paper-with-me

홈 › Papers

On the Importance of Embedding Norms in Self-Supervised Learning

2025-02-13 · Andrew Draganov, Sharvaree Vadgama, Sebastian Damrich, Jan Niklas Böhm, Lucas Maes, Dmitry Kobak, Erik Bekkers

Self-supervised learning (SSL) allows training data representations without a supervised signal and has become an important paradigm in machine learning. Most SSL methods employ the cosine similarity between embedding vectors and hence effectively embed data on a hypersphere. While this seemingly implies that embedding norms cannot play any role in SSL, a few recent works have suggested that embedding norms have properties related to network convergence and confidence. In this paper, we resolve this apparent contradiction and systematically establish the embedding norm's role in SSL training. Using theoretical analysis, simulations, and experiments, we show that embedding norms (i) govern SSL convergence rates and (ii) encode network confidence, with smaller norms corresponding to unexpected samples. Additionally, we show that manipulating embedding norms can have large effects on convergence speed. Our findings demonstrate that SSL embedding norms are integral to understanding and optimizing network behavior.

📄 PDF Abstract BibTeX arXiv:2502.09252

Code (1)

andrew-draganov/sslembeddingnorms 공식 구현 pytorch

Tasks

Self-Supervised Learning

Similar Papers 제목 키워드 기반

Asymmetric Norms to Approximate the Minimum Action Distance

2023-12-16 · Lorenzo Steccanella, Anders Jonsson

This paper presents a state representation for reward-free Markov decision processes. The idea is to learn, in a self-supervised manner, an embedding space where distances between pairs of embedded states correspond to t…

Self-supervised speech representation and contextual text embedding for match-mismatch classification with EEG recording

2024-01-10 · Bo wang, Xiran Xu, Zechen Zhang, Haolin Zhu 외

Relating speech to EEG holds considerable importance but is challenging. In this study, a deep convolutional network was employed to extract spatiotemporal features from EEG data. Self-supervised speech representation an…

Contrastive LearningEEG

Morality is Non-Binary: Building a Pluralist Moral Sentence Embedding Space using Contrastive Learning

2024-01-30 · Jeongwoo Park, Enrico Liscio, Pradeep K. Murukannaiah

Recent advances in NLP show that language models retain a discernible level of knowledge in deontological ethics and moral norms. However, existing works often treat morality as binary, ranging from right to wrong. This …

Contrastive LearningEthicsSentenceSentence Embedding+1

Agent Alignment in Evolving Social Norms

2024-01-09 · ShiMin Li, Tianxiang Sun, Qinyuan Cheng, Xipeng Qiu

Agents based on Large Language Models (LLMs) are increasingly permeating various domains of human production and life, highlighting the importance of aligning them with human values. The current alignment of AI systems p…

Deep Metric Learning with Spherical Embedding

2020-11-05 · NeurIPS 2020 12 · Dingyi Zhang, Yingming Li, Zhongfei Zhang

Deep metric learning has attracted much attention in recent years, due to seamlessly combining the distance metric learning and deep neural network. Many endeavors are devoted to design different pair-based angular loss …

Face RecognitionMetric LearningSelf-Supervised Learning