TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Methods/DynamicConv

DynamicConv

Dynamic Convolution

SequentialIntroduced 200011 papers
Source Paper

Description

DynamicConv is a type of convolution for sequential modelling where it has kernels that vary over time as a learned function of the individual time steps. It builds upon LightConv and takes the same form but uses a time-step dependent kernel:

DynamicConv(X,i,c)=LightConv(X,f(X_i)_h,:,i,c)\text{DynamicConv}\left(X, i, c\right) = \text{LightConv}\left(X, f\left(X\_{i}\right)\_{h,:}, i, c\right)DynamicConv(X,i,c)=LightConv(X,f(X_i)_h,:,i,c)

Papers Using This Method

Beyond Simple Concatenation: Fairly Assessing PLM Architectures for Multi-Chain Protein-Protein Interactions Prediction2025-05-26Navigating Nuance: In Quest for Political Truth2025-01-01ChatGPT v.s. Media Bias: A Comparative Study of GPT-3.5 and Fine-tuned Language Models2024-03-29M$^3$Net: Multilevel, Mixed and Multistage Attention Network for Salient Object Detection2023-09-15Transformer Based Punctuation Restoration for Turkish2023-09-15Improved Data Augmentation for Translation Suggestion2022-10-12Instances as Queries2021-05-05ConvBERT: Improving BERT with Span-based Dynamic Convolution2020-08-06Normalization of Input-output Shared Embeddings in Text Generation Models2020-01-22Low-Memory Neural Network Training: A Technical Report2019-04-24Pay Less Attention with Lightweight and Dynamic Convolutions2019-01-29