# Efficient Learned Data Compression via Dual-Stream Feature Decoupling

arXiv: https://arxiv.org/abs/2604.07239 · HTML: https://mlsanity.com/paper/2604.07239/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 47 references that are in the map.
- First posted on arXiv 8 Apr 2026.

## Builds on (most cited first, 12 of 12)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [Language Modeling with Gated Convolutional Networks](https://mlsanity.com/paper/1612.08083/) (2016)
- [DeepZip: Lossless Data Compression using Recurrent Neural Networks](https://mlsanity.com/paper/1811.08162/) (2018)
- [A Fast Transformer-based General-Purpose Lossless Compressor](https://mlsanity.com/paper/2203.16114/) (2022)
- [Sub-Linear Memory: How to Make Performers SLiM](https://mlsanity.com/paper/2012.11346/) (2020)
- [SDRBench: Scientific Data Reduction Benchmark for Lossy Compressors](https://mlsanity.com/paper/2101.03201/) (2021)
- [PMKLC: Parallel Multi-Knowledge Learning-based Lossless Compression for Large-Scale Genomics Database](https://mlsanity.com/paper/2507.12805/) (2025)
- [EDPC: Accelerating Lossless Compression via Lightweight Probability Models and Decoupled Parallel Dataflow](https://mlsanity.com/paper/2507.18969/) (2025)

## Abstract (arXiv)

While Learned Data Compression (LDC) has achieved superior compression ratios, balancing precise probability modeling with system efficiency remains challenging. Crucially, uniform single-stream architectures struggle to simultaneously capture micro-syntactic and macro-semantic features, necessitating deep serial stacking that exacerbates latency. Compounding this, heterogeneous systems are constrained by device speed mismatches, where throughput is capped by Amdahl's Law due to serial processing. To this end, we propose a Dual-Stream Multi-Scale Decoupler that disentangles local and global contexts to replace deep serial processing with shallow parallel streams, and incorporate a Hierarchical Gated Refiner for adaptive feature refinement and precise probability modeling. Furthermore, we design a Concurrent Stream-Parallel Pipeline, which overcomes systemic bottlenecks to achieve full-pipeline parallelism. Extensive experiments demonstrate that our method achieves state-of-the-art performance in both compression ratio and throughput, while maintaining the lowest latency and memory usage. The code is available at https://github.com/huidong-ma/FADE.