UNSEE: Unsupervised Non-contrastive Sentence Embeddings
Not on the map. Why?
Abstract (arXiv)
We present UNSEE: Unsupervised Non-Contrastive Sentence Embeddings, a novel approach that outperforms SimCSE in the Massive Text Embedding benchmark. Our exploration begins by addressing the challenge of representation collapse, a phenomenon observed when contrastive objectives in SimCSE are replaced with non-contrastive objectives. To counter this issue, we propose a straightforward solution known as the target network, effectively mitigating representation collapse. The introduction of the target network allows us to leverage non-contrastive objectives, maintaining training stability while achieving performance improvements comparable to contrastive objectives. Our method has achieved peak performance in non-contrastive sentence embeddings through meticulous fine-tuning and optimization. This comprehensive effort has yielded superior sentence representation models, showcasing the effectiveness of our approach.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 36 of its 44 references that are in the map. First posted on arXiv 27 Jan 2024.
Builds on
36 of 44 references.
References · 36
- 2017Attention Is All You Needcited by 59,932
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
- 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
- 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
- 2020Exploring Simple Siamese Representation Learningcited by 2,853
- 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
- 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,665
- 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
- 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,157
- 2015A large annotated corpus for learning natural language inferencecited by 1,837
24 more
- 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,818
- 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,486
- 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,393
- 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,255
- 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,216
- 2018Deep Clustering for Unsupervised Learning of Visual Featurescited by 1,020
- 2017SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluationcited by 998
- 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 705
- 2017Supervised Learning of Universal Sentence Representations from Natural Language Inference Datacited by 428
- 2022One Embedder, Any Task: Instruction-Finetuned Text Embeddingscited by 329
- 2015Skip-Thought Vectorscited by 321
- 2022Masked Siamese Networks for Label-Efficient Learningcited by 301
- 2018SentEval: An Evaluation Toolkit for Universal Sentence Representationscited by 294
- 2020Whitening for Self-Supervised Representation Learningcited by 278
- 2018An efficient framework for learning sentence representationscited by 197
- 2022DiffCSE: Difference-based Contrastive Learning for Sentence Embeddingscited by 131
- 2016Learning Distributed Representations of Sentences from Unlabelled Datacited by 90
- 2021Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoderscited by 88
- 2022PromptBERT: Improving BERT Sentence Embeddings with Promptscited by 75
- 2022Self-Supervised Learning with an Information Maximization Criterioncited by 38
- 2022Improved Universal Sentence Embeddings with Prompt-based Contrastive Learning and Energy-based Learningcited by 30
- 2021Self-Supervised Classification Networkcited by 27
- 2021Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillationscited by 20
- 2022SCD: Self-Contrastive Decorrelation for Sentence Embeddingscited by 19
Built on by
Not cited yet.