2025-07-28

Chandan Singh, Wooseok Ha, Bin Yu

Recent deep-learning models have achieved impressive predictive performance by learning complex functions of many variables, often at the cost of interpretability. This chapter covers recent work aiming to interpret models by attributing importance to features and feature groups for a single prediction. Importantly, the proposed attributions assign importance to interactions between features, in addition to features in isolation. These attributions are shown to yield insights across real-world domains, including bio-imaging, cosmology image and natural-language processing. We then show how these attributions can be used to directly improve the generalization of a neural network or to distill it into a simple model. Throughout the chapter, we emphasize the use of reality checks to scrutinize the proposed interpretation techniques.

PaperPDFCode

Syntology This paper's arXiv id is not in Syntology's Atlas id list (549,449 ids, as this build read them; the read time is in the build record), so this page links to no Syntology page for it. The list is not the whole graph; Syntology's feed shows papers as they enter the graph.

Code

Yu-Group/adaptive-wavelet-distillation officialpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Adaptive wavelet distillation from neural networks through interpretations (arXiv:2107.09145; that paper's own run record: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
csinva/hierarchical-dnn-interpretations officialpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Interpretable machine learning: definitions, methods, and applications (arXiv:1901.04592; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 16 unverified); nothing checks that they implement this paper's method. report
csinva/transformation-importance officialpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Transformation Importance with Applications to Cosmology (arXiv:2003.01926; that paper's own run record: 3 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
laura-rieger/deep-explanation-penalization officialpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Interpretations are useful: penalizing explanations to align neural networks with... (arXiv:1909.13584; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Deep Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections