DynamiX: Dynamic Resource eXploration for Personalized Ad-Recommendations
For online ad-recommendation systems, processing complete user-ad-engagement histories is both computationally intensive and noise-prone. We introduce Dynamix, a scalable, personalized sequence exploration framework that optimizes event history processing using maximum relevance principles and self-supervised learning through Event Based Features (EBFs). Dynamix categorizes users-engagements at session and surface-levels by leveraging correlations between dwell-times and ad-conversion events. This enables targeted, event-level feature removal and selective feature boosting for certain user-segments, thereby yielding training and inference efficiency wins without sacrificing engaging ad-prediction accuracy. While, dynamic resource removal increases training and inference throughput by 1.15% and 1.8%, respectively, dynamic feature boosting provides 0.033 NE gains while boosting inference QPS by 4.2% over baseline models. These results demonstrate that Dynamix achieves significant cost efficiency and performance improvements in online user-sequence based recommendation models. Self-supervised user-segmentation and resource exploration can further boost complex feature selection strategies while optimizing for workflow and compute resources.
Code (0)
등록된 구현이 없습니다.
Tasks
Self-Supervised LearningRecommendation SystemsSimilar Papers 제목 키워드 기반
DynamixSFT: Dynamic Mixture Optimization of Instruction Tuning Collections
As numerous instruction-tuning datasets continue to emerge, dynamically balancing and optimizing their mixtures has become a critical challenge. To address this, we propose DynamixSFT, a dynamic and automated method for …
DYNAMIX: RL-based Adaptive Batch Size Optimization in Distributed Machine Learning Systems
Existing batch size selection approaches in distributed machine learning rely on static allocation or simplistic heuristics that fail to adapt to heterogeneous, dynamic computing environments. We present DYNAMIX, a reinf…
Reinforcement LearningDynaMIX: Resource Optimization for DNN-Based Real-Time Applications on a Multi-Tasking System
As deep neural networks (DNNs) prove their importance and feasibility, more and more DNN-based apps, such as detection and classification of objects, have been developed and deployed on autonomous vehicles (AVs). To meet…
Autonomous VehiclesDynamiX: Large-Scale Dynamic Social Network Simulator
Understanding the intrinsic mechanisms of social platforms is an urgent demand to maintain social stability. The rise of large language models provides significant potential for social network simulations to capture atti…
Link PredictionDynaMixer: A Vision MLP Architecture with Dynamic Mixing
Recently, MLP-like vision models have achieved promising performances on mainstream visual recognition tasks. In contrast with vision transformers and CNNs, the success of MLP-like models shows that simple information fu…
Image Classification