{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/pool-of-experts-realtime-querying-specialized","title":"Pool of Experts: Realtime Querying Specialized Knowledge in Massive Neural Networks","arxiv_id":"2107.01354","date":"2021-07-03","proceeding":null,"authors":["Hakbin Kim","Dong-Wan Choi"],"abstract":"In spite of the great success of deep learning technologies, training and delivery of a practically serviceable model is still a highly time-consuming process. Furthermore, a resulting model is usually too generic and heavyweight, and hence essentially goes through another expensive model compression phase to fit in a resource-limited device like embedded systems. Inspired by the fact that a machine learning task specifically requested by mobile users is often much simpler than it is supported by a massive generic model, this paper proposes a framework, called Pool of Experts (PoE), that instantly builds a lightweight and task-specific model without any training process. For a realtime model querying service, PoE first extracts a pool of primitive components, called experts, from a well-trained and sufficiently generic network by exploiting a novel conditional knowledge distillation method, and then performs our train-free knowledge consolidation to quickly combine necessary experts into a lightweight network for a target task. Thanks to this train-free property, in our thorough empirical study, PoE can build a fairly accurate yet compact model in a realtime manner, whereas it takes a few minutes per query for the other training methods to achieve a similar level of the accuracy.","url_abs":"https://arxiv.org/abs/2107.01354v1","url_pdf":"https://arxiv.org/pdf/2107.01354v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"pool-of-experts-realtime-querying-specialized","repo_url":"https://github.com/bigdata-inha/Pool-of-Experts-code","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"pool-of-experts-realtime-querying-specialized","repo_url":"https://github.com/Mind23-2/MindCode-172","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"model-compression","task_name":"Model Compression"}],"methods":[{"method_slug":null,"method_name":null},{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}