Papers › A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems

A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems

15 Sep 2022arXiv:2209.07326archive 2025-07-28

Andrea Gesmundo

The traditional Machine Learning (ML) methodology requires to fragment the development and experimental process into disconnected iterations whose feedback is used to guide design or tuning choices. This methodology has multiple efficiency and scalability disadvantages, such as leading to spend significant resources into the creation of multiple trial models that do not contribute to the final solution.The presented work is based on the intuition that defining ML models as modular and extensible artefacts allows to introduce a novel ML development methodology enabling the integration of multiple design and evaluation iterations into the continuous enrichment of a single unbounded intelligent system. We define a novel method for the generation of dynamic multitask ML models as a sequence of extensions and generalizations. We first analyze the capabilities of the proposed method by using the standard ML empirical evaluation methodology. Finally, we propose a novel continuous development methodology that allows to dynamically extend a pre-existing multitask large-scale ML system while analyzing the properties of the proposed method extensions. This results in the generation of an ML model capable of jointly solving 124 image classification tasks achieving state of the art quality with improved size and compute cost.

PaperPDFCode

Syntology This paper's arXiv id is not in Syntology's Atlas id list (549,449 ids, as this build read them; the read time is in the build record), so this page links to no Syntology page for it. The list is not the whole graph; Syntology's feed shows papers as they enter the graph.

Code

google-research/google-research officialjaxSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Efficient Neural Architecture Search via Parameter Sharing (arXiv:1802.03268; that paper's own run record: 18 ran (of which 10 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 6 where Syntology's instrument failed) · 20 unverified), Milking CowMask for Semi-Supervised Image Classification (arXiv:2003.12022; that paper's own run record: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result), Neural Additive Models: Interpretable Machine Learning with Neural Nets (arXiv:2004.13912; that paper's own run record: 26 ran (of which 14 constructed an object rather than computing a result; 26 with no instrument failure: 5 honoured, 0 violated, 21 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified) and 21 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Domain GeneralizationFine-Grained Image ClassificationImage ClassificationLong-tail LearningMetric LearningScene Classificationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Generalization ImageNet-A µ2Net+ (ViT-L/16) Top-1 accuracy % 84.53 #3 of 39 Archive leaderboard report
Fine-Grained Image Classification Caltech-101 µ2Net+ (ViT-L/16) Top-1 Error Rate 4.06% #4 of 18 Archive leaderboard report
Fine-Grained Image Classification Food-101 µ2Net+ (ViT-L/16) Accuracy 91.47 #10 of 15 Archive leaderboard report
Fine-Grained Image Classification Oxford-IIIT Pets µ2Net+ (ViT-L/16) Accuracy 95.5 #3 of 19 Archive leaderboard report
Fine-Grained Image Classification Stanford Dogs µ2Net+ (ViT-L/16) Accuracy 93.5% #4 of 24 Archive leaderboard report
Image Classification CARS196 µ2Net+ (ViT-L/16) Accuracy 87.18 #1 of 1 Archive leaderboard report
Image Classification DTD µ2Net+ (ViT-L/16) Accuracy 82.23 #3 of 11 Archive leaderboard report
Image Classification EMNIST-Letters µ2Net+ (ViT-L/16) Accuracy 95.03 #7 of 11 Archive leaderboard report
Image Classification EuroSAT µ2Net+ (ViT-L/16) Accuracy (%) 99.22 #3 of 15 Archive leaderboard report
Image Classification ImageNet-Sketch µ2Net+ (ViT-L/16) Accuracy 88.6 #1 of 1 Archive leaderboard report
Image Classification Imagenette µ2Net+ (ViT-L/16) Accuracy 100 #1 of 2 Archive leaderboard report
Image Classification Malaria Dataset µ2Net+ (ViT-L/16) Acc. (test) 97.46% #2 of 3 Archive leaderboard report
Image Classification Places365 µ2Net+ (ViT-L/16) Top 1 Accuracy 59.15 #6 of 7 Archive leaderboard report
Image Classification STL-10 µ2Net+ (ViT-L/16) Percentage correct 99.64 #1 of 117 Archive leaderboard report
Image Classification Stanford Online Products µ2Net+ (ViT-L/16) Accuracy 89.47 #1 of 1 Archive leaderboard report
Image Classification cats_vs_dogs µ2Net+ (ViT-L/16) Accuracy 99.83 #1 of 1 Archive leaderboard report
Image Classification iNaturalist 2018 µ2Net+ (ViT-L/16) Top-1 Accuracy 80.97 #15 of 60 Archive leaderboard report
Long-tail Learning ImageNet-LT µ2Net+ (ViT-L/16) Top-1 Accuracy 82.5 #2 of 69 Archive leaderboard report
Scene Classification UC Merced Land Use Dataset µ2Net+ (ViT-L/16) Accuracy (%) 100 #1 of 6 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections