AlerTiger: Deep Learning for AI Model Health Monitoring at LinkedIn

Data-driven companies use AI models extensively to develop products and intelligent business solutions, making the health of these models crucial for business success. Model monitoring and alerting in industries pose unique challenges, including a lack of clear model health metrics definition, label sparsity, and fast model iterations that result in short-lived models and features. As a product, there are also requirements for scalability, generalizability, and explainability. To tackle these challenges, we propose AlerTiger, a deep-learning-based MLOps model monitoring system that helps AI teams across the company monitor their AI models' health by detecting anomalies in models' input features and output score over time. The system consists of four major steps: model statistics generation, deep-learning-based anomaly detection, anomaly post-processing, and user alerting. Our solution generates three categories of statistics to indicate AI model health, offers a two-stage deep anomaly detection solution to address label sparsity and attain the generalizability of monitoring new models, and provides holistic reports for actionable alerts. This approach has been deployed to most of LinkedIn's production AI models for over a year and has identified several model issues that later led to significant business metric gains after fixing.

Analysis of tunnel failure characteristics under multiple explosion loads based on persistent homology-based machine learning

The study of tunnel failure characteristics under the load of external explosion source is an important problem in tunnel design and protection, in particular, it is of great significance to construct an intelligent topological feature description of the tunnel failure process. The failure characteristics of tunnels under explosive loading are described by using discrete element method and persistent homology-based machine learning. Firstly, the discrete element model of shallow buried tunnel was established in the discrete element software, and the explosive load was equivalent to a series of uniformly distributed loads acting on the surface by Saint-Venant principle, and the dynamic response of the tunnel under multiple explosive loads was obtained through iterative calculation. The topological characteristics of surrounding rock is studied by persistent homology-based machine learning. The geometric, physical and interunit characteristics of the tunnel subjected to explosive loading are extracted, and the nonlinear mapping relationship between the topological quantity of persistent homology, and the failure characteristics of the surrounding rock is established, and the results of the intelligent description of the failure characteristics of the tunnel are obtained. The research shows that the length of the longest Betty 1 bar code is closely related to the stability of the tunnel, which can be used for effective early warning of the tunnel failure, and an intelligent description of the tunnel failure process can be established to provide a new idea for tunnel engineering protection.

ATRank: An Attention-Based User Behavior Modeling Framework for Recommendation

A user can be represented as what he/she does along the history. A common way to deal with the user modeling problem is to manually extract all kinds of aggregated features over the heterogeneous behaviors, which may fail to fully represent the data itself due to limited human instinct. Recent works usually use RNN-based methods to give an overall embedding of a behavior sequence, which then could be exploited by the downstream applications. However, this can only preserve very limited information, or aggregated memories of a person. When a downstream application requires to facilitate the modeled user features, it may lose the integrity of the specific highly correlated behavior of the user, and introduce noises derived from unrelated behaviors. This paper proposes an attention based user behavior modeling framework called ATRank, which we mainly use for recommendation tasks. Heterogeneous user behaviors are considered in our model that we project all types of behaviors into multiple latent semantic spaces, where influence can be made among the behaviors via self-attention. Downstream applications then can use the user behavior vectors via vanilla attention. Experiments show that ATRank can achieve better performance and faster training process. We further explore ATRank to use one unified model to predict different types of user behaviors at the same time, showing a comparable performance with the highly optimized individual models.