Skip to main content
  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
Poster 11 Oct 2023

This paper proposes InteractionLIME: a model-agnostic attribution technique to explain deep models predictions in terms of feature interactions. Specifically, we regress a bilinear form to approximate the output of any two-input model, by sampling pertubations of both inputs simultaneously. Upon training, we retrieve a global explanation and a set of feature partitioning maps via the singular value decomposition of the learned interaction matrix of the bilinear model. We demonstrate InteractionLIME on vision and text-vision contrastive models, using visual examples and quantitative evaluation metrics. Our results show that the bilinear model successfully retrieves important interacting features from both inputs, while strongly reducing the occurrence of incomplete or asymmetric explanations produced by a linear model.

More Like This

  • CIS
    Members: Free
    IEEE Members: Free
    Non-members: Free
  • MTT
    Members: Free
    IEEE Members: $9.00
    Non-members: $14.00
  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00