arXiv:2407.21515

Learning Effective Representations for Retrieval Using Self-Distillation with Adaptive Relevance Margins

Lukas Gienapp, Niklas Deckers, Martin Potthast, Harrisen Scells

제출 2024-07-31

원문 초록

Representation-based retrieval models, so-called biencoders, estimate the relevance of a document to a query by calculating the similarity of their respective embeddings. Current state-of-the-art biencoders are trained using an expensive training regime involving knowledge distillation from a teacher model and batch-sampling. Instead of relying on a teacher model, we contribute a novel parameter-free loss function for self-supervision that exploits the pre-trained language modeling capabilities of the encoder model as a training signal, eliminating the need for batch sampling by performing implicit hard negative mining. We investigate the capabilities of our proposed approach through extensive ablation studies, demonstrating that self-distillation can match the effectiveness of teacher distillation using only 13.5% of the data, while offering a speedup in training time between 3x and 15x compared to parametrized losses. Code and data is made openly available.

함께 살펴볼 논문

공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.

arXiv:2507.06204공통 태그 Retrieval, Language Modeling, Language Modelling공식 코드 · Papers with Code

Differential Mamba

토론

이 논문과 연결된 포럼 글이 아직 없습니다.