The DOI matches its Crossref record; 64 of the 67 references it cites were found in a registry or an index.
Multitask Learning
Open accessOverview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“There are two main goals in continual learning: maintaining stability and maintaining plasticity88–91.”
From Loss of plasticity in deep continual learning (2024) · cites this paper as [88]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“pretraining followed by task-specific fine-tuning can improve generalization (Caruana, 1997)”
From Masked Autoencoder Pretraining on Strong-Lensing Images for Joint Dark-Matter Model Classification and Super-Resolution (2025) · cites this paper as Caruana, 1997
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“These studies hint that a common representation of lensing data can benefit various tasks”
From Masked Autoencoder Pretraining on Strong-Lensing Images for Joint Dark-Matter Model Classification and Super-Resolution (2025) · cites this paper as Caruana, 1997
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The motivation for the proposed architecture is that the multi-task learning (Caruana, 1997) of related tasks could improve the generalization capability by suppressing the shared encoder from learning any taskspecific features.”
From Robust multi-task learning and online refinement for spacecraft pose estimation across domain gap (2024) · cites this paper as Caruana, 1997
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Inspired by Caruana, they employed shared layers to extract hidden features of different battery states and task-specific layers to achieve accurate multi-state monitoring[110].”
From Advancements in the estimation of the state of charge of lithium-ion battery: a comprehensive review of traditional and deep learning approaches (2025) · cites this paper as [110]
The cited source says what the claim attributes to it.
In the citing paper
“For this reason, ILP naturally supports lifelong (Silver et al., 2013), multi-task (Caruana, 1997), and transfer learning (Torrey & Shavlik, 2009), which are considered essential for human-like AI (Lake et al., 2016).”
From Inductive Logic Programming At 30: A New Introduction (2022) · cites this paper as Caruana, 1997
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“Vision Transformers are commonly evaluated using the sliding window procedure from MMSegmentation [59] (e.g., [10, 101, 103]).”
From MultiMAE: Multi-modal Multi-task Masked Autoencoders (2022) · cites this paper as [10]
Experimental — accuracy not yet measuredIn the citing paper
“Within this formulation, our multi-task supervised contrastive framework provides a unified optimization process in which the classification and contrastive objectives jointly guide the encoder to capture activity semantics while suppressing user-specific variations [37].”
From Towards User-Generalizable Wearable-Sensor-Based Human Activity Recognition: A Multi-Task Contrastive Learning Approach (2025) · cites this paper as [37]
In the citing paper
“In addition, using multi-task learning 147 to train models to perform a variety of tasks rather than one narrowly defined task, such as multi-cancer detection from histopathology images 148 , makes them more generally useful and often more robust.”
From Deep learning-enabled medical computer vision (2021) · cites this paper as [147]
In the citing paper
“To increase the robustness Multi-Task Learning (MTL) uses the information in training data as an inductive bias to perform multiple tasks in parallel, and the learning of one task improves the understanding of others through shared representations [82].”
From A mini-review on perturbation modelling across single-cell omic modalities (2024) · cites this paper as [82]
In the citing paper
“Hard parameter sharing [110]: It consists of extracting a generic representation for different tasks using the same parameters. It is usually applied to avoid overfitting problems.”
From A survey on deep multimodal learning for computer vision: advances, trends, applications, and datasets (2022) · cites this paper as [110]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Learning representations by back-propagating errors
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986) · Nature · doi:10.1038/323533a0 · Cited by 31,892
(1992) · Cited by 23,431
Quinlan, J. R. (1986) · Machine Learning · doi:10.1007/bf00116251 · Cited by 21,439
Statistical Analysis With Missing Data
Lahiff, M., Little, R. J. A., & Rubin, D. B. (1989) · Journal of the American Statistical Association · doi:10.2307/2289883 · Cited by 17,385
Backpropagation Applied to Handwritten Zip Code Recognition
LeCun, Y., Boser, B., Denker, J. S., Henderson, D., Howard, R. E., Hubbard, W., & Jackel, L. D. (1989) · Neural Computation · doi:10.1162/neco.1989.1.4.541 · Cited by 11,891
Statistical Analysis With Missing Data
Ghosh, S., Little, R. J. A., & Rubin, D. B. (1988) · Technometrics · doi:10.2307/1269814 · Cited by 4,730
Causation, Prediction, and Search
Spirtes, P., Glymour, C., & Scheines, R. (1993) · Lecture Notes in Statistics · doi:10.1007/978-1-4612-2748-9 · Cited by 4,617
Causation, Prediction, and Search
Spirtes, P., Glymour, C., & Scheines, R. (2001) · doi:10.7551/mitpress/1754.001.0001 · Cited by 4,521
A Bayesian Method for the Induction of Probabilistic Networks from Data
Cooper, G. F., & Herskovits, E. H. (1992) · Machine Learning · doi:10.1023/a:1022649401552 · Cited by 4,241
Hierarchical Mixtures of Experts and the EM Algorithm
Jordan, M. I., & Jacobs, R. A. (1994) · Neural Computation · doi:10.1162/neco.1994.6.2.181 · Cited by 2,786
Flagged first, then by citations
3 of the 67 references couldn’t be matched to a known paper.
Research works printed but not linked: 5
- Caruana, R. (1994).”Multitask Connectionist Learning,” Proceedings of the 1993 Connectionist Models Summer School, pp. 372-379.
- Caruana, R. (1997). “Multitask Learning,” Ph.D. Thesis, School of Computer Science, Carnegie Mellon University.
- de Sa, V. R. (1994). “Learning Classification with Unlabelled Data,” Advances in Neural Information Processing Systems 6, (Proceedings of NIPS-93), pp. 112-119.
- Liu, H. & Setiono, R. (1996). “A Probibilistic Approach to Feature Selection—A Filter Solution,” Proceedings of the 13th International Conference on Machine Learning,ICML-96, Bari, Italy, pp. 319-327.
- Martin, J. D. (1994). “Goal-directed Clustering,” Proceedings of the 1994 AAAI Spring Symposium on Goal-directed Learning.
Cited by
Sorted by citations
Girshick, R. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.169 · Cited by 28,105
Pan, S. J., & Yang, Q. (2010) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2009.191 · Cited by 23,387
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Deep learning in neural networks: an overview
Schmidhuber, J. (2015) · Neural Networks · doi:10.1016/j.neunet.2014.09.003 · Cited by 18,570
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929
Metadata
- Authors
- Caruana, R.
- Affiliations
- Carnegie Mellon University (US)
- Corresponding author
- Caruana, Rich
- ORCID
- Caruana, Rich
- Venue
- Machine Learning
- Published
- 1997-07
- Volume
- 28
- Issue
- 1
- Pages
- 41-75
- ISSN
- 0885-6125 (ISSN-L)
- 1573-0565
- OpenAlex
- W2913340405
- Cited by
- 6,636
- References
- 67
- Citations by year
- 2026: 532 · 2025: 617 · 2024: 510 · 2023: 505 · 2022: 565 · 2021: 803 · 2020: 767 · 2019: 563 · 2018: 323 · 2017: 259 · 2016: 188 · 2015: 151 · 2014: 124 · 2013: 89 · 2012: 136
- FWCI
- 5.68
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Licence
- Locations
- Machine Learning (publishedVersion)
- Funders
- National Science Foundation (9315428)
- University of Pittsburgh
- Advanced Research Projects Agency
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Algorithms
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Keywords
- multi-task learning, inductive transfer, inductive bias, shared representations, task relatedness, k-nearest neighbors, kernel regression, case-based learning, decision tree
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
