CoChat

Skipping RNN State Updates without Retraining the Original Model

Tao, Jin, Thakker, Urmish, Dasika, Ganesh, Beu, Jesse · 2019 · Proceedings of the 1st Workshop on Machine Learning on Edge in Sensor Systems
Cited by 19

The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.

Abstract

Recurrent Neural Networks (RNNs) break a time-series input (or a sentence) into multiple time-steps (or words) and process it one time-step (word) at a time. However, not all of these time-steps (words) need to be processed to determine the final output accurately. Prior work has exploited this intuition by incorporating an additional predictor in front of the RNN model to prune time-steps that are not relevant. However, they jointly train the predictor and the RNN model, allowing one to learn from the mistakes of the other. In this work we present a method to skip RNN time-steps without retraining or fine tuning the original RNN model. Using an ideal predictor, we show that even without retraining the original model, we can train a predictor to skip 45% of steps for the SST dataset and 80% of steps for the IMDB dataset without impacting the model accuracy. We show that the decision to skip is not easy by comparing against 5 different baselines based on solutions derived from domain knowledge. Finally, we present a case study about the cost and accuracy benefits of realizing such a predictor. This realistic predictor on the SST dataset is able to reduce the computation by more than 25% with at most 0.3% loss in accuracy while being 40× smaller than the original RNN model.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1145/3362743.3362965

Cites

3 of 3 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 3 references

Cited by

See all 19

Metadata

Authors
Tao, J., Thakker, U., Dasika, G., & Beu, J.
Venue
Proceedings of the 1st Workshop on Machine Learning on Edge in Sensor Systems
Publisher
ACM
Published
2019-11-10
Pages
31-36
OpenAlex
W2982011653
Cited by
19
References
3
FWCI
1.18
Type
conference paper
Language
en
Open access
closed

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: Skipping RNN State Updates without Retraining the Original Model. https://app.cochat.ai/papers/10.1145/3362743.3362965
The paper
Tao, J., Thakker, U., Dasika, G., & Beu, J. (2019). Skipping RNN State Updates without Retraining the Original Model. Proceedings of the 1st Workshop on Machine Learning on Edge in Sensor Systems. https://doi.org/10.1145/3362743.3362965

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.