Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.

PALM: Machine Learning Explanations For Iterative Debugging

Krishnan, Sanjay, Wu, Eugene · 2017 · Proceedings of the 2nd Workshop on Human-In-the-Loop Data Analytics

Abstract

When a Deep Neural Network makes a misprediction, it can be challenging for a developer to understand why. While there are many models for interpretability in terms of predictive features, it may be more natural to isolate a small set of training examples that have the greatest influence on the prediction. However, it is often the case that every training example contributes to a prediction in some way but with varying degrees of responsibility. We present Partition Aware Local Model (PALM), which is a tool that learns and summarizes this responsibility structure to aide machine learning debugging. PALM approximates a complex model (e.g., a deep neural network) using a two-part surrogate model: a meta-model that partitions the training data, and a set of sub-models that approximate the patterns within each partition. These sub-models can be arbitrarily complex to capture intricate local patterns. However, the meta-model is constrained to be a decision tree. This way the user can examine the structure of the meta-model, determine whether the rules match intuition, and link problematic test examples to responsible training data efficiently. Queries to PALM are nearly 30x faster than nearest neighbor queries for identifying relevant data, which is a key property for interactive applications.

Overview

Integrity signals

Registry

Crossref · 10.1145/3077257.3077271

Cites

13 of 13 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Show all 13 references

Research works printed but not linked: 3

  1. Andrew Crotty , Alex Galakatos , and Tim Kraska . 2014 . Tupleware: Distributed Machine Learning on Small Clusters . In IEEE Data Eng. Bull . http://sites.computer.org/debull/A14sept/p63.pdf Andrew Crotty, Alex Galakatos, and Tim Kraska. 2014. Tupleware: Distributed Machine Learning on Small Clusters. In IEEE Data Eng. Bull. http://sites.computer.org/debull/A14sept/p63.pdf
  2. Roy Fox* Sanjay Krishnan* Ken Goldberg and Ion Stoica. 2017. Multi-Layer Deep Option Discovery. In Under Review ICML. Roy Fox* Sanjay Krishnan* Ken Goldberg and Ion Stoica. 2017. Multi-Layer Deep Option Discovery. In Under Review ICML.
  3. Tameru Hailesilassie . 2016. Rule Extraction Algorithm for Deep Neural Networks: A Review. arXiv preprint arXiv:1610.05267 ( 2016 ). Tameru Hailesilassie. 2016. Rule Extraction Algorithm for Deep Neural Networks: A Review. arXiv preprint arXiv:1610.05267 (2016). · arXiv

Cited by

See all 82

Metadata

Authors
Krishnan, S., & Wu, E.
Affiliations
  • University of California, Berkeley (US)
  • Columbia University (US)
Venue
Proceedings of the 2nd Workshop on Human-In-the-Loop Data Analytics
Publisher
ACM
Published
2017-05-14
Pages
1-6
OpenAlex
W2614087582
Cited by
81
References
13
Citations by year
2026: 2 · 2025: 5 · 2024: 15 · 2023: 5 · 2022: 10 · 2021: 15 · 2020: 11 · 2019: 11 · 2018: 4 · 2017: 2
FWCI
3.49
Type
conference paper
Language
en
Open access
closed
Locations
Workshop on Human-In-the-Loop Data Analytics (HILDA) (publishedVersion)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
  • Physical Sciences › Computer Science › Software › Software Testing and Debugging Techniques
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Data Classification
Keywords
interpretability, training data influence, surrogate models, deep neural network

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: PALM: Machine Learning Explanations For Iterative Debugging. https://app.cochat.ai/papers/10.1145/3077257.3077271
The paper
Krishnan, S., & Wu, E. (2017). PALM: Machine Learning Explanations For Iterative Debugging. Proceedings of the 2nd Workshop on Human-In-the-Loop Data Analytics. https://doi.org/10.1145/3077257.3077271

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.