Behavior Structformer: Learning Players Representations with Structured Tokenization
This work addresses behavior modeling for users, but it appears incremental as it builds on existing Transformer methods with structured tokenization.
The paper tackles the problem of modeling user behavior by introducing Behavior Structformer, which uses structured tokenization within a Transformer to convert tracking events into dense tokens, resulting in enhanced training efficiency and effectiveness as shown in ablation studies and benchmarking against baselines.
In this paper, we introduce the Behavior Structformer, a method for modeling user behavior using structured tokenization within a Transformer-based architecture. By converting tracking events into dense tokens, this approach enhances model training efficiency and effectiveness. We demonstrate its superior performance through ablation studies and benchmarking against traditional tabular and semi-structured baselines. The results indicate that structured tokenization with sequential processing significantly improves behavior modeling.