E
Eric P. Xing
Researcher at Carnegie Mellon University
Publications - 725
Citations - 48035
Eric P. Xing is an academic researcher from Carnegie Mellon University. The author has contributed to research in topics: Inference & Topic model. The author has an hindex of 99, co-authored 711 publications receiving 41467 citations. Previous affiliations of Eric P. Xing include Microsoft & Intel.
Papers
More filters
Posted Content
High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks
TL;DR: In this paper, the authors investigate the relationship between the frequency spectrum of image data and the generalization behavior of convolutional neural networks (CNN) and find that high frequency components are almost imperceptible to a human.
Journal Article
Pathological Visual Question Answering
TL;DR: The created PathVQA dataset represents the first one addressing the pathology VQA problem and the results demonstrate the effectiveness of the proposed learning-by-ignoring method and cross-modal self-supervised learning methods.
Posted Content
Understanding the Interaction between Interests, Conversations and Friendships in Facebook
TL;DR: This paper explores salient questions about user interests, conversations and friendships in the Facebook social network, using a novel latent space model that integrates several data types, allowing for the interplay between user friendships, interests, and higher-order network-wide social trends on Facebook.
Posted Content
Graph Estimation From Multi-attribute Data
TL;DR: A new principled framework for estimating the structure of undirected graphical models from such multivariate (or multi-attribute) nodal data is proposed and a method that efficiently maximizes this objective is developed.
Proceedings ArticleDOI
Automating Dependence-Aware Parallelization of Machine Learning Training on Distributed Shared Memory
TL;DR: The evaluation shows that for a number of ML applications, Orion can parallelize a serial program while preserving critical dependences and thus achieve a significantly faster convergence rate than data-parallel programs and a matching convergence rate and comparable computation throughput to state-of-the-art manual parallelizations including model-par parallel programs.