Papers › Squeezed Very Deep Convolutional Neural Networks for Text Classification

Squeezed Very Deep Convolutional Neural Networks for Text Classification

28 Jan 2019arXiv:1901.09821archive 2025-07-28

Andréa B. Duque, Luã Lázaro J. Santos, David Macêdo, Cleber Zanchettin

Most of the research in convolutional neural networks has focused on increasing network depth to improve accuracy, resulting in a massive number of parameters which restricts the trained network to platforms with memory and processing constraints. We propose to modify the structure of the Very Deep Convolutional Neural Networks (VDCNN) model to fit mobile platforms constraints and keep performance. In this paper, we evaluate the impact of Temporal Depthwise Separable Convolutions and Global Average Pooling in the network parameters, storage size, and latency. The squeezed model (SVDCNN) is between 10x and 20x smaller, depending on the network depth, maintaining a maximum size of 6MB. Regarding accuracy, the network experiences a loss between 0.4% and 1.3% and obtains lower latencies compared to the baseline model.

PaperPDFCode

Code

lazarotm/SVDCNN mentioned in paperpytorch 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.

Code Syntology ran Syntology

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

Tasks

ClassificationGeneral ClassificationSentiment AnalysisText Classificationtext-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Sentiment Analysis Yelp Binary classification SVDCNN Error 4.74 #19 of 20 Archive leaderboard report
Sentiment Analysis Yelp Fine-grained classification SVDCNN Error 46.80 #17 of 17 Archive leaderboard report
Text Classification AG News SVDCNN Error 9.45 #18 of 24 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Average PoolingGlobal Average Pooling

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