C2:Cross learning module enhanced decision transformer with Constraint-aware loss for auto-bidding

TL;DR

This paper introduces C2, a decision transformer framework with cross-attention and constraint-aware loss, improving auto-bidding performance by better modeling sequence correlations and selectively learning optimal behaviors.

Contribution

C2 enhances decision transformers with a cross-learning block and constraint-aware loss, addressing key limitations in auto-bidding models and achieving superior results.

Findings

Up to 3.2% performance improvement over state-of-the-art

Effective modeling of inter-sequence correlations

Selective learning of optimal trajectories

Abstract

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.