{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T17:32:25Z","timestamp":1767893545078,"version":"3.49.0"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"15","license":[{"start":{"date-parts":[[2024,2,23]],"date-time":"2024-02-23T00:00:00Z","timestamp":1708646400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,2,23]],"date-time":"2024-02-23T00:00:00Z","timestamp":1708646400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100019290","name":"Halmstad University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100019290","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput &amp; Applic"],"published-print":{"date-parts":[[2024,5]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Few-shot meta-learning involves training a model on multiple tasks to enable it to efficiently adapt to new, previously unseen tasks with only a limited number of samples. However, current meta-learning methods assume that all tasks are closely related and belong to a common domain, whereas in practice, tasks can be highly diverse and originate from multiple domains, resulting in a multimodal task distribution. This poses a challenge for existing methods as they struggle to learn a shared representation that can be easily adapted to all tasks within the distribution. To address this challenge, we propose a meta-learning framework that can handle multimodal task distributions by conditioning the model on the current task, resulting in a faster adaptation. Our proposed method learns to encode each task and generate task embeddings that modulate the model\u2019s activations. The resulting modulated model become specialized for the current task and leads to more effective adaptation. Our framework is designed to work in a realistic setting where the mode from which a task is sampled is unknown. Nonetheless, we also explore the possibility of incorporating auxiliary information, such as the task-mode-label, to further enhance the performance of our method if such information is available. We evaluate our proposed framework on various few-shot regression and image classification tasks, demonstrating its superiority over other state-of-the-art meta-learning methods. The results highlight the benefits of learning to embed task-specific information in the model to guide the adaptation when tasks are sampled from a multimodal distribution.<\/jats:p>","DOI":"10.1007\/s00521-024-09540-1","type":"journal-article","created":{"date-parts":[[2024,2,23]],"date-time":"2024-02-23T12:02:51Z","timestamp":1708689771000},"page":"8519-8529","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Multimodal meta-learning through meta-learned task representations"],"prefix":"10.1007","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0185-5038","authenticated-orcid":false,"given":"Anna","family":"Vettoruzzo","sequence":"first","affiliation":[]},{"given":"Mohamed-Rafik","family":"Bouguelia","sequence":"additional","affiliation":[]},{"given":"Thorsteinn","family":"R\u00f6gnvaldsson","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,2,23]]},"reference":[{"key":"9540_CR1","unstructured":"Finn C, Abbeel P, Levine S (2017) Model-agnostic meta-learning for fast adaptation of deep networks. In: International conference on machine learning. PMLR, pp 1126\u20131135"},{"key":"9540_CR2","unstructured":"Vinyals O, Blundell C, Lillicrap T, Wierstra D et al (2016) Matching networks for one shot learning. Adv Neural Inf Process Syst 29"},{"key":"9540_CR3","unstructured":"Ravi S, Larochelle H (2017) Optimization as a model for few-shot learning. In: International conference on learning representations"},{"key":"9540_CR4","unstructured":"Snell J, Swersky K, Zemel R (2017) Prototypical networks for few-shot learning. Adv Neural Inf Process Syst 30"},{"key":"9540_CR5","unstructured":"Mishra N, Rohaninejad M, Chen X, Abbeel P (2017) A simple neural attentive meta-learner. In: International conference on learning representations (ICLR)"},{"key":"9540_CR6","doi-asserted-by":"crossref","unstructured":"Sung F, Yang Y, Zhang L, Xiang T, Torr PH, Hospedales TM (2018) Learning to compare: relation network for few-shot learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1199\u20131208","DOI":"10.1109\/CVPR.2018.00131"},{"key":"9540_CR7","unstructured":"Rusu AA, Rao D, Sygnowski J, Vinyals O, Pascanu R, Osindero S, Hadsell R (2018) Meta-learning with latent embedding optimization. In: International conference on learning representations"},{"key":"9540_CR8","unstructured":"Oreshkin B, Rodr\u00edguez\u00a0L\u00f3pez P, Lacoste A (2018) Tadam: task dependent adaptive metric for improved few-shot learning. Adv Neural Inf Process Syst 31"},{"key":"9540_CR9","unstructured":"Nichol A, Achiam J, Schulman J (2018) On first-order meta-learning algorithms. Preprint arXiv:1803.02999"},{"key":"9540_CR10","unstructured":"Rajeswaran A, Finn C, Kakade SM, Levine S (2019) Meta-learning with implicit gradients. Adv Neural Inf Process Syst 32"},{"key":"9540_CR11","unstructured":"Garnelo M, Rosenbaum D, Maddison C, Ramalho T, Saxton D, Shanahan M, Teh YW, Rezende D, Eslami SA (2018) Conditional neural processes. In: International conference on machine learning. PMLR, pp 1704\u20131713"},{"key":"9540_CR12","unstructured":"Vuorio R, Sun S-H, Hu H, Lim JJ (2019) Multimodal model-agnostic meta-learning via task-aware modulation. Adv Neural Inf Process Syst 32"},{"key":"9540_CR13","unstructured":"Zintgraf L, Shiarli K, Kurin V, Hofmann K, Whiteson S (2019) Fast context adaptation via meta-learning. In: International conference on machine learning. PMLR, pp 7693\u20137702"},{"key":"9540_CR14","unstructured":"Li H, Dong W, Mei X, Ma C, Huang F, Hu B-G (2019) LGM-Net: learning to generate matching networks for few-shot learning. In: International conference on machine learning. PMLR, pp 3825\u20133834"},{"key":"9540_CR15","unstructured":"Yao H, Wei Y, Huang J, Li Z (2019) Hierarchically structured meta-learning. In: International conference on machine learning. PMLR, pp 7045\u20137054"},{"key":"9540_CR16","unstructured":"Jiang W, Kwok J, Zhang Y (2022) Subspace learning for effective meta-learning. In: International conference on machine learning. PMLR, pp 10177\u201310194"},{"key":"9540_CR17","unstructured":"Jerfel G, Grant E, Griffiths T, Heller KA (2019) Reconciling meta-learning and continual learning with online mixtures of tasks. Adv Neural Inf Process Syst 32"},{"key":"9540_CR18","unstructured":"Zhou P, Zou Y, Yuan X-T, Feng J, Xiong C, Hoi S (2021) Task similarity aware meta-learning: Theory-inspired improvement on MAML. In: Uncertainty in artificial intelligence. PMLR, pp 23\u201333"},{"key":"9540_CR19","doi-asserted-by":"crossref","unstructured":"Vettoruzzo A, Bouguelia M-R, R\u00f6gnvaldsson T (2023) Meta-learning from multimodal task distributions using multiple sets of meta-parameters. In: 2023 international joint conference on neural networks (IJCNN). IEEE, pp 1\u20138","DOI":"10.1109\/IJCNN54540.2023.10191944"},{"key":"9540_CR20","unstructured":"Triantafillou E, Zhu T, Dumoulin V, Lamblin P, Evci U, Xu K, Goroshin R, Gelada C, Swersky K, Manzagol P-A (2019) Meta-dataset: a dataset of datasets for learning to learn from few examples. In: International conference on learning representations"},{"key":"9540_CR21","unstructured":"Raghu A, Raghu M, Bengio S, Vinyals O (2019) Rapid learning or feature reuse? Towards understanding the effectiveness of MAML. In: International conference on learning representations"},{"key":"9540_CR22","first-page":"14632","volume":"34","author":"M Abdollahzadeh","year":"2021","unstructured":"Abdollahzadeh M, Malekzadeh T, Cheung N-MM (2021) Revisit multimodal meta-learning through the lens of multi-task learning. Adv Neural Inf Process Syst 34:14632\u201314644","journal-title":"Adv Neural Inf Process Syst"},{"key":"9540_CR23","unstructured":"Bilen H, Vedaldi A (2017) Universal representations: the missing link between faces, text, planktons, and cat breeds. Preprint arXiv:1701.07275"},{"key":"9540_CR24","unstructured":"Requeima J, Gordon J, Bronskill J, Nowozin S, Turner RE (2019) Fast and flexible multi-task classification using conditional neural adaptive processes. Adv Neural Inf Process Syst 32"},{"key":"9540_CR25","doi-asserted-by":"crossref","unstructured":"Liu L, Hamilton WL, Long G, Jiang J, Larochelle H (2020) A universal representation transformer layer for few-shot image classification. In: International conference on learning representations","DOI":"10.1109\/ICCV48922.2021.00939"},{"key":"9540_CR26","doi-asserted-by":"crossref","unstructured":"Dvornik N, Schmid C, Mairal J (2020) Selecting relevant features from a multi-domain representation for few-shot classification. In: Computer vision\u2013ECCV 2020: 16th European conference, Glasgow, Proceedings, Part X 16. Springer, pp 769\u2013786","DOI":"10.1007\/978-3-030-58607-2_45"},{"key":"9540_CR27","doi-asserted-by":"crossref","unstructured":"Li W-H, Liu X, Bilen H (2021) Universal representation learning from multiple domains for few-shot classification. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 9526\u20139535","DOI":"10.1109\/ICCV48922.2021.00939"},{"key":"9540_CR28","unstructured":"Triantafillou E, Larochelle H, Zemel R, Dumoulin V (2021) Learning a universal template for few-shot dataset generalization. In: International conference on machine learning. PMLR, pp 10424\u201310433"},{"key":"9540_CR29","doi-asserted-by":"crossref","unstructured":"Ma Y, Zhao S, Wang W, Li Y, King I (2022) Multimodality in meta-learning: a comprehensive survey. Knowl-Based Syst 108976","DOI":"10.1016\/j.knosys.2022.108976"},{"key":"9540_CR30","doi-asserted-by":"crossref","unstructured":"Vettoruzzo A, Bouguelia M-R, Vanschoren J, R\u00f6gnvaldsson T, Santosh K (2024) Advances and challenges in meta-learning: a technical review. IEEE Transactions on Pattern Analysis and Machine Intelligence","DOI":"10.1109\/TPAMI.2024.3357847"},{"key":"9540_CR31","doi-asserted-by":"crossref","unstructured":"Perez E, Strub F, De\u00a0Vries H, Dumoulin V, Courville A (2018) Film: visual reasoning with a general conditioning layer. In: Proceedings of the AAAI conference on artificial intelligence, vol 32","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"9540_CR32","unstructured":"Lake B, Salakhutdinov R, Gross J, Tenenbaum J (2011) One shot learning of simple visual concepts. In: Proceedings of the annual meeting of the cognitive science society, vol 33"},{"key":"9540_CR33","unstructured":"Maji S, Rahtu E, Kannala J, Blaschko M, Vedaldi A (2013) Fine-grained visual classification of aircraft. Preprint arXiv:1306.5151"},{"key":"9540_CR34","unstructured":"Wah C, Branson S, Welinder P, Perona P, Belongie S (2011) The caltech-ucsd birds-200-2011 dataset. Technical Report CNS-TR-2011-001, California Institute of Technology"},{"key":"9540_CR35","doi-asserted-by":"crossref","unstructured":"Cimpoi M, Maji S, Kokkinos I, Mohamed S, Vedaldi A (2014) Describing textures in the wild. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3606\u20133613","DOI":"10.1109\/CVPR.2014.461"},{"key":"9540_CR36","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1016\/j.neunet.2012.02.016","volume":"32","author":"J Stallkamp","year":"2012","unstructured":"Stallkamp J, Schlipsing M, Salmen J, Igel C (2012) Man versus computer: benchmarking machine learning algorithms for traffic sign recognition. Neural netw 32:323\u2013332","journal-title":"Neural netw"},{"key":"9540_CR37","doi-asserted-by":"crossref","unstructured":"Nilsback M-E, Zisserman A (2008) Automated flower classification over a large number of classes. In: 2008 sixth Indian conference on computer vision, graphics & image processing. IEEE, pp 722\u2013729","DOI":"10.1109\/ICVGIP.2008.47"},{"issue":"11","key":"9540_CR38","doi-asserted-by":"publisher","first-page":"559","DOI":"10.1080\/14786440109462720","volume":"2","author":"K Pearson","year":"1901","unstructured":"Pearson K (1901) Liii. on lines and planes of closest fit to systems of points in space. Lond Edinb Dublin Philos Mag J Sci 2(11):559\u2013572. https:\/\/doi.org\/10.1080\/14786440109462720","journal-title":"Lond Edinb Dublin Philos Mag J Sci"},{"key":"9540_CR39","unstructured":"Van der Maaten L, Hinton G (2008) Visualizing data using t-SNE. J Mach Learn Res 9(11)"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-024-09540-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-024-09540-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-024-09540-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,16]],"date-time":"2024-04-16T15:23:33Z","timestamp":1713281013000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-024-09540-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,23]]},"references-count":39,"journal-issue":{"issue":"15","published-print":{"date-parts":[[2024,5]]}},"alternative-id":["9540"],"URL":"https:\/\/doi.org\/10.1007\/s00521-024-09540-1","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,23]]},"assertion":[{"value":"27 July 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 January 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 February 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}]}}