Abstract
Several deep neural ranking models have been proposed in the recent IR literature. While their transferability to one target domain held by a dataset has been widely addressed using traditional domain adaptation strategies, the question of their cross-domain transferability is still under-studied. We study here in what extent neural ranking models catastrophically forget old knowledge acquired from previously observed domains after acquiring new knowledge, leading to performance decrease on those domains. Our experiments show that the effectiveness of neural IR ranking models is achieved at the cost of catastrophic forgetting and that a lifelong learning strategy using a cross-domain regularizer successfully mitigates the problem. Using an explanatory approach built on a regression model, we also show the effect of domain characteristics on the rise of catastrophic forgetting. We believe that the obtained results can be useful for both theoretical and practical future work in neural IR.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
According to Jialin and Qiang [40], a domain consists of at most two components: a feature space over a dataset and a marginal probability distribution within a task.
- 2.
- 3.
In our work, different domains refer to different datasets characterized by different data distributions w.r.t. to their source and content as defined in [40].
References
Adomavicius, G., Zhang, J.: Impact of data characteristics on recommender systems performance. ACM Trans. Manage. Inf. Syst. 3(1), 1–17 (2012)
Asghar, N., Mou, L., Selby, K.A., Pantasdo, K.D., Poupart, P., Jiang, X.: Progressive memory banks for incremental domain adaptation. arXiv preprint arXiv:1811.00239 (2020)
Bajaj, P., et al.: Ms marco: a human generated machine reading comprehension dataset. arXiv preprint arXiv:1611.09268 (2016)
Bengio, Y.: Deep learning of representations for unsupervised and transfer learning. In: UTLW2011, pp. 17–37 (2011)
Cai, H., Chen, H., Zhang, C., Song, Y., Zhao, X., Yin, D.: Adaptive parameterization for neural dialogue generation. In: EMNLP-IJCNLP, pp. 1793–1802 (2019)
Chen, Z., Liu, B.: Lifelong machine learning. Synth. Lect. Artif. Intell. Mach. Learn. 12(3), 1–207 (2018)
Cohen, D., Mitra, B., Hofmann, K., Croft, W.B.: Cross domain regularization for neural ranking models using adversarial learning. In: ACM SIGIR, pp. 1025–1028 (2018)
Dehghani, M., Zamani, H., Severyn, A., Kamps, J., Croft, W.B.: Neural ranking models with weak supervision. In: Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 65–74 (2017)
Deldjoo, Y., Di Noia, T., Di Sciascio, E., Merra, F.A.: How dataset characteristics affect the robustness of collaborative recommendation models. In: ACM SIGIR, pp. 951–960 (2020)
Díaz-Rodríguez, N., Lomonaco, V., Filliat, D., Maltoni, D.: Don’t forget, there is more than forgetting: new metrics for Continual Learning. arXiv preprint arXiv:1810.13166 (2018)
French, R.M.: Catastrophic forgetting in connectionist networks. Trends in Cogn. Sci. 3(4), 128–135 (1999)
Goodfellow, I.J., Mirza, M., Da, X., Courville, A.C., Bengio, Y.: An empirical investigation of catastrophic forgetting in gradient-based neural networks. arXiv preprint arXiv:1312.6211 (2014)
Gulrajani, I., Lopez-Paz, D.: In search of lost domain generalization. In: International Conference on Learning Representations (2021). https://openreview.net/forum?id=lQdXeXDoWtI
Guo, J., Fan, Y., Ai, Q., Croft, W.B.: A deep relevance matching model for ad-hoc retrieval. In: CIKM 2016, pp. 55–64. Association for Computing Machinery (2016)
Hancock, B., Bordes, A., Mazare, P.E., Weston, J.: Learning from dialogue after deployment: feed yourself, chatbot! In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 3667–3684 (2019)
Hofstätter, S., Rekabsaz, N., Eickhoff, C., Hanbury, A.: On the effect of low-frequency terms on neural-ir models. In: SIGIR, pp. 1137–1140 (2019)
Hui, K., Yates, A., Berberich, K., de Melo, G.: PACRR: a position-aware neural IR model for relevance matching. arXiv preprint arXiv:1704.03940 (2017)
Quionero-Candela, J., Sugiyama, M., Schwaighofer, A., Lawrence, N.D.: Dataset shift in machine learning. The MIT Press (2009)
Jha, R., Lovering, C., Pavlick, E.: When does data augmentation help generalization in NLP? arXiv preprint arXiv:2004.15012 (2020)
Kemker, R., McClure, M., Abitino, A., Hayes, T.L., Kanan, C.: Measuring catastrophic forgetting in neural networks. In: AAAI-18, pp. 3390–3398 (2018)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Kirkpatrick, J., et al.: Overcoming catastrophic forgetting in neural networks. Proc. Natl. Acad. Sci. 114(13), 3521–3526 (2016)
Lee, C., Cho, K., Kang, W.: Mixout: effective regularization to finetune large-scale pretrained language models. In: 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26–30, 2020. OpenReview.net (2020). https://openreview.net/forum?id=HkgaETNtDB
Lee, S.W., Kim, J.H., Jun, J., Ha, J.W., Zhang, B.T.: Overcoming catastrophic forgetting by incremental moment matching. In: NIPS2017, Curran Associates Inc., Red Hook, NY, USA, pp. 4655–4665 (2017)
Li, J., Miller, A.H., Chopra, S., Ranzato, M., Weston, J.: Learning through dialogue interactions by asking questions. In: ICLR 2017 (2017)
Li, Z., Hoiem, D.: Learning without forgetting. IEEE Trans. Pattern Anal. Mach. Intell. 12, 2935–2947 (2018)
Lin, J., Efron, M.: Overview of the trec-2013 microblog track. In: Text REtrieval Conference (TREC), Gaithersburg, Maryland, USA (2013)
Liu, T.Y.: Learning to rank for information retrieval. Found. Trends Inf. Retr. 3(3), 225–331 (2009)
Liu, X., Gao, J., He, X., Deng, L., Duh, K., Wang, Y.: Representation learning using multi-task deep neural networks for semantic classification and information retrieval. NAACL HLT 2015, 912–921 (2015)
MacAvaney, S.: OpenNIR: a complete neural ad-hoc ranking pipeline. In: WSDM 2020 (2020)
MacAvaney, S., Yates, A., Cohan, A., Goharian, N.: CEDR: contextualized embeddings for document ranking. In: ACM SIGIR, pp. 1101–1104 (2019)
d’Autume, C.D.M., Ruder, S., Kong, L., Yogatama, D.: Episodic memory in lifelong language learning. arXiv preprint arXiv:1906.01076 (2019)
Mazumder, S., Ma, N., Liu, B.: Towards a continuous knowledge learning engine for chatbots. arXiv preprint arXiv:1802.06024 (2018)
Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. In: ICLR 2013 (2013)
Mitra, B., Craswell, N.: An introduction to neural information retrieval. Found. Trend Inf. Retrieval 13(1), 1–126 (2018)
Mitra, B., Craswell, N.: An updated duet model for passage re-ranking. arXiv preprint arXiv:1903.07666 (2019)
Mosbach, M., Andriushchenko, M., Klakow, D.: On the stability of fine-tuning bert: misconceptions, explanations, and strong baselines. arXiv preprint arXiv:2006.04884 (2020)
Mou, L., Meng, Z., Yan, R., Li, G., Xu, Y., Zhang, L., Jin, Z.: How transferable are neural networks in NLP applications? In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp. 479–489 (2016)
Onal, K.D., et al.: Neural information retrieval: at the end of the early years. Inf. Retrieval J. 21, 111–182 (2017)
Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. on Knowl. and Data Eng. 22(10), 1345–1359 (Oct 2010)
Parisi, G.I., Kemker, R., Part, J.L., Kanan, C., Wermter, S.: Continual lifelong learning with neural networks: a review. Neural Netw. 113, 54–71 (2019)
Roller, S., Boureau, Y.L., Weston, J., Bordes, A., Dinan, E., Fan, A., Gunning, D., Ju, D., Li, M., Poff, S., et al.: Open-domain conversational agents: Current progress, open problems, and future directions. arXiv preprint arXiv:2006.12442 (2020)
Rusu, A.A., et al.: Progressive neural networks. arXiv preprint arXiv:1606.04671 (2016)
Soboroff, I., Ounis, I., Macdonald, C., Lin, J.J.: Overview of the TREC-2012 microblog track. In: Proceedings of The Twenty-First Text REtrieval Conference, TREC 2012. NIST Special Publication, vol. 500 p. 298 (2012)
Thompson, B., Gwinnup, J., Khayrallah, H., Duh, K., Koehn, P.: Overcoming catastrophic forgetting during domain adaptation of neural machine translation. In: NAACL, pp. 2062–2068 (2019)
Wang, L.L., et al.: Cord-19: the covid-19 open research dataset. ArXiv (2020)
Wen, S., Itti, L.: Overcoming catastrophic forgetting problem by weight consolidation and long-term memory. arXiv preprint arXiv:1805.07441 (2018)
Wiese, G., Weissenborn, D., Neves, M.: Neural domain adaptation for biomedical question answering. CoNLL 2017, 281–289 (2017)
Xiong, C., Dai, Z., Callan, J., Liu, Z., Power, R.: End-to-end neural ad-hoc ranking with kernel pooling. In: ACM SIGIR, pp. 55–64 (2017)
Xu, H., Liu, B., Shu, L., Yu, P.S.: Lifelong domain word embedding via meta-learning. In: IJCAI-18, pp. 4510–4516 (2018)
Yang, W., Lu, K., Yang, P., Lin, J.: Critically examining the “neural hype" weak baselines and the additivity of effectiveness gains from neural ranking models. In: ACM SIGIR, pp. 1129–1132 (2019)
Yang, W., Xie, Y., Tan, L., Xiong, K., Li, M., Lin, J.: Data augmentation for BERT fine-tuning in open-domain question answering. arXiv preprint arXiv:1904.06652 (2019)
Yosinski, J., Clune, J., Bengio, Y., Lipson, H.: How transferable are features in deep neural networks? In: NIPS2014, pp. 3320–3328 (2014)
Acknowledgement
We would like to thank projects ANR COST (ANR-18-CE23-0016) and ANR JCJC SESAMS (ANR-18-CE23-0001) for supporting this work.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Lovón-Melgarejo, J., Soulier, L., Pinel-Sauvagnat, K., Tamine, L. (2021). Studying Catastrophic Forgetting in Neural Ranking Models. In: Hiemstra, D., Moens, MF., Mothe, J., Perego, R., Potthast, M., Sebastiani, F. (eds) Advances in Information Retrieval. ECIR 2021. Lecture Notes in Computer Science(), vol 12656. Springer, Cham. https://doi.org/10.1007/978-3-030-72113-8_25
Download citation
DOI: https://doi.org/10.1007/978-3-030-72113-8_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-72112-1
Online ISBN: 978-3-030-72113-8
eBook Packages: Computer ScienceComputer Science (R0)