IRMar 10

CS3: Efficient Online Capability Synergy for Two-Tower Recommendation

arXiv:2604.2276162.5
Predicted impact top 51% in IR · last 90 daysOriginality Incremental advance
AI Analysis

For practitioners of large-scale recommender systems, CS3 provides a practical, real-time compatible framework that significantly boosts revenue without sacrificing latency.

CS3 enhances two-tower recommendation models with three innovations (Cycle-Adaptive Structure, Cross-Tower Synchronization, CascadeModel Sharing) to improve representation capacity and alignment while maintaining efficiency. In a large-scale advertising system, it increased online ad revenue by up to 8.36% across three scenarios with millisecond-level latency.

To balance effectiveness and efficiency in recommender systems, multi-stage pipelines employ lightweight two-tower models for large-scale candidate retrieval. However, their isolated architecture inherently hampers representation capacity, embedding-space alignment, and cross-feature modeling. Prior studies have explored incorporating late interaction or knowledge distillation to mitigate these issues, but such approaches often significantly increase model latency or pose challenges for implementation in online learning scenarios. To address these limitations, we propose an efficient online framework called Capability Synergy (CS3), which enhances two-tower models through three key innovations: (1) Cycle-Adaptive Structure, enabling self-revision via adaptive feature denoising within individual towers; (2) Cross-Tower Synchronization, improving representation alignment through mutual awareness between the towers; and (3) CascadeModel Sharing, bridging cross-stage consistency by reusing knowledge from downstream models. The CS3 framework is compatible with various two-tower architectures and meets real-time requirements in online learning scenarios. We evaluated CS3 on three public offline datasets and subsequently deployed it in a large-scale advertising system. Experimental results demonstrate that CS3 increases online ad revenue by up to 8.36% across three scenarios while maintaining millisecond-level latency and consistently performing well across diverse two-tower architectures.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes