# Efficient Document Embeddings via Self-Contrastive Bregman Divergence Learning

arXiv: https://arxiv.org/abs/2305.16031 · HTML: https://mlsanity.com/paper/2305.16031/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 33 references that are in the map.
- First posted on arXiv 25 May 2023.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [BioBERT: a pre-trained biomedical language representation model for biomedical text mining](https://mlsanity.com/paper/1901.08746/) (2019)
- [Big Bird: Transformers for Longer Sequences](https://mlsanity.com/paper/2007.14062/) (2020)
- [VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning](https://mlsanity.com/paper/2105.04906/) (2021)
- [Distributed Representations of Sentences and Documents](https://mlsanity.com/paper/1405.4053/) (2014)
- [Understanding Dimensional Collapse in Contrastive Self-supervised Learning](https://mlsanity.com/paper/2110.09348/) (2021)
- [Skip-Thought Vectors](https://mlsanity.com/paper/1506.06726/) (2015)
- [LexGLUE: A Benchmark Dataset for Legal Language Understanding in English](https://mlsanity.com/paper/2110.00976/) (2021)
- [DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations](https://mlsanity.com/paper/2006.03659/) (2020)
- [Efficient Few-Shot Learning Without Prompts](https://mlsanity.com/paper/2209.11055/) (2022)
- [Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders](https://mlsanity.com/paper/2104.08027/) (2021)
- [Paragraph-level Rationale Extraction through Regularization: A case study on European Court of Human Rights Cases](https://mlsanity.com/paper/2103.13084/) (2021)
- [An Exploration of Hierarchical Attention Transformers for Efficient Long Document Classification](https://mlsanity.com/paper/2210.05529/) (2022)
- [SCD: Self-Contrastive Decorrelation for Sentence Embeddings](https://mlsanity.com/paper/2203.07847/) (2022)
- [Regulatory Compliance through Doc2Doc Information Retrieval: A case study in EU/UK legislation where text similarity has limitations](https://mlsanity.com/paper/2101.10726/) (2021)
- [Deep Bregman Divergence for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2109.07455/) (2021)
- [Overview of BioASQ 2022: The tenth BioASQ challenge on Large-Scale Biomedical Semantic Indexing and Question Answering](https://mlsanity.com/paper/2210.06852/) (2022)
- [miCSE: Mutual Information Contrastive Learning for Low-shot Sentence Embeddings](https://mlsanity.com/paper/2211.04928/) (2022)

## Built on by (most cited first, 3 of 3)

- [Patent Representation Learning via Self-supervision](https://mlsanity.com/paper/2511.10657/) (2025)
- [Revisiting Theory of Contrastive Learning for Domain Generalization](https://mlsanity.com/paper/2512.02831/) (2025)
- [Skim-Aware Contrastive Learning for Efficient Document Representation](https://mlsanity.com/paper/2512.24373/) (2025)

## Abstract (arXiv)

Learning quality document embeddings is a fundamental problem in natural language processing (NLP), information retrieval (IR), recommendation systems, and search engines. Despite recent advances in the development of transformer-based models that produce sentence embeddings with self-contrastive learning, the encoding of long documents (Ks of words) is still challenging with respect to both efficiency and quality considerations. Therefore, we train Longfomer-based document encoders using a state-of-the-art unsupervised contrastive learning method (SimCSE). Further on, we complement the baseline method -- siamese neural network -- with additional convex neural networks based on functional Bregman divergence aiming to enhance the quality of the output document representations. We show that overall the combination of a self-contrastive siamese network and our proposed neural Bregman network outperforms the baselines in two linear classification settings on three long document topic classification tasks from the legal and biomedical domains.