Tagged
Representation Learning
Recommendation Systems (5): Embedding and Representation Learning
How modern recommenders learn dense vector representations for users and items: Word2Vec / Item2Vec, Node2Vec, two-tower DSSM and YouTube DNN, negative sampling, FAISS/HNSW serving, and how to evaluate embedding quality. …
Graph Neural Networks for Learning Equivariant Representations of Neural Networks
Represent a neural network as a directed graph (neurons as nodes, weights as edges) and use a GNN to produce permutation-equivariant embeddings. The right symmetry unlocks generalisation prediction, network …