{"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/hyper-x-a-unified-hypernetwork-for-multi-task","title":"Hyper-X: A Unified Hypernetwork for Multi-Task Multilingual Transfer","arxiv_id":"2205.12148","date":"2022-05-24","proceeding":null,"authors":["Ahmet Üstün","Arianna Bisazza","Gosse Bouma","Gertjan van Noord","Sebastian Ruder"],"abstract":"Massively multilingual models are promising for transfer learning across tasks and languages. However, existing methods are unable to fully leverage training data when it is available in different task-language combinations. To exploit such heterogeneous supervision, we propose Hyper-X, a single hypernetwork that unifies multi-task and multilingual learning with efficient adaptation. This model generates weights for adapter modules conditioned on both tasks and language embeddings. By learning to combine task and language-specific knowledge, our model enables zero-shot transfer for unseen languages and task-language combinations. Our experiments on a diverse set of languages demonstrate that Hyper-X achieves the best or competitive gain when a mixture of multiple resources is available, while being on par with strong baselines in the standard scenario. Hyper-X is also considerably more efficient in terms of parameters and resources compared to methods that train separate adapters. Finally, Hyper-X consistently produces strong results in few-shot scenarios for new languages, showing the versatility of our approach beyond zero-shot transfer.","url_abs":"https://arxiv.org/abs/2205.12148v3","url_pdf":"https://arxiv.org/pdf/2205.12148v3.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":"hyper-x-a-unified-hypernetwork-for-multi-task","repo_url":"https://github.com/ahmetustun/hyperx","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[{"method_slug":"adapter","method_name":"Adapter"},{"method_slug":"hypernetwork","method_name":"HyperNetwork"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2205.12148","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}