通过双流解耦提升数据压缩效率，降低延迟与内存占用。
Efficient Learned Data Compression via Dual-Stream Feature Decoupling
- 采用双流并行结构分离局部与全局特征，替代深层串行处理。
- 在保持最高压缩比的同时，吞吐量达1.8倍于基线模型。
- 适合需要低延迟、高效率的实时数据压缩场景。
尽管学习型数据压缩（LDC）已实现优异的压缩比，但在精确概率建模与系统效率之间取得平衡仍具挑战。传统单流架构难以同时捕捉微观语法与宏观语义特征，需深度串行堆叠，导致延迟升高。此外，异构系统受设备速度差异制约，吞吐量受限于阿姆达尔定律。为此，我们提出双流多尺度解耦器，分离局部与全局上下文，以浅层并行流取代深层串行处理，并引入分层门控精炼器实现自适应特征优化与精准概率建模。进一步设计并发流并行流水线，突破系统瓶颈，实现全流水线并行。大量实验表明，本方法在压缩比与吞吐量上均达到当前最优，同时具备最低延迟与内存开销。代码已开源：https://github.com/huidong-ma/FADE。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。