Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Tri-contrastive Learning: Identifiable Representation Learning with Automatic Feature Importance Discovery
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v2-stream-005-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v2-stream-005-alpha.b-cdn.net
      • sl-yoda-v2-stream-005-beta.b-cdn.net
      • 1034628162.rsc.cdn77.org
      • 1409346856.rsc.cdn77.org
      • Subtitles
      • Off
      • English
      • Playback rate
      • Quality
      • Subtitles size
      • Large
      • Medium
      • Small
      • Mode
      • Video Slideshow
      • Audio Slideshow
      • Slideshow
      • Video
      My playlists
        Bookmarks
          00:00:00
            Tri-contrastive Learning: Identifiable Representation Learning with Automatic Feature Importance Discovery
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Tri-contrastive Learning: Identifiable Representation Learning with Automatic Feature Importance Discovery

            Dec 10, 2023

            Speakers

            QZ

            Qi Zhang

            Speaker · 0 followers

            YW

            Yifei Wang

            Speaker · 0 followers

            YW

            Yifei Wang

            Speaker · 0 followers

            About

            Existing contrastive learning methods rely on pairwise sample contrast z_x^⊤ z_x' to learn data representations, but the learned features often lack clear interpretability from a human perspective. Theoretically, it lacks feature identifiability and different initialization may lead to totally different features.In this paper, we study a new method named tri-contrastive learning (triCL) that involves a 3-factor contrast in the form of z_x^⊤ S z_x', where S= diag(s_1,...,s_k) is a learnable diago…

            Organizer

            N2
            N2

            NeurIPS 2023

            Account · 617 followers

            Like the format? Trust SlidesLive to capture your next event!

            Professional recording and live streaming, delivered globally.

            Sharing

            Recommended Videos

            Presentations on similar topic, category or speaker

            A Pairwise GUI Dataset Construction Between Android Phones and Tablets
            05:02

            A Pairwise GUI Dataset Construction Between Android Phones and Tablets

            Han Hu, …

            N2
            N2
            NeurIPS 2023 15 months ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            A Data-Centric View on Workflows that Couple HPC with Large-Scale Models
            29:14

            A Data-Centric View on Workflows that Couple HPC with Large-Scale Models

            Ana Gainaru

            N2
            N2
            NeurIPS 2023 15 months ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            On the Generalization Properties of Diffusion Models
            05:03

            On the Generalization Properties of Diffusion Models

            Puheng Li, …

            N2
            N2
            NeurIPS 2023 15 months ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            MultiVENT: Multilingual Videos of Events and Aligned Natural Text
            04:38

            MultiVENT: Multilingual Videos of Events and Aligned Natural Text

            Kate Sanders, …

            N2
            N2
            NeurIPS 2023 15 months ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            TempME: Towards the Explainability of Temporal Graph Neural Networks via Motif Discovery
            04:55

            TempME: Towards the Explainability of Temporal Graph Neural Networks via Motif Discovery

            Jialin Chen, …

            N2
            N2
            NeurIPS 2023 15 months ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Lessons learned in deploying CV for ecology
            41:51

            Lessons learned in deploying CV for ecology

            Sara Beery

            N2
            N2
            NeurIPS 2023 15 months ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Interested in talks like this? Follow NeurIPS 2023