Recommendation Systems (5): Embedding and Representation Learning

Sat, 13 Dec 2025 09:00:00 +0000

When Netflix suggests Inception to someone who just finished The Dark Knight, the magic is not a hand-crafted “if-watched-Nolan-then” rule. It is geometry. Both films sit close together in a 128-dimensional embedding space that the model has learned from billions of viewing events. Geometry replaces enumeration: instead of comparing a movie to fifteen thousand others through brittle similarity rules, the system asks a single question — how far apart are these two vectors?

Graph Neural Networks for Learning Equivariant Representations of Neural Networks

Sun, 03 Apr 2022 09:00:00 +0000

Shuffling the hidden neurons of a trained MLP yields the exact same function, but the flat parameter vector looks entirely different. This fact ruins most attempts at “learning over neural networks”: naive representations treat two functionally identical models as unrelated points in parameter space, causing the downstream learner to waste capacity rediscovering a symmetry it should have for free. This paper, Graph Neural Networks for Learning Equivariant Representations of Neural Networks (Kofinas et al., ICML 2024), proposes a clean fix: turn the network into a graph and use a GNN whose architecture natively respects the relevant permutation symmetry.

Representation Learning on Chen Kai Blog

Recommendation Systems (5): Embedding and Representation Learning

Graph Neural Networks for Learning Equivariant Representations of Neural Networks