CTNet: Continual Transfer Learning for Cross-Domain Recommendation
CTNet is a continual transfer learning framework that uses a lightweight Adapter to map source‑domain features onto evolving target‑domain recommendation tasks, preserving all model parameters to avoid catastrophic forgetting and delivering substantial gains in click‑through rate, conversion, and overall business performance in Taobao’s cross‑domain e‑commerce scenario.
This paper proposes CTNet, a continual transfer learning framework for cross-domain recommendation systems. It addresses the challenge of leveraging source domain knowledge in evolving recommendation scenarios without catastrophic forgetting. The method employs a lightweight Adapter module to map source domain model features to target domain tasks, achieving significant business improvements in e-commerce recommendation tasks.
The approach maintains all parameters from both source and target models, enabling efficient knowledge transfer through incremental updates. Experiments on Taobao's '有好货' recommendation scenario demonstrate superior performance compared to traditional transfer learning methods, with notable gains in CTR, conversion rates, and business metrics.
Signed-in readers can open the original source through BestHub's protected redirect.
This article has been distilled and summarized from source material, then republished for learning and reference. If you believe it infringes your rights, please contactand we will review it promptly.
How this landed with the community
Was this worth your time?
0 Comments
Thoughtful readers leave field notes, pushback, and hard-won operational detail here.