{"type":"ScholarlyArticle","title":"SEP: A General Lossless Compression Framework with Semantics Enhancement and Multi-Stream Pipelines","authors":[{"name":"Meng Wan","slug":"meng-wan","given":"Meng","family":"Wan","affiliation":""},{"name":"Rongqiang Cao","slug":"rongqiang-cao","given":"Rongqiang","family":"Cao","affiliation":""},{"name":"Yanghao Li","slug":"yanghao-li","given":"Yanghao","family":"Li","affiliation":""},{"name":"Jue Wang","slug":"jue-wang","given":"Jue","family":"Wang","affiliation":""},{"name":"Zijian Wang","slug":"zijian-wang","given":"Zijian","family":"Wang","affiliation":""},{"name":"Qi Su","slug":"qi-su","given":"Qi","family":"Su","affiliation":""},{"name":"Lei Qiu","slug":"lei-qiu","given":"Lei","family":"Qiu","affiliation":""},{"name":"Peng Shi","slug":"peng-shi","given":"Peng","family":"Shi","affiliation":""},{"name":"Yangang Wang","slug":"yangang-wang","given":"Yangang","family":"Wang","affiliation":""},{"name":"Chong Li","slug":"chong-li","given":"Chong","family":"Li","affiliation":""}],"abstract":"Deep-learning-based lossless compression is of immense importance in real-world applications, such as cold data persistence, sensor data collection, and astronomical data transmission. However, existing compressors typically model data using single-byte symbols as tokens, which makes it hard to capture the inherent correlations and cannot effectively utilize the parallel capabilities of GPU and multi-core CPU. This paper proposes SEP, a novel lossless compression framework for most time-series backbone neural networks. We first introduce a semantic enhancement module to capture the complex intra-patch relationships of binary byte streams. To improve the compression speed, we design multi-stream pipelines that dynamically assign parallel tasks to GPU streams and multi-cores. We further propose a novel GPU memory optimization strategy, which reuses GPU memory by a shared pool across streams. We conduct experiments on seven real-world datasets and the results demonstrate that our SEP framework outperforms state-of-the-art compressors with an average speed improvement of 30.0% and an average compression ratio gain of 5.1%, which is further elevated to 7.6% with the use of pre-training models. The GPU memory footprint is reduced by as high as 63.1% and by an average of 36.2%. The source code is available at: https://github.com/damonwan1/SEP.","doi":"10.24963/ijcai.2025/370","url":"https://ijcai.org/proceedings/2025/370","pdf":"https://ijcai.org/proceedings/2025/0370.pdf","markdown":"https://ijcai.org/proceedings/2025/370.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/370","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Data Mining","track":"Main Track","number":370,"pages":{"first":3326,"last":3334},"keywords":["Data Mining: DM: Applications","Machine Learning: ML: Applications"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}