Jian Xu

Live Gradient Compensation for Evading Stragglers in Distributed Learning

2021

The training efficiency of distributed learning systems is vulnerable to stragglers, namely, those slow worker nodes. A naive strategy is performing the distributed learning by incor-porating the fastest K workers and ignoring these stragglers, which …

Personalized Federated Learning with Feature Alignment and Classifier Collaboration

2023 · arXiv (Cornell University)

Data heterogeneity is one of the most challenging issues in federated learning, which motivates a variety of approaches to learn personalized models for participating clients. One such approach in deep neural networks based tasks is …

Neural Operator Variational Inference based on Regularized Stein Discrepancy for Deep Gaussian Processes

2023 · arXiv (Cornell University)

Deep Gaussian Process (DGP) models offer a powerful nonparametric approach for Bayesian inference, but exact inference is typically intractable, motivating the use of various approximations. However, existing approaches, such as mean-field Gaussian assumptions, limit the …

Surface Anomaly Detection Based on Multi-Scale Feature Propagation and Normalized Flow

2023

Unsupervised learning is widely used for surface anomaly detection, due to the sparse and difficult description of anomaly samples. The goal of this paper is to improve the problems of low accuracy and slow speed …

Unified Visual Preference Learning for User Intent Understanding

2024

In the world of E-Commerce, the core task is to understand the personalized preference from various kinds of heterogeneous information, such as textual reviews, item images and historical behaviors. In current systems, these heterogeneous information …

External Large Foundation Model: How to Efficiently Serve Trillions of Parameters for Online Ads Recommendation

2025 · arXiv (Cornell University)

Ads recommendation is a prominent service of online advertising systems and has been actively studied. Recent studies indicate that scaling-up and advanced design of the recommendation model can bring significant performance improvement. However, with a …

Diffusion Bridge Variational Inference for Deep Gaussian Processes

2025 · arXiv (Cornell University)

Deep Gaussian processes (DGPs) enable expressive hierarchical Bayesian modeling but pose substantial challenges for posterior inference, especially over inducing variables. Denoising diffusion variational inference (DDVI) addresses this by modeling the posterior as a time-reversed diffusion …

Field-weighted Factorization Machines for Click-Through Rate Prediction in Display Advertising

2018

Click-through rate (CTR) prediction is a critical task in online display advertising. The data involved in CTR prediction are typically multi-field categorical data, i.e., every feature is categorical and belongs to one and only one …

Lifelong Sequential Modeling with Personalized Memorization for User Response Prediction

2019

User response prediction, which models the user preference w.r.t. the presented items, plays a key role in online services. With two-decade rapid development, nowadays the cumulated user behavior sequences on mature Internet service platforms have …