Learning Unified User Quantized Tokenizers for User Representation
This work addresses scalability and generalization issues in user representation for web platforms like Alipay, though it is incremental as it builds on existing embedding and quantization methods.
The paper tackled the problem of multi-source user representation learning for personalized services by proposing U2QT, a framework that integrates cross-domain knowledge transfer with early fusion, which outperformed baselines in behavior prediction and recommendation tasks while improving storage and computation efficiency.
Multi-source user representation learning plays a critical role in enabling personalized services on web platforms (e.g., Alipay). While prior works have adopted late-fusion strategies to combine heterogeneous data sources, they suffer from three key limitations: lack of unified representation frameworks, scalability and storage issues in data compression, and inflexible cross-task generalization. To address these challenges, we propose U2QT (Unified User Quantized Tokenizers), a novel framework that integrates cross-domain knowledge transfer with early fusion of heterogeneous domains. Our framework employs a two-stage architecture: first, we use the Qwen3 Embedding model to derive a compact yet expressive feature representation; second, a multi-view RQ-VAE discretizes causal embeddings into compact tokens through shared and source-specific codebooks, enabling efficient storage while maintaining semantic coherence. Experimental results showcase U2QT's advantages across diverse downstream tasks, outperforming task-specific baselines in future behavior prediction and recommendation tasks while achieving efficiency gains in storage and computation. The unified tokenization framework enables seamless integration with language models and supports industrial-scale applications.