AI Paper Atlas

Research map / Time series / Foundation models for time series

Dynamic Sparse Network for Time Series Classification: Learning What to “See”

Qiao Xiao, Boqian Wu, Yu Zhang, Shiwei Liu, Mykola Pechenizkiy, Elena Mocanu, Decebal Constantin Mocanu

NeurIPS 2022 · Time series › Foundation models for time series · approach: Time series representation learning · 13 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use sparse kernels (S=80%) instead of dense kernels (ablation)DSN · EEG2accuracy (%): 89.60 -> 99.10Improved
use sparse kernels (S=80%) instead of dense kernels (ablation)DSN · HARaccuracy (%): 96.06 -> 96.82Improved
use sparse kernels (S=80%) instead of dense kernels (ablation)DSN · Daily Sportaccuracy (%): 99.19 -> 99.19No clear effect
increase sparsity from 50% to 80% (ablation)DSN · EEG2accuracy (%): 96.23 -> 99.10Improved
increase sparsity from 80% to 90% (ablation)DSN · EEG2accuracy (%): 99.10 -> 98.90No clear effect
add kernel grouping to dynamic sparse training (ablation)DSN · EEG2accuracy (%): 96.77 -> 97.87 (S=60%), 97.27 -> 98.70 (S=70%), 98.77 -> 99.10 (S=80%)Improved
add kernel grouping to dynamic sparse training (ablation)DSN · HARaccuracy (%): 96.87 -> 96.53 (S=60%), 96.52 -> 97.14 (S=70%), 96.79 -> 96.82 (S=80%)Mixed
add kernel grouping to dynamic sparse training (ablation)DSN · Daily Sportaccuracy (%): 99.23 -> 99.27 (S=60%), 99.25 -> 99.20 (S=70%), 99.28 -> 99.19 (S=80%)No clear effect
dynamic sparse training instead of fixed topology (DSN fix) (ablation)DSN · UCR 85 archiveaccuracyImproved
grow weights by gradient (RigL-style) instead of randomly (ablation)DSN · UCR 85 archiveaccuracyNo clear effect
DSN versus OS-CNN, InceptionTime, ResNetDSN · UCR 85 archivedatasets won: 53-29-3 vs ResNet; 40-40-5 vs InceptionTime; 49-33-3 vs OS-CNNImproved
DSN versus MLSTM-FCN on Daily SportDSN · Daily Sportaccuracy (%): 99.65 vs 99.19Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy