{"adoption": {"forks": 174, "observed_at": "2026-08-28T04:03:28.010468+00:00", "stars": 1070}, "canonical_url": "https://ross.abutalabs.com/products/multiobjectiveoptimization", "card": {"archived": true, "artifact_type": "library", "description": "Source code for Neural Information Processing Systems (NeurIPS) 2018 paper \"Multi-Task Learning as Multi-Objective Optimization\"", "domain": ["machine-learning", "deep-learning"], "enriched": true, "function": ["machine-learning", "deep-learning"], "health_score": 10, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "abandoned", "member_repos": ["isl-org/MultiObjectiveOptimization"], "name": "isl-org/MultiObjectiveOptimization", "platform": ["python", "cross-platform"], "pushed_at": "2024-09-02T19:26:42+00:00", "repo": "isl-org/MultiObjectiveOptimization", "stars": 1070, "tags": ["multi-task-learning", "multi-objective-optimization", "mgda", "gradient-descent", "pytorch", "neurips-2018", "research-code", "numpy", "optimization", "research"], "topics": [], "urls": [], "use_cases": ["implement multi-task learning as multi-objective optimization", "balance gradients across multiple loss functions in deep learning", "reproduce the MGDA_UB algorithm from the NeurIPS 2018 paper", "train models on the MultiMNIST dataset", "use Frank-Wolfe or projected gradient descent for Pareto optimization", "port gradient surgery techniques to other deep learning frameworks"], "what_it_is": "Source code for the NeurIPS 2018 paper 'Multi-Task Learning as Multi-Objective Optimization', implementing the MGDA_UB algorithm for multi-task learning. It includes PyTorch and pure NumPy implementations of Frank-Wolfe and projected gradient descent solvers, plus the MultiMNIST dataset.", "when_to_avoid": ["you need maintained software with bug fixes or updates - Intel has discontinued the project", "you need production-ready multi-task learning tooling with active community support", "you require support for recent PyTorch versions without your own patches"], "when_to_choose": ["you need the reference implementation of MGDA_UB for research or citation", "you want a framework-agnostic NumPy multi-objective gradient solver", "you are studying multi-task learning optimization methods"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/multiobjectiveoptimization", "repo": "isl-org/MultiObjectiveOptimization", "role": "main", "score": 10}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:28.010468+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:54:02.376122+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dc518480eebe208d5da95d13af6dfb87757bcd080b7a240722e246177cd06ccf", "fetched_at": "2026-08-28T04:03:28.010468+00:00", "kind": "readme", "missing": false, "url": "https://github.com/isl-org/MultiObjectiveOptimization"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:28.010468+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:54:02.376122+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dc518480eebe208d5da95d13af6dfb87757bcd080b7a240722e246177cd06ccf", "fetched_at": "2026-08-28T04:03:28.010468+00:00", "kind": "readme", "missing": false, "url": "https://github.com/isl-org/MultiObjectiveOptimization"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:54:02.376122+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dc518480eebe208d5da95d13af6dfb87757bcd080b7a240722e246177cd06ccf", "fetched_at": "2026-08-28T04:03:28.010468+00:00", "kind": "readme", "missing": false, "url": "https://github.com/isl-org/MultiObjectiveOptimization"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:28.010468+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:28.010468+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:28.010468+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:54:02.376122+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dc518480eebe208d5da95d13af6dfb87757bcd080b7a240722e246177cd06ccf", "fetched_at": "2026-08-28T04:03:28.010468+00:00", "kind": "readme", "missing": false, "url": "https://github.com/isl-org/MultiObjectiveOptimization"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:28.010468+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:28.010468+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:54:02.376122+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dc518480eebe208d5da95d13af6dfb87757bcd080b7a240722e246177cd06ccf", "fetched_at": "2026-08-28T04:03:28.010468+00:00", "kind": "readme", "missing": false, "url": "https://github.com/isl-org/MultiObjectiveOptimization"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:28.010468+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:28.010468+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:28.010468+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:54:02.376122+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dc518480eebe208d5da95d13af6dfb87757bcd080b7a240722e246177cd06ccf", "fetched_at": "2026-08-28T04:03:28.010468+00:00", "kind": "readme", "missing": false, "url": "https://github.com/isl-org/MultiObjectiveOptimization"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:28.010468+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:28.010468+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:54:02.376122+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dc518480eebe208d5da95d13af6dfb87757bcd080b7a240722e246177cd06ccf", "fetched_at": "2026-08-28T04:03:28.010468+00:00", "kind": "readme", "missing": false, "url": "https://github.com/isl-org/MultiObjectiveOptimization"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:54:02.376122+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dc518480eebe208d5da95d13af6dfb87757bcd080b7a240722e246177cd06ccf", "fetched_at": "2026-08-28T04:03:28.010468+00:00", "kind": "readme", "missing": false, "url": "https://github.com/isl-org/MultiObjectiveOptimization"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:54:02.376122+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dc518480eebe208d5da95d13af6dfb87757bcd080b7a240722e246177cd06ccf", "fetched_at": "2026-08-28T04:03:28.010468+00:00", "kind": "readme", "missing": false, "url": "https://github.com/isl-org/MultiObjectiveOptimization"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:54:02.376122+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dc518480eebe208d5da95d13af6dfb87757bcd080b7a240722e246177cd06ccf", "fetched_at": "2026-08-28T04:03:28.010468+00:00", "kind": "readme", "missing": false, "url": "https://github.com/isl-org/MultiObjectiveOptimization"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases", "archived"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 2778, "days_push": 730, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 10, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}