Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: HarsanyiNet: Computing Accurate Shapley Values in a Single Forward Propagation
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v2-stream-002-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v2-stream-002-alpha.b-cdn.net
      • sl-yoda-v2-stream-002-beta.b-cdn.net
      • 1001562353.rsc.cdn77.org
      • 1075090661.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
            HarsanyiNet: Computing Accurate Shapley Values in a Single Forward Propagation
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            HarsanyiNet: Computing Accurate Shapley Values in a Single Forward Propagation

            Jul 24, 2023

            Speakers

            LC

            Lu Chen

            Speaker · 0 followers

            SL

            Siyu Lou

            Speaker · 0 followers

            KZ

            Keyan Zhang

            Speaker · 0 followers

            About

            The Shapley value is widely regarded as a trustworthy attribution metric. However, when people use Shapley values to explain the attribution of input variables of a deep neural network (DNN), it usually requires a very high computational cost to approximate relatively accurate Shapley values in real-world applications. Therefore, we propose a novel network architecture, the HarsanyiNet, which makes inferences on the input sample and simultaneously computes the exact Shapley values of the input v…

            Organizer

            I2
            I2

            ICML 2023

            Account · 615 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

            SpENCNN: Orchestrating Encoding and Sparsity for Fast Homomorphically Encrypted Neural Network Inference
            05:17

            SpENCNN: Orchestrating Encoding and Sparsity for Fast Homomorphically Encrypted Neural Network Inference

            Ran Ran, …

            I2
            I2
            ICML 2023 2 years ago

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

            Graph Neural Networks with Learnable and Optimal Polynomial Bases
            04:26

            Graph Neural Networks with Learnable and Optimal Polynomial Bases

            Yuhe Guo, …

            I2
            I2
            ICML 2023 2 years ago

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

            High-dimensional Location Estimation via Norm Concentration for Subgamma Vectors
            04:48

            High-dimensional Location Estimation via Norm Concentration for Subgamma Vectors

            Shivam Gupta, …

            I2
            I2
            ICML 2023 2 years ago

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

            Quantifying the Variability Collapse of Neural Networks
            04:24

            Quantifying the Variability Collapse of Neural Networks

            Jing Xu, …

            I2
            I2
            ICML 2023 2 years ago

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

            Memory-Based Dual Gaussian Processes for Sequential Learning
            06:36

            Memory-Based Dual Gaussian Processes for Sequential Learning

            Paul Chang, …

            I2
            I2
            ICML 2023 2 years ago

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

            Welcome and Opening Remarks
            09:43

            Welcome and Opening Remarks

            Katherine Lee, …

            I2
            I2
            ICML 2023 2 years ago

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

            Interested in talks like this? Follow ICML 2023