88 citations · 556 across the 36 of their papers we have counts for
36 papers
Text2Poster: Laying out Stylized Texts on Retrieved Images
Chuhao Jin, Hongteng Xu, Ruihua Song +1
Poster generation is a significant task for a wide range of applications, which is often time-consuming and requires lots of manual editing and artistic experience. In this paper,…
Interventional Multi-Instance Learning with Deconfounded Instance-Level Prediction
Tiancheng Lin, Hongteng Xu, Canqian Yang +1
When applying multi-instance learning (MIL) to make predictions for bags of instances, the prediction accuracy of an instance often depends on not only the instance itself but also…
Hawkes Processes on Graphons
Hongteng Xu, Dixin Luo, Hongyuan Zha
We propose a novel framework for modeling multiple multivariate point processes, each with heterogeneous event types that share an underlying space and obey the same generative mec…
Learning Graphons via Structured Gromov-Wasserstein Barycenters
Hongteng Xu, Dixin Luo, Lawrence Carin +1
We propose a novel and principled method to learn a nonparametric graph model called graphon, which is defined in an infinite-dimensional space and represents arbitrary-size graphs…
A Hypergradient Approach to Robust Regression without Correspondence
Yujia Xie, Yixiu Mao, Simiao Zuo +4
We consider a variant of regression problem, where the correspondence between input and output data is not available. Such shuffled data is commonly observed in many real world pro…
Hierarchical Optimal Transport for Robust Multi-View Learning
Dixin Luo, Hongteng Xu, Lawrence Carin
Traditional multi-view learning methods often rely on two assumptions: () the samples in different views are well-aligned, and () their representations in latent space obey…
Learning Autoencoders with Relational Regularization
Hongteng Xu, Dixin Luo, Ricardo Henao +2
A new algorithmic framework is proposed for learning autoencoders of data distributions. We minimize the discrepancy between the model and target distributions, with a \emph{relati…
Quaternion Product Units for Deep Learning on 3D Rotation Groups
Xuan Zhang, Shaofei Qin, Yi Xu +1
We propose a novel quaternion product unit (QPU) to represent data on 3D rotation groups. The QPU leverages quaternion algebra and the law of 3D rotation group, representing 3D rot…
Graph-Driven Generative Models for Heterogeneous Multi-Task Learning
Wenlin Wang, Hongteng Xu, Zhe Gan +6
We propose a novel graph-driven generative model, that unifies multiple heterogeneous learning tasks into the same framework. The proposed model is based on the fact that heterogen…
Gromov-Wasserstein Factorization Models for Graph Clustering
Hongteng Xu
We propose a new nonlinear factorization model for graphs that are with topological structures, and optionally, node attributes. This model is based on a pseudometric called Gromov…
Fused Gromov-Wasserstein Alignment for Hawkes Processes
Dixin Luo, Hongteng Xu, Lawrence Carin
We propose a novel fused Gromov-Wasserstein alignment method to jointly learn the Hawkes processes in different event spaces, and align their event types. Given two Hawkes processe…
Learning to Recommend from Sparse Data via Generative User Feedback
Wenlin Wang, Hongteng Xu, Ruiyi Zhang +3
Traditional collaborative filtering (CF) based recommender systems tend to perform poorly when the user-item interactions/ratings are highly scarce. To address this, we propose a l…
Zero-Shot Recognition via Optimal Transport
Wenlin Wang, Hongteng Xu, Guoyin Wang +2
We propose an optimal transport (OT) framework for generalized zero-shot learning (GZSL), seeking to distinguish samples for both seen and unseen classes, with the assist of auxili…
Adversarial Self-Paced Learning for Mixture Models of Hawkes Processes
Dixin Luo, Hongteng Xu, Lawrence Carin
We propose a novel adversarial learning strategy for mixture models of Hawkes processes, leveraging data augmentation techniques of Hawkes process in the framework of self-paced le…
Interpretable ICD Code Embeddings with Self- and Mutual-Attention Mechanisms
Dixin Luo, Hongteng Xu, Lawrence Carin
We propose a novel and interpretable embedding method to represent the international statistical classification codes of diseases and related health problems (i.e., ICD codes). Thi…
Scalable Gromov-Wasserstein Learning for Graph Partitioning and Matching
Hongteng Xu, Dixin Luo, Lawrence Carin
We propose a scalable Gromov-Wasserstein learning (S-GWL) method and establish a novel and theoretically-supported paradigm for large-scale graph analysis. The proposed method is b…
Topic-Guided Variational Autoencoders for Text Generation
Wenlin Wang, Zhe Gan, Hongteng Xu +5
We propose a topic-guided variational autoencoder (TGVAE) model for text generation. Distinct from existing variational autoencoder (VAE) based approaches, which assume a simple Ga…
Quaternion Convolutional Neural Networks
Xuanyu Zhu, Yi Xu, Hongteng Xu +1
Neural networks in the real domain have been studied for a long time and achieved promising results in many vision tasks for recent years. However, the extensions of the neural net…
Gromov-Wasserstein Learning for Graph Matching and Node Embedding
Hongteng Xu, Dixin Luo, Hongyuan Zha +1
A novel Gromov-Wasserstein learning framework is proposed to jointly match (align) graphs and learn embedding vectors for the associated graph nodes. Using Gromov-Wasserstein discr…
PoPPy: A Point Process Toolbox Based on PyTorch
Hongteng Xu
PoPPy is a Point Process toolbox based on PyTorch, which achieves flexible designing and efficient learning of point process models. It can be used for interpretable sequential dat…
Distilled Wasserstein Learning for Word Embedding and Topic Modeling
Hongteng Xu, Wenlin Wang, Wei Liu +1
We propose a novel Wasserstein method with a distillation mechanism, yielding joint learning of word embeddings and topics. The proposed method is based on the fact that the Euclid…
Predicting Smoking Events with a Time-Varying Semi-Parametric Hawkes Process Model
Matthew Engelhard, Hongteng Xu, Lawrence Carin +3
Health risks from cigarette smoking -- the leading cause of preventable death in the United States -- can be substantially reduced by quitting. Although most smokers are motivated…
Learning an Inverse Tone Mapping Network with a Generative Adversarial Regularizer
Shiyu Ning, Hongteng Xu, Li Song +2
Transferring a low-dynamic-range (LDR) image to a high-dynamic-range (HDR) image, which is the so-called inverse tone mapping (iTM), is an important imaging technique to improve vi…
Superposition-Assisted Stochastic Optimization for Hawkes Processes
Hongteng Xu, Xu Chen, Lawrence Carin
We consider the learning of multi-agent Hawkes processes, a model containing multiple Hawkes processes with shared endogenous impact functions and different exogenous intensities.…