Smooth InfoMax -- Towards Easier Post-Hoc Interpretability

Abstract

We introduce Smooth InfoMax (SIM), a self-supervised representation learning method that incorporates interpretability constraints into the latent representations at different depths of the network. Based on ${\hat{I}}^2$-VAEs, SIM's architecture consists of probabilistic modules optimized locally with the InfoNCE loss to produce Gaussian-distributed representations regularized toward the standard normal distribution. This creates smooth, well-defined, and better-disentangled latent spaces, enabling easier post-hoc analysis. Evaluated on speech data, SIM preserves the large-scale training benefits of Greedy InfoMax while improving the effectiveness of post-hoc interpretability methods across layers.