Published December 6, 2020 | Version v1
Conference paper Open

Structured Pruning of LSTMs via Eigenanalysis and Geometric Median for Mobile Multimedia and Deep Learning Applications

  • 1. CERTH-ITI

Description

In this paper, a novel structured pruning approach for learning efficient long short-term memory (LSTM) network architectures is proposed. More specifically, the eigenvalues of the covariance matrix associated with the responses of each LSTM layer are computed and utilized to quantify the layers’ redundancy and automatically obtain an individual pruning rate for each layer. Subsequently, a Geometric Median based (GM-based) criterion is used to identify and prune in a structured way the most redundant LSTM units, realizing the pruning rates derived in the previous step. The experimental evaluation on the Penn Treebank text corpus and the large-scale YouTube-8M audio-video dataset for the tasks of word-level prediction and visual concept detection, respectively, shows the efficacy of the proposed approach. Source code is made publicly available at: https://github.com/bmezaris/lstm_structured_pruning_geometric_median

Files

ism2020_preprint.pdf

Files (253.0 kB)

Name Size Download all
md5:09f01069fd210ff9f0114eb054d79f93
253.0 kB Preview Download

Additional details

Funding

ReTV – Enhancing and Re-Purposing TV Content for Trans-Vector Engagement 780656
European Commission