Don't Waste the Last Token: A Quantizer-Agnostic Quality Boost from Semantic ID Collision Resolution
Generative recommenders represent each item as a Semantic ID: a short sequence of discrete tokens. Popular quantization algorithms, such as RQ-VAE and residual K-means, can map several items to the same token sequence, producing collisions. Collisions must be resolved before training a single-stage generative recommend...
Anna Volodkevich, Anton Klenitskiy, Artem Fatkulin et al.
· 0 citations