Skip to Main content Skip to Navigation
Conference papers

Studying Catastrophic Forgetting in Neural Ranking Models

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.
Complete list of metadata
Contributor : Jesus Lovon Melgarejo Connect in order to contact the contributor
Submitted on : Tuesday, March 2, 2021 - 3:48:10 PM
Last modification on : Tuesday, November 16, 2021 - 4:33:02 AM
Long-term archiving on: : Monday, May 31, 2021 - 7:21:40 PM


Files produced by the author(s)


  • HAL Id : hal-03156630, version 1
  • ARXIV : 2101.06984


Jesús Lovón-Melgarejo, Laure Soulier, Karen Pinel-Sauvagnat, Lynda Tamine. Studying Catastrophic Forgetting in Neural Ranking Models. 43rd European Conference on Information Retrieval - ECIR 2021, Apr 2021, Lucca (on line), Italy. ⟨hal-03156630⟩



Record views


Files downloads