Representing Deep Neural Networks Latent Space Geometries With Graphs

Abstract

Deep Learning (DL) has attracted a lot of attention for its ability to reach state-of-the-art performance in many machine learning tasks. The core principle of DL methods consists in training composite architectures in an end-to-end fashion, where inputs are associated with outputs trained to optimize an objective function. Because of their compositional nature, DL architectures naturally exhibit several intermediate representations of the inputs, which belong to so-called latent spaces. When treated individually, these intermediate representations are most of the time unconstrained during the learning process, as it is unclear which properties should be favored. However, when processing a batch of inputs concurrently, the corresponding set of intermediate representations exhibit relations (what we call a geometry) on which desired properties can be sought. In this work, we show that it is possible to introduce constraints on these latent geometries to address various problems. In more

Stats

• citations9
• S2 citations—
• github stars0
• HF likes0
• heat score7.50
• arxiv keylassance2020representing

Related papers

• Connecting Neural Models Latent Geometries With Relative Geodesic Representations (2025)0.00
• For Manifold Learning, Deep Neural Networks Can Be Locality Sensitive Hash Functions (2021)0.00
• Learning Graph Edit Distance By Graph Neural Networks (2020)10.85
• Latent Functional Maps: A Spectral Framework For Representation Alignment (2024)3.58
• Deep Graph Similarity Learning: A Survey (2019)13.97
• Learning To Represent Image And Text With Denotation Graph (2020)7.81
• Randomly Weighted Neuromodulation In Neural Networks Facilitates Learning Of Manifolds Common Across Tasks (2023)0.00
• Geometric Deep Learning For Computer-aided Design: A Survey (2024)8.60