CADET: Context-Conditioned Ads CTR Prediction With a Decoder-Only Transformer
Click-through rate (CTR) prediction is fundamental to online advertising systems. While Deep Learning Recommendation Models (DLRMs) with explicit feature interactions have long dominated this domain, recent advances in generative recommenders have shown promising results in content recommendation. However, adapting these transformer-based architectures to ads CTR prediction still presents unique challenges, including handling post-scoring contextual signals, maintaining offline-online consistency, and scaling to industrial workloads. We present CADET (Context-Conditioned Ads Decoder-Only Transformer), an end-to-end decoder-only transformer for ads CTR prediction deployed at LinkedIn. Our approach introduces several key innovations: (1) a context-conditioned decoding architecture with multi-tower prediction heads that explicitly model post-scoring signals such as ad position, resolving the chicken-and-egg problem between predicted CTR and ranking; (2) a self-gated attention mechanism that stabilizes training by adaptively regulating information flow at both representation and interaction levels; (3) a timestamp-based variant of Rotary Position Embedding (RoPE) that captures temporal relationships across timescales from seconds to months; (4) session masking strategies that prevent the model from learning dependencies on unavailable in-session events, addressing train-serve skew; and (5) production engineering techniques including tensor packing, sequence chunking, and custom Flash Attention kernels that enable efficient training and serving at scale. In online A/B testing, CADET achieves a 11.04\% CTR lift compared to the production LiRank baseline model, a hybrid ensemble of DCNv2 and sequential encoders. The system has been successfully deployed on LinkedIn's advertising platform, serving the main traffic for homefeed sponsored updates.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
An Expert System Approach for determine the stage of UiTM Perlis Palapes Cadet Performance and Ranking Selection
The palapes cadets are one of the uniform organizations in UiTM Perlis for extra-curricular activities. The palapes cadets arrange their organization in a hierarchy according to grade. Senior uniform officer (SUO) is the…
CADet: Fully Self-Supervised Out-Of-Distribution Detection With Contrastive Learning
Handling out-of-distribution (OOD) samples has become a major stake in the real-world deployment of machine learning systems. This work explores the use of self-supervised contrastive learning to the simultaneous detecti…
Anomaly DetectionContrastive LearningOut-of-Distribution DetectionCADET: A Modular Platform for Evaluating Distributed Cooperative Autonomy in Connected Autonomous Vehicles
Deep learning models are increasingly central to autonomous vehicle (AV) pipelines, yet their integration has traditionally followed a monolithic design where perception, planning, and control execute on a single onboard…
Autonomous VehiclesCausality Guided Representation Learning for Cross-Style Hate Speech Detection
The proliferation of online hate speech poses a significant threat to the harmony of the web. While explicit hate is easily recognized through overt slurs, implicit hate speech is often conveyed through sarcasm, irony, s…
Representation LearningHate Speech DetectionDynamic Neural Representational Decoders for High-Resolution Semantic Segmentation
Semantic segmentation requires per-pixel prediction for a given image. Typically, the output resolution of a segmentation network is severely reduced due to the downsampling operations in the CNN backbone. Most previous …
DecoderSegmentationSemantic SegmentationVocal Bursts Intensity Prediction