---
title: "Diverse Few-Shot Text Classification with Multiple Metrics (2018)"
description: "They propose ROBUSTTC-FSL, which works in two stages: Meta-training. 82.65 accuracy. 28 references, cited by 66 papers here."
authors: ["Mo Yu", "Xiaoxiao Guo", "Jinfeng Yi", "Shiyu Chang", "Saloni Potdar", "Yu Cheng", "Gerald Tesauro", "Haoyu Wang", "Bowen Zhou"]
year: 2018
venue: "Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)"
source: "https://aclanthology.org/N18-1109/"
doi: "10.18653/v1/n18-1109"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/yu-2018-diverse-few-shot-text-classification/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/yu-2018-diverse-few-shot-text-classification/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2018](https://md.research.elamur.ai/free/en/papers/2018/page/2/) / Diverse Few-Shot Text Classification with Multiple Metrics

# Diverse Few-Shot Text Classification with Multiple Metrics

**Authors:** [Mo Yu](https://md.research.elamur.ai/free/en/authors/mo-yu/), Xiaoxiao Guo, Jinfeng Yi, [Shiyu Chang](https://md.research.elamur.ai/free/en/authors/shiyu-chang/), Saloni Potdar, [Yu Cheng](https://md.research.elamur.ai/free/en/authors/yu-cheng/), Gerald Tesauro, Haoyu Wang and [Bowen Zhou](https://md.research.elamur.ai/free/en/authors/bowen-zhou/) · **Year:** 2018 · **Venue:** [Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)](https://md.research.elamur.ai/free/en/venues/naacl/) ([NAACL 2018](https://md.research.elamur.ai/free/en/venues/naacl/2018/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/N18-1109/) · [PDF](https://aclanthology.org/N18-1109.pdf) · [DOI 10.18653/v1/n18-1109](https://doi.org/10.18653/v1/n18-1109) · [OpenAlex](https://openalex.org/W2964316912)

**Citations:** 225 citations (OpenAlex, 2026-10-14) · [66](https://md.research.elamur.ai/free/en/papers/yu-2018-diverse-few-shot-text-classification/cited-by/) in our library, of the 141,840 papers whose bibliographies we read

## Summary
Most few-shot learning research assumes that all tasks are drawn from one large, homogeneous collection, as with Omniglot or ImageNet. Under that assumption, a single shared similarity metric works well. Real text classification workloads are different: tasks span many domains and can have different numbers of labels. For example, an enterprise cloud service may receive many small client datasets. The authors argue that one metric cannot cover this variety.

They propose ROBUSTTC-FSL, which works in two stages:
- **Meta-training.** Training tasks are grouped by how well a model trained on one task transfers to another. Missing or unreliable transfer scores are filled in with matrix completion, and the tasks are then partitioned with spectral clustering. Each cluster gets its own CNN-based Matching Network encoder, which serves as that cluster's metric.
- **Meta-testing.** For each new few-shot task, the method learns a weighted mix of the cluster metrics.

Experiments on Amazon review sentiment tasks and dialog intent tasks show clear gains over single-metric baselines such as Matching Networks and ProtoNet. This supports keeping several metrics when few-shot tasks are diverse.

## Key points
- The clustering step builds a cross-task transfer-performance matrix S, in which entry (i, j) is the accuracy of adapting task i's model to task j. S is cleaned and completed, then clustered with spectral clustering.
- Unlike earlier task-clustering methods such as ASAP-MT-LR, ROBUSTTC works with deep networks and with tasks whose label counts differ, as in intent classification.
- The sentiment tasks are Amazon review domains, each binarized at a star threshold of 2, 4, or 5. A visualization groups the training tasks into 10 clusters, and tasks with the same threshold or similar domains tend to land together.
- Every tested number of clusters beat the single-metric setting (#cluster = 1). The paper highlights 5 clusters for sentiment and 20 for intent.
- ROBUSTTC clusters slightly outperform ASAP-MT-LR clusters on sentiment (83.12 vs. 82.65 accuracy with 5 clusters). Code and data are released at github.com/Gorov/DiverseFewShot_Amazon.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [IBM](https://md.research.elamur.ai/free/en/companies/ibm/) — Company, Armonk, United States · 85 works · 66,118 citations
- [IBM Research - Thomas J. Watson Research Center](https://md.research.elamur.ai/free/en/labs/ibm-research-thomas-j-watson-research-center/) — Research institute, Yorktown Heights, United States · 41 works · 46,197 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 9,086 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 8,889 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 9,296 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 9,206 works

🧭 Topics (1): [📏 Evaluation & benchmarks](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) · 685 works

## Cite

Cite as: Mo Yu, Xiaoxiao Guo, Jinfeng Yi, Shiyu Chang, Saloni Potdar, Yu Cheng, Gerald Tesauro, Haoyu Wang and Bowen Zhou. 2018. Diverse Few-Shot Text Classification with Multiple Metrics. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{yu2018diverse,
  title = {{Diverse Few-Shot Text Classification with Multiple Metrics}},
  author = {Mo Yu, Xiaoxiao Guo, Jinfeng Yi, Shiyu Chang, Saloni Potdar, Yu Cheng, Gerald Tesauro, Haoyu Wang and Bowen Zhou},
  booktitle = {Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)},
  year = {2018},
  doi = {10.18653/v1/n18-1109},
  url = {https://doi.org/10.18653/v1/n18-1109}
}
```

- [← previous Predictive power of word surprisal for reading times is a linear function of language model quality](https://md.research.elamur.ai/free/en/papers/goodkind-2018-predictive-power-word-surprisal-reading/)
- [next → Expert, Crowdsourced, and Machine Assessment of Suicide Risk via Online Postings](https://md.research.elamur.ai/free/en/papers/shing-2018-expert-crowdsourced-machine-assessment-suicide/)
- [↑ back to papers of 2018](https://md.research.elamur.ai/free/en/papers/2018/page/2/)

## References

28 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Aviad Barzilai and Koby Crammer. 2015. Convex multi-task learning by clustering. In AISTATS. [find](https://scholar.google.com/scholar?q=Aviad+Barzilai+and+Koby+Crammer%2E+2015%2E+Convex+multi%2Dtask+learning+by+clustering%2E+In+AISTATS%2E)
2. Brenden M Lake, Ruslan Salakhutdinov, Jason Gross, and Joshua B Tenenbaum. 2011. One shot learning of simple visual concepts. In CogSci, volume 172, page 2. [find](https://scholar.google.com/scholar?q=Brenden+M+Lake%2C+Ruslan+Salakhutdinov%2C+Jason+Gross%2C+and+Joshua+B+Tenenbaum%2E+2011%2E+One+shot+learning+of+simple+visual+concepts%2E+In+CogSci%2C+volume+172%2C+page+2%2E)
3. John Blitzer, Mark Dredze, and Fernando Pereira. 2007. [Biographies, bollywood, boom-boxes and blenders: Domain adaptation for sentiment classification](https://md.research.elamur.ai/free/en/papers/blitzer-2007-biographies-bollywood-boom-boxes-blenders/). In ACL, volume 7, pages 440–447.
4. Brenden M Lake, Ruslan Salakhutdinov, and Joshua B Tenenbaum. 2015. Human-level concept learning through probabilistic program induction. Science, 350(6266):1332–1338. [find](https://scholar.google.com/scholar?q=Brenden+M+Lake%2C+Ruslan+Salakhutdinov%2C+and+Joshua+B+Tenenbaum%2E+2015%2E+Human%2Dlevel+concept+learning+through+probabilistic+program+induction%2E+Science%2C+350%286266%29%3A1332%E2%80%931338%2E)
5. Emmanuel J Candès and Terence Tao. 2010. The power of convex relaxation: Near-optimal matrix completion. IEEE Transactions on Information Theory, 56(5):2053–2080. [find](https://scholar.google.com/scholar?q=Emmanuel+J+Cande%CC%80s+and+Terence+Tao%2E+2010%2E+The+power+of+convex+relaxation%3A+Near%2Doptimal+matrix+completion%2E+IEEE+Transactions+on+Information+Theory%2C+56%285%29%3A2053%E2%80%932080%2E)
6. Fei-Fei Li, Rob Fergus, and Pietro Perona. 2006. One-shot learning of object categories. IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(4):594–611. [find](https://scholar.google.com/scholar?q=Fei%2DFei+Li%2C+Rob+Fergus%2C+and+Pietro+Perona%2E+2006%2E+One%2Dshot+learning+of+object+categories%2E+IEEE+Transactions+on+Pattern+Analysis+and+Machine+Intelligence%2C+28%284%29%3A594%E2%80%93611%2E)
7. Venkat Chandrasekaran, Sujay Sanghavi, Pablo A Parrilo, and Alan S Willsky. 2011. Rank-sparsity incoherence for matrix decomposition. SIAM Journal on Optimization, 21(2):572–596. [find](https://scholar.google.com/scholar?q=Venkat+Chandrasekaran%2C+Sujay+Sanghavi%2C+Pablo+A+Parrilo%2C+and+Alan+S+Willsky%2E+2011%2E+Rank%2Dsparsity+incoherence+for+matrix+decomposition%2E+SIAM+Journal+on+Optimization%2C+21%282%29%3A572%E2%80%93596%2E)
8. Erik G Miller, Nicholas E Matsakis, and Paul A Viola. 2000. Learning from one example through shared densities on transforms. In Computer Vision and Pattern Recognition, 2000. Proceedings. IEEE Conference on, volume 1, pages 464–471. IEEE. [find](https://scholar.google.com/scholar?q=Erik+G+Miller%2C+Nicholas+E+Matsakis%2C+and+Paul+A+Viola%2E+2000%2E+Learning+from+one+example+through+shared+densities+on+transforms%2E+In+Computer+Vision+and+Pattern+Recognition%2C+2000%2E+Proceedings%2E+IEEE+Confer)
9. Yu Cheng, Mo Yu, Xiaoxiao Guo, and Bowen Zhou. 2017. Few-shot learning with meta metric learners. In NIPS 2017 Workshop on Meta-Learning. [find](https://scholar.google.com/scholar?q=Yu+Cheng%2C+Mo+Yu%2C+Xiaoxiao+Guo%2C+and+Bowen+Zhou%2E+2017%2E+Few%2Dshot+learning+with+meta+metric+learners%2E+In+NIPS+2017+Workshop+on+Meta%2DLearning%2E)
10. Ronan Collobert, Jason Weston, Léon Bottou, Michael Karlen, Koray Kavukcuoglu, and Pavel Kuksa. 2011. [Natural language processing (almost) from scratch](https://md.research.elamur.ai/free/en/papers/collobert-2011-natural-language-processing-almost-scratch/). Journal of Machine Learning Research, 12(Aug):2493–2537.
11. Koby Crammer and Yishay Mansour. 2012. Learning multiple tasks using shared hypotheses. In Advances in Neural Information Processing Systems, pages 1475–1483. [find](https://scholar.google.com/scholar?q=Koby+Crammer+and+Yishay+Mansour%2E+2012%2E+Learning+multiple+tasks+using+shared+hypotheses%2E+In+Advances+in+Neural+Information+Processing+Systems%2C+pages+1475%E2%80%931483%2E)
12. Chelsea Finn, Pieter Abbeel, and Sergey Levine. 2017. Model-agnostic meta-learning for fast adaptation of deep networks. arXiv preprint arXiv:1703.03400. [find](https://scholar.google.com/scholar?q=Chelsea+Finn%2C+Pieter+Abbeel%2C+and+Sergey+Levine%2E+2017%2E+Model%2Dagnostic+meta%2Dlearning+for+fast+adaptation+of+deep+networks%2E+arXiv+preprint+arXiv%3A1703%2E03400%2E)
13. Rie Johnson and Tong Zhang. 2016. Supervised and semi-supervised text categorization using one-hot lstm for region embeddings. stat, 1050:7. [find](https://scholar.google.com/scholar?q=Rie+Johnson+and+Tong+Zhang%2E+2016%2E+Supervised+and+semi%2Dsupervised+text+categorization+using+one%2Dhot+lstm+for+region+embeddings%2E+stat%2C+1050%3A7%2E)
14. Armand Joulin, Edouard Grave, Piotr Bojanowski, and Tomas Mikolov. 2016. Bag of tricks for efficient text classification. arXiv preprint arXiv:1607.01759. [find](https://scholar.google.com/scholar?q=Armand+Joulin%2C+Edouard+Grave%2C+Piotr+Bojanowski%2C+and+Tomas+Mikolov%2E+2016%2E+Bag+of+tricks+for+efficient+text+classification%2E+arXiv+preprint+arXiv%3A1607%2E01759%2E)
15. Zhuoliang Kang, Kristen Grauman, and Fei Sha. 2011. Learning with whom to share in multi-task feature learning. In Proceedings of the 28th International Conference on Machine Learning (ICML-11), pages 521–528. [find](https://scholar.google.com/scholar?q=Zhuoliang+Kang%2C+Kristen+Grauman%2C+and+Fei+Sha%2E+2011%2E+Learning+with+whom+to+share+in+multi%2Dtask+feature+learning%2E+In+Proceedings+of+the+28th+International+Conference+on+Machine+Learning+%28ICML%2D11%29%2C+pages)
16. Yoon Kim. 2014. [Convolutional neural networks for sentence classification](https://md.research.elamur.ai/free/en/papers/kim-2014-convolutional-neural-networks-sentence-classification/). In EMNLP, pages 1746– 1751, Doha, Qatar. Association for Computational Linguistics.
17. Gregory Koch. 2015. Siamese neural networks for one-shot image recognition. Ph.D. thesis, University of Toronto. [find](https://scholar.google.com/scholar?q=Gregory+Koch%2E+2015%2E+Siamese+neural+networks+for+one%2Dshot+image+recognition%2E+Ph%2ED%2E+thesis%2C+University+of+Toronto%2E)
18. Abhishek Kumar and Hal Daume III. 2012. Learning task grouping and overlap in multi-task learning. In Proceedings of the 29th International Conference on Machine Learning (ICML-12). [find](https://scholar.google.com/scholar?q=Abhishek+Kumar+and+Hal+Daume+III%2E+2012%2E+Learning+task+grouping+and+overlap+in+multi%2Dtask+learning%2E+In+Proceedings+of+the+29th+International+Conference+on+Machine+Learning+%28ICML%2D12%29%2E)
19. Nikhil Mishra, Mostafa Rohaninejad, Xi Chen, and Pieter Abbeel. 2017. A simple neural attentive meta-learner. In NIPS 2017 Workshop on Meta-Learning. [find](https://scholar.google.com/scholar?q=Nikhil+Mishra%2C+Mostafa+Rohaninejad%2C+Xi+Chen%2C+and+Pieter+Abbeel%2E+2017%2E+A+simple+neural+attentive+meta%2Dlearner%2E+In+NIPS+2017+Workshop+on+Meta%2DLearning%2E)
20. Tsendsuren Munkhdalai and Hong Yu. 2017. Meta networks. arXiv preprint arXiv:1703.00837. — [arXiv:1703.00837](https://arxiv.org/abs/1703.00837) [find](https://scholar.google.com/scholar?q=Tsendsuren+Munkhdalai+and+Hong+Yu%2E+2017%2E+Meta+networks%2E+arXiv+preprint+arXiv%3A1703%2E00837%2E+%E2%80%94+%5BarXiv%3A1703%2E00837%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F1703%2E00837%29)
21. Keerthiram Murugesan, Jaime Carbonell, and Yiming Yang. 2017. Co-clustering for multitask learning. arXiv preprint arXiv:1703.00994. — [arXiv:1703.00994](https://arxiv.org/abs/1703.00994) [find](https://scholar.google.com/scholar?q=Keerthiram+Murugesan%2C+Jaime+Carbonell%2C+and+Yiming+Yang%2E+2017%2E+Co%2Dclustering+for+multitask+learning%2E+arXiv+preprint+arXiv%3A1703%2E00994%2E+%E2%80%94+%5BarXiv%3A1703%2E00994%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F1703%2E00994%29)
22. Andrew Y Ng, Michael I Jordan, and Yair Weiss. 2002. On spectral clustering: Analysis and an algorithm. In Advances in neural information processing systems, pages 849–856. [find](https://scholar.google.com/scholar?q=Andrew+Y+Ng%2C+Michael+I+Jordan%2C+and+Yair+Weiss%2E+2002%2E+On+spectral+clustering%3A+Analysis+and+an+algorithm%2E+In+Advances+in+neural+information+processing+systems%2C+pages+849%E2%80%93856%2E)
23. Jeffrey Pennington, Richard Socher, and Christopher D Manning. 2014. [Glove: Global vectors for word representation](https://md.research.elamur.ai/free/en/papers/pennington-2014-glove-global-vectors-word-representation/). In EMNLP, volume 14, pages 1532– 1543.
24. Sachin Ravi and Hugo Larochelle. 2017. Optimization as a model for few-shot learning. In International Conference on Learning Representations, volume 1, page 6. [find](https://scholar.google.com/scholar?q=Sachin+Ravi+and+Hugo+Larochelle%2E+2017%2E+Optimization+as+a+model+for+few%2Dshot+learning%2E+In+International+Conference+on+Learning+Representations%2C+volume+1%2C+page+6%2E)
25. Jake Snell, Kevin Swersky, and Richard S Zemel. 2017. Prototypical networks for few-shot learning. arXiv preprint arXiv:1703.05175. [find](https://scholar.google.com/scholar?q=Jake+Snell%2C+Kevin+Swersky%2C+and+Richard+S+Zemel%2E+2017%2E+Prototypical+networks+for+few%2Dshot+learning%2E+arXiv+preprint+arXiv%3A1703%2E05175%2E)
26. Eleni Triantafillou, Richard Zemel, and Raquel Urtasun. 2017. Few-shot learning through an information retrieval lens. In Advances in Neural Information Processing Systems, pages 2252–2262. [find](https://scholar.google.com/scholar?q=Eleni+Triantafillou%2C+Richard+Zemel%2C+and+Raquel+Urtasun%2E+2017%2E+Few%2Dshot+learning+through+an+information+retrieval+lens%2E+In+Advances+in+Neural+Information+Processing+Systems%2C+pages+2252%E2%80%932262%2E)
27. Oriol Vinyals, Charles Blundell, Tim Lillicrap, Daan Wierstra, et al. 2016. Matching networks for one shot learning. In Advances in Neural Information Processing Systems, pages 3630–3638. [find](https://scholar.google.com/scholar?q=Oriol+Vinyals%2C+Charles+Blundell%2C+Tim+Lillicrap%2C+Daan+Wierstra%2C+et+al%2E+2016%2E+Matching+networks+for+one+shot+learning%2E+In+Advances+in+Neural+Information+Processing+Systems%2C+pages+3630%E2%80%933638%2E)
28. Yu-Xiong Wang, Deva Ramanan, and Martial Hebert. 2017. Learning to model the tail. In Advances in Neural Information Processing Systems 30, pages 7032–7042. [find](https://scholar.google.com/scholar?q=Yu%2DXiong+Wang%2C+Deva+Ramanan%2C+and+Martial+Hebert%2E+2017%2E+Learning+to+model+the+tail%2E+In+Advances+in+Neural+Information+Processing+Systems+30%2C+pages+7032%E2%80%937042%2E)

*Updated 24 October 2026*