Representation Collapsing Problems in Vector Quantization
This addresses a critical degradation problem in vector quantization for generative models like LLMs and diffusion models, though it appears incremental as it builds on known issues.
The paper investigates representation collapse in vector quantization, where codebook tokens or latent embeddings lose discriminative power by converging to limited values, compromising model diversity. It identifies restricted initialization and limited encoder capacity as causes and proposes potential solutions.
Vector quantization is a technique in machine learning that discretizes continuous representations into a set of discrete vectors. It is widely employed in tokenizing data representations for large language models, diffusion models, and other generative models. Despite its prevalence, the characteristics and behaviors of vector quantization in generative models remain largely underexplored. In this study, we investigate representation collapse in vector quantization - a critical degradation where codebook tokens or latent embeddings lose their discriminative power by converging to a limited subset of values. This collapse fundamentally compromises the model's ability to capture diverse data patterns. By leveraging both synthetic and real datasets, we identify the severity of each type of collapses and triggering conditions. Our analysis reveals that restricted initialization and limited encoder capacity result in tokens collapse and embeddings collapse. Building on these findings, we propose potential solutions aimed at mitigating each collapse. To the best of our knowledge, this is the first comprehensive study examining representation collapsing problems in vector quantization.