In the realm of recommender systems, the ubiquitous adoption of deep neural networks has emerged as a dominant paradigm for modeling diverse business objectives. As user bases continue to expand, the necessity of personalization and frequent model updates have assumed paramount significance to ensure the delivery of relevant and refreshed experiences to a diverse array of members. In this work, we introduce an innovative meta-learning solution tailored to the personalization of models for individual members and other entities, coupled with the frequent updates based on the latest user interaction signals. Specifically, we leverage the Model-Agnostic Meta Learning (MAML) algorithm to adapt per-task sub-networks using recent user interaction data. Given the near infeasibility of productionizing original MAML-based models in online recommendation systems, we propose an efficient strategy to operationalize meta-learned sub-networks in production, which involves transforming them into fixed-sized vectors, termed meta embeddings, thereby enabling the seamless deployment of models with hundreds of billions of parameters for online serving. Through extensive experimentation on production data drawn from various applications at LinkedIn, we demonstrate that the proposed solution consistently outperforms the baseline models of those applications, including strong baselines such as using wide-and-deep ID based personalization approach. Our approach has enabled the deployment of a range of highly personalized AI models across diverse LinkedIn applications, leading to substantial improvements in business metrics as well as refreshed experience for our members.

In this paper, we propose a generic model-based re-ranking framework, MultiSlot ReRanker, which simultaneously optimizes relevance, diversity, and freshness. Specifically, our Sequential Greedy Algorithm (SGA) is efficient enough (linear time complexity) for large-scale production recommendation engines. It achieved a lift of $+6\%$ to $ +10\%$ offline Area Under the receiver operating characteristic Curve (AUC) which is mainly due to explicitly modeling mutual influences among items of a list, and leveraging the second pass ranking scores of multiple objectives. In addition, we have generalized the offline replay theory to multi-slot re-ranking scenarios, with trade-offs among multiple objectives. The offline replay results can be further improved by Pareto Optimality. Moreover, we've built a multi-slot re-ranking simulator based on OpenAI Gym integrated with the Ray framework. It can be easily configured for different assumptions to quickly benchmark both reinforcement learning and supervised learning algorithms.

In this paper, Mobile notification systems play a major role in a variety of applications we focus our discussion on a near-real-time notification system, to communicate, send alerts and reminders to the users to which can process both near-real-time and offline notifications and inform them about news, events or messages. In this paper, we formulate make decisions in a stream fashion in near-real-time. An example of the near-real-time notification decision problem as a Markov such a distributed near-real-time notification system can be found Decision Process where we optimize for multiple objectives in the in [7]. Note that a near-real-time notification system can process rewards. We propose an end-to-end offline reinforcement learning offline notifications and spread them out over time, for example framework to optimize sequential notification decisions. We using a notification spacing queuing system introduced in [35]. On address the challenge of offline learning using a Double Deep Q-the other hand, a system designed solely for offline notifications network method based on Conservative Q-learning that mitigates may not be able to process near-real-time notifications. the distributional shift problem and Q-value overestimation. We There are a few characteristics of the notification system that illustrate our fully-deployed system and demonstrate the performance make them suitable applications for reinforcement learning (RL).