论文标题
大规模CTR预测的增量学习框架
An Incremental Learning framework for Large-scale CTR Prediction
论文作者
论文摘要
在这项工作中，我们为点击率（CTR）预测引入了一个增量学习框架，并证明了其对Taboola庞大的建议服务的有效性。我们的方法通过从先前部署的模型中进行热门启动并仅对“新鲜”数据进行微调，可以快速捕获新兴趋势。过去的知识是通过教师范式维护的，教师充当蒸馏技术，减轻灾难性的遗忘现象。我们的增量学习框架可以显着更快地训练和部署周期（X12加速）。我们证明，每毫米（RPM）在多个交通段中的收入一致，而新引入的物品的CTR大幅增加。
In this work we introduce an incremental learning framework for Click-Through-Rate (CTR) prediction and demonstrate its effectiveness for Taboola's massive-scale recommendation service. Our approach enables rapid capture of emerging trends through warm-starting from previously deployed models and fine tuning on "fresh" data only. Past knowledge is maintained via a teacher-student paradigm, where the teacher acts as a distillation technique, mitigating the catastrophic forgetting phenomenon. Our incremental learning framework enables significantly faster training and deployment cycles (x12 speedup). We demonstrate a consistent Revenue Per Mille (RPM) lift over multiple traffic segments and a significant CTR increase on newly introduced items.
