C2:Cross learning module enhanced decision transformer with Constraint-aware loss for auto-bidding
This work addresses auto-bidding for online advertising by improving generative models, representing an incremental advancement with specific enhancements to existing methods.
The paper tackled the problem of Decision Transformer's insufficient cross-correlation modeling and indiscriminate learning in auto-bidding by proposing C2 with a Cross Learning Block and Constraint-aware Loss, achieving up to 3.2% performance gains over state-of-the-art methods in offline evaluations.
Decision Transformer (DT) shows promise for generative auto-bidding by capturing temporal dependencies, but suffers from two critical limitations: insufficient cross-correlation modeling among state, action, and return-to-go (RTG) sequences, and indiscriminate learning of optimal/suboptimal behaviors. To address these, we propose C2, a novel framework enhancing DT with two core innovations: (1) a Cross Learning Block (CLB) via cross-attention to strengthen inter-sequence correlation modeling; (2) a Constraint-aware Loss (CL) incorporating budget and Cost-Per-Acquisition (CPA) constraints for selective learning of optimal trajectories. Extensive offline evaluations on the AuctionNet dataset demonstrate consistent performance gains (up to 3.2% over state-of-the-art method) across diverse budget settings; ablation studies verify the complementary synergy of CLB and CL, confirming C2's superiority in auto-bidding. The code for reproducing our results is available at: https://github.com/Dingjinren/C2.