{"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/pareto-manifold-learning-tackling-multiple","title":"Pareto Manifold Learning: Tackling multiple tasks via ensembles of single-task models","arxiv_id":"2210.09759","date":"2022-10-18","proceeding":null,"authors":["Nikolaos Dimitriadis","Pascal Frossard","François Fleuret"],"abstract":"In Multi-Task Learning (MTL), tasks may compete and limit the performance achieved on each other, rather than guiding the optimization to a solution, superior to all its single-task trained counterparts. Since there is often not a unique solution optimal for all tasks, practitioners have to balance tradeoffs between tasks' performance, and resort to optimality in the Pareto sense. Most MTL methodologies either completely neglect this aspect, and instead of aiming at learning a Pareto Front, produce one solution predefined by their optimization schemes, or produce diverse but discrete solutions. Recent approaches parameterize the Pareto Front via neural networks, leading to complex mappings from tradeoff to objective space. In this paper, we conjecture that the Pareto Front admits a linear parameterization in parameter space, which leads us to propose \\textit{Pareto Manifold Learning}, an ensembling method in weight space. Our approach produces a continuous Pareto Front in a single training run, that allows to modulate the performance on each task during inference. Experiments on multi-task learning benchmarks, ranging from image classification to tabular datasets and scene understanding, show that \\textit{Pareto Manifold Learning} outperforms state-of-the-art single-point algorithms, while learning a better Pareto parameterization than multi-point baselines.","url_abs":"https://arxiv.org/abs/2210.09759v2","url_pdf":"https://arxiv.org/pdf/2210.09759v2.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":"pareto-manifold-learning-tackling-multiple","repo_url":"https://github.com/nik-dim/pamal","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.09759","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.09759"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/nik-dim/pamal","reach":null}],"summary":{"ran":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"7f24b9b23b50ce5f","entry":"PaMaL_GL","repo":"nik-dim/pamal","repo_kind":"official","path":"src/methods/pamal_weight_methods.py","file_url":"https://github.com/nik-dim/pamal/blob/HEAD/src/methods/pamal_weight_methods.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7f24b9b23b50ce5f"}},{"code_sha256_prefix":"87c368e49fbc3c8b","entry":"PamalWeightMethod","repo":"nik-dim/pamal","repo_kind":"official","path":"src/methods/pamal_weight_methods.py","file_url":"https://github.com/nik-dim/pamal/blob/HEAD/src/methods/pamal_weight_methods.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"87c368e49fbc3c8b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}