Methods › Sequential › Temporal Convolutions › Causal Convolution
Causal Convolution
Introduced by Aaron van den Oord et al. in WaveNet: A Generative Model for Raw Audio
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Causal convolutions are a type of convolution used for temporal data which ensures the model cannot violate the ordering in which we model the data: the prediction p(xₜ₊₁ | x₁, …, xₜ) emitted by the model at timestep t cannot depend on any of the future timesteps xₜ₊₁, xₜ₊₂, …, x_T. For images, the equivalent of a causal convolution is a masked convolution which can be implemented by constructing a mask tensor and doing an element-wise multiplication of this mask with the convolution kernel before applying it. For 1-D data such as audio one can more easily implement this by shifting the output of a normal convolution by a few timesteps.
Papers archive 2025-07-28
27 shown of 27, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Rolling Forward: Enhancing LightGCN with Causal Graph Convolution for Credit Bond Recommendation 18 Mar 2025 · 0 repositories · arXiv:2503.14213
-
Improved Video VAE for Latent Video Diffusion Model 10 Nov 2024 · 0 repositories · arXiv:2411.06449
-
Causal Discovery from Time-Series Data with Short-Term Invariance-Based Convolutional Neural Networks 15 Aug 2024 · 1 repository · arXiv:2408.08023
-
CausalFormer: An Interpretable Transformer for Temporal Causal Discovery 24 Jun 2024 · 1 repository · arXiv:2406.16708Syntology ran 7 of 7 samples · 0 unverified · 7 pointer-only (licence)
-
ACCO: Automated Causal CNN Scheduling Optimizer for Real-Time Edge Accelerators 11 Jun 2024 · 1 repository · arXiv:2406.07161
-
MambaTS: Improved Selective State Space Models for Long-term Time Series Forecasting 26 May 2024 · 1 repository · arXiv:2405.16440Syntology ran 5 of 7 samples · 2 unverified
-
Localization of Dummy Data Injection Attacks in Power Systems Considering Incomplete Topological Information: A Spatio-Temporal Graph Wavelet Convolutional Neural Network Approach 27 Jan 2024 · 0 repositories · arXiv:2401.15321
-
Ultra-short-term multi-step wind speed prediction for wind farms based on adaptive noise reduction technology and temporal convolutional network 27 Nov 2023 · 1 repository · arXiv:2311.16198
-
DualVC 2: Dynamic Masked Convolution for Unified Streaming and Non-Streaming Voice Conversion 27 Sep 2023 · 0 repositories · arXiv:2309.15496
-
Learning minimal representations of stochastic processes with variational autoencoders 21 Jul 2023 · 1 repository · arXiv:2307.11608
-
Sequence Modeling with Multiresolution Convolutional Memory 2 May 2023 · 1 repository · arXiv:2305.01638Syntology ran 3 of 8 samples · 5 unverified
-
Dynamic Chunk Convolution for Unified Streaming and Non-Streaming Conformer ASR 18 Apr 2023 · 0 repositories · arXiv:2304.09325
-
HGWaveNet: A Hyperbolic Graph Neural Network for Temporal Link Prediction 14 Apr 2023 · 1 repository · arXiv:2304.07302
-
Real-Time Target Sound Extraction 4 Nov 2022 · 1 repository · arXiv:2211.02250Syntology ran 3 of 7 samples · 4 unverified
-
Towards Fast Single-Trial Online ERP based Brain-Computer Interface using dry EEG electrodes and neural networks: a pilot study 4 Nov 2022 · 2 repositories · arXiv:2211.10352
-
GM-TCNet: Gated Multi-scale Temporal Convolutional Network using Emotion Causality for Speech Emotion Recognition 28 Oct 2022 · 1 repository · arXiv:2210.15834
-
Locality-aware Attention Network with Discriminative Dynamics Learning for Weakly Supervised Anomaly Detection 11 Aug 2022 · 0 repositories · arXiv:2208.05636
-
HarmoF0: Logarithmic Scale Dilated Convolution For Pitch Estimation 2 May 2022 · 1 repository · arXiv:2205.01019
-
PGCN: Progressive Graph Convolutional Networks for Spatial-Temporal Traffic Forecasting 18 Feb 2022 · 0 repositories · arXiv:2202.08982
-
Streaming Transformer Transducer Based Speech Recognition Using Non-Causal Convolution 7 Oct 2021 · 0 repositories · arXiv:2110.05241
-
SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction 17 Jun 2021 · 6 repositories · arXiv:2106.09305Syntology ran 1 of 6 samples · 5 unverified
-
Transformer-Transducer: End-to-End Speech Recognition with Self-Attention 28 Oct 2019 · 1 repository · arXiv:1910.12977
-
MC\^2: Multi-perspective Convolutional Cube for Conversational Machine Reading Comprehension 1 Jul 2019 · 0 repositories
-
Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting 29 Jun 2019 · 2 repositories · arXiv:1907.00235
-
ConvS2S-VC: Fully convolutional sequence-to-sequence voice conversion 5 Nov 2018 · 0 repositories · arXiv:1811.01609
-
SeriesNet:A Generative Time Series Forecasting Model 23 Aug 2018 · 0 repositories
-
WaveNet: A Generative Model for Raw Audio 12 Sep 2016 · 62 repositories · arXiv:1609.03499Syntology ran 41 of 103 samples · 62 unverified · 25 pointer-only (licence)
Tasks archive 2025-07-28
20 shown of 51 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
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