Reverse Engineering SSL (NeurIPS 2023) with Ravid Shwartz-Ziv on Talking Papers Podcast скачать в хорошем качестве

Reverse Engineering SSL (NeurIPS 2023) with Ravid Shwartz-Ziv on Talking Papers Podcast

Welcome to another exciting episode of the Talking Papers Podcast! In this episode, we delve into the fascinating world of self-supervised learning with our special guest, Ravid Shwartz-Ziv. Together, we explore and dissect their research paper titled "Reverse Engineering Self-Supervised Learning," published in NeurIPS 2023. Self-supervised learning (SSL) has emerged as a game-changing technique in the field of machine learning. However, understanding the learned representations and their underlying mechanisms has remained a challenge - until now. Ravid Shwartz-Ziv's paper provides an in-depth empirical analysis of SSL-trained representations, encompassing various models, architectures, and hyperparameters. The study uncovers a captivating aspect of the SSL training process - its inherent ability to facilitate the clustering of samples based on semantic labels. Surprisingly, this clustering is driven by the regularization term in the SSL objective. Not only does this process enhance downstream classification performance, but it also exhibits a remarkable power of data compression. The paper further establishes that SSL-trained representations align more closely with semantic classes than random classes, even across different hierarchical levels. What's more, this alignment strengthens during training and as we venture deeper into the network. Join us as we discuss the insights gained from this exceptional research. One remarkable aspect of the paper is its departure from the trend of focusing solely on outperforming competitors. Instead, it dives deep into understanding the semantic clustering effect of SSL techniques, shedding light on the underlying capabilities of the tools we commonly use. It is truly a genre of research that holds immense value. During our conversation, Ravid Shwartz-Ziv - a CDS Faculty Fellow at NYU Center for Data Science - shares their perspectives and insights, providing an enriching layer to our exploration. Interestingly, despite both of us being in Israel at the time of recording, we had never met in person, highlighting the interconnectedness and collaborative nature of the academic world. Don't miss this thought-provoking episode that promises to expand your understanding of self-supervised learning and its impact on representation learning mechanisms. Subscribe to our channel now, join the discussion, and let us know your thoughts in the comments below! TIME STAMPS --------------------- 00:00 Opening 01:16 Authors 02:23 TL;DR 03:21 Introduction 09:52 Contribution 14:18 Related work 15:49 Experiments and findings 56:37 Future work 1:02:45 What did reviewer 2 say? CONTACT --------------------- If you would like to be a guest, sponsor or share your thoughts, feel free to reach out via email: talking.papers.podcast@gmail.com 🎧Subscribe on your favourite podcast app https://talking.papers.podcast.itzikb... 📧Subscribe to our mailing list http://eepurl.com/hRznqb 🐦Follow us on Twitter   / talking_papers   🎥Subscribe to our YouTube channel https://bit.ly/3eQOgwP All links and resources are available in the blogpost: https://www.itzikbs.com/revenge_ssl #TalkingPapersPodcast #NeurIPS2023 #Research #MachineLearning #SelfSupervisedLearning #RepresentationLearning