Representation Learning

A Theory of Usable Information Under Computational Constraints

ASIF: Coupled Data Turns Unimodal Models to Multimodal Without Training

Norelli, Fumero, Maiorca, Rodolà et al. (Sapienza University, arXiv:2210.01738, 2022) show that any two unimodal models can be composed into a zero-shot multimodal system by finding approximate shared nearest neighbors across their embedding spaces, given only a small set of coupled pairs. The result challenges the assumption that multimodal capability requires joint training.

A Survey on Graph Representation Learning Methods

Khoshraftar and An (York University) provide a comprehensive survey of graph representation learning covering node embeddings, GNNs, and knowledge graph methods, with attention to both spectral and spatial approaches. It's the right starting point for anyone orienting to the GRL landscape — methodical coverage from DeepWalk through GAT.

Visualizing Representations: Deep Learning and Human Beings

Christopher Olah's essay on visualizing what neural networks actually learn — using dimensionality reduction to show how deep networks transform data into progressively more separable representations. One of the most important early pieces on deep learning interpretability.