SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.15866 · 2024

Stochastic Amortization: A Unified Approach to Accelerate Feature and Data Attribution

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 7 functions out of this paper's own repositories and ran 6 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
chanwkimlab/amortized-attribution canonical 4 of 5
chanwkimlab/xai-amortization canonical 1 of 1
iancovert/amortized-valuation canonical 1 of 1
FunctionStatusWhere it lives
calculate_result_shapley Ran chanwkimlab/amortized-attribution/calculate_feature_attribution_using_extracted.py
code served (permissive licence) · get_code("3c70075679568849")
default_min_variance_samples Ran chanwkimlab/xai-amortization/calculate_feature_attribution_using_extracted.py
code served (permissive licence) · get_code("ddb5cac385e0f2fb")
default_variance_batches Ran chanwkimlab/amortized-attribution/calculate_feature_attribution_using_extracted.py
code served (permissive licence) · get_code("ac3ff5c34c9fc38e")
generate_metrics Ran iancovert/amortized-valuation/adv/utils.py
code served (permissive licence) · get_code("78d066869510afc7")
ncr Ran chanwkimlab/amortized-attribution/feature_attribution_methods.py
code served (permissive licence) · get_code("39ca9c029d8bb6b7")
projection_step Ran chanwkimlab/amortized-attribution/feature_attribution_methods.py
code served (permissive licence) · get_code("01daf633dbc6f213")
ShapleySampling Not yet run chanwkimlab/amortized-attribution/feature_attribution_methods.py
code served (permissive licence) · get_code("ad8720e6855c6c91")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Many tasks in explainable machine learning, such as data valuation and feature attribution, perform expensive computation for each data point and are intractable for large datasets. These methods require efficient approximations, and although amortizing the process by learning a network to directly predict the desired output is a promising solution, training such models with exact labels is often infeasible. We therefore explore training amortized models with noisy labels, and we find that this is inexpensive and surprisingly effective. Through theoretical analysis of the label noise and experiments with various models and datasets, we show that this approach tolerates high noise levels and significantly accelerates several feature attribution and data valuation methods, often yielding an order of magnitude speedup over existing approaches.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2401.15866")
get_code_for_paper("2401.15866")
have("2401.15866")

Connect an agent — have() is free.