Search Results for author: Xin Guo

Found 65 papers, 11 papers with code

基于迭代信息传递和滑动窗口注意力的问题生成模型研究(Question Generation Model Based on Iterative Message Passing and Sliding Windows Hierarchical Attention)

no code implementations CCL 2021 Qian Chen, Xiaoying Gao, Suge Wang, Xin Guo

“知识图谱问题生成任务是从给定的知识图谱中生成与其相关的问题。目前, 知识图谱问题生成模型主要使用基于RNN或Transformer对知识图谱子图进行编码, 但这种方式丢失了显式的图结构化信息, 在解码器中忽视了局部信息对节点的重要性。本文提出迭代信息传递图编码器来编码子图, 获取子图显式的图结构化信息, 此外, 我们还使用滑动窗口注意力机制提高RNN解码器, 提升子图局部信息对节点的重要度。从WQ和PQ数据集上的实验结果看, 我们提出的模型比KTG模型在BLEU4指标上分别高出2. 16和15. 44, 证明了该模型的有效性。”

Question Generation Question-Generation

Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning

1 code implementation8 Feb 2024 Zhiheng Xi, Wenxiang Chen, Boyang Hong, Senjie Jin, Rui Zheng, wei he, Yiwen Ding, Shichun Liu, Xin Guo, Junzhe Wang, Honglin Guo, Wei Shen, Xiaoran Fan, Yuhao Zhou, Shihan Dou, Xiao Wang, Xinbo Zhang, Peng Sun, Tao Gui, Qi Zhang, Xuanjing Huang

In this paper, we propose R$^3$: Learning Reasoning through Reverse Curriculum Reinforcement Learning (RL), a novel method that employs only outcome supervision to achieve the benefits of process supervision for large language models.

GSM8K reinforcement-learning +1

Multimodal Urban Areas of Interest Generation via Remote Sensing Imagery and Geographical Prior

no code implementations12 Jan 2024 Chuanji Shi, Yingying Zhang, Jiaotuan Wang, Xin Guo, Qiqi Zhu

Unlike conventional AOI generation methods, such as the Road-cut method that segments road networks at various levels, our approach diverges from semantic segmentation algorithms that depend on pixel-level classification.

Multimodal Deep Learning Semantic Segmentation

Transportation Marketplace Rate Forecast Using Signature Transform

no code implementations10 Jan 2024 Haotian Gu, Xin Guo, Timothy L. Jacobs, Philip Kaminsky, Xinyu Li

Freight transportation marketplace rates are typically challenging to forecast accurately.

Time Series

Fast Policy Learning for Linear Quadratic Control with Entropy Regularization

no code implementations23 Nov 2023 Xin Guo, Xinyu Li, Renyuan Xu

This paper proposes and analyzes two new policy learning methods: regularized policy gradient (RPG) and iterative policy optimization (IPO), for a class of discounted linear-quadratic control (LQC) problems over an infinite time horizon with entropy regularization.

Risk of Transfer Learning and its Applications in Finance

no code implementations6 Nov 2023 Haoyang Cao, Haotian Gu, Xin Guo, Mathieu Rosenbaum

Transfer learning is an emerging and popular paradigm for utilizing existing knowledge from previous learning tasks to improve the performance of new ones.

Portfolio Optimization Transfer Learning

FinEval: A Chinese Financial Domain Knowledge Evaluation Benchmark for Large Language Models

1 code implementation19 Aug 2023 Liwen Zhang, Weige Cai, Zhaowei Liu, Zhi Yang, Wei Dai, Yujie Liao, Qianru Qin, Yifei Li, Xingyu Liu, Zhiqiang Liu, Zhoufan Zhu, Anbo Wu, Xin Guo, Yun Chen

Our work offers a more comprehensive financial knowledge evaluation benchmark, utilizing data of mock exams and covering a wide range of evaluated LLMs.

Multiple-choice

Transfer Learning for Portfolio Optimization

no code implementations25 Jul 2023 Haoyang Cao, Haotian Gu, Xin Guo, Mathieu Rosenbaum

In particular, 1. a strong correlation between the transfer risk and the overall performance of transfer learning methods is established, underscoring the significance of transfer risk as a viable indicator of "transferability"; 2. transfer risk is shown to provide a computationally efficient way to identify appropriate source tasks in transfer learning, enhancing the efficiency and effectiveness of the transfer learning approach; 3. additionally, the numerical experiments offer valuable new insights for portfolio management across these different settings.

Management Portfolio Optimization +1

MESOB: Balancing Equilibria & Social Optimality

no code implementations16 Jul 2023 Xin Guo, Lihong Li, Sareh Nabi, Rabih Salhab, Junzi Zhang

Motivated by bid recommendation in online ad auctions, this paper considers a general class of multi-level and multi-agent games, with two major characteristics: one is a large number of anonymous agents, and the other is the intricate interplay between competition and cooperation.

Feasibility of Transfer Learning: A Mathematical Framework

no code implementations22 May 2023 Haoyang Cao, Haotian Gu, Xin Guo

Transfer learning is a popular paradigm for utilizing existing knowledge from previous learning tasks to improve the performance of new ones.

Domain Adaptation Image Classification +1

Markov $α$-Potential Games

no code implementations21 May 2023 Xin Guo, Xinyu Li, Chinmay Maheshwari, Shankar Sastry, Manxi Wu

In this new framework, Markov games are shown to be Markov $\alpha$-potential games, and the existence of an associated $\alpha$-potential function is established.

On Consistency of Signatures Using Lasso

no code implementations17 May 2023 Xin Guo, Ruixun Zhang, Chaoyi Zhao

Signature transforms are iterated path integrals of continuous and discrete-time time series data, and their universal nonlinearity linearizes the problem of feature selection.

feature selection regression +1

Feasibility and Transferability of Transfer Learning: A Mathematical Framework

no code implementations27 Jan 2023 Haoyang Cao, Haotian Gu, Xin Guo, Mathieu Rosenbaum

In this paper we build for the first time, to the best of our knowledge, a mathematical framework for the general procedure of transfer learning.

Transfer Learning

Learning Weather-General and Weather-Specific Features for Image Restoration Under Multiple Adverse Weather Conditions

no code implementations CVPR 2023 Yurui Zhu, Tianyu Wang, Xueyang Fu, Xuanyu Yang, Xin Guo, Jifeng Dai, Yu Qiao, Xiaowei Hu

Inspired by this observation, we design an efficient unified framework with a two-stage training strategy to explore the weather-general and weather-specific features.

Image Restoration

Uncertainty-guided Learning for Improving Image Manipulation Detection

no code implementations ICCV 2023 Kaixiang Ji, Feng Chen, Xin Guo, Yadong Xu, Jian Wang, Jingdong Chen

Image manipulation detection (IMD) is of vital importance as faking images and spreading misinformation can be malicious and harm our daily life.

Image Manipulation Image Manipulation Detection +1

Capacity dependent analysis for functional online learning algorithms

no code implementations25 Sep 2022 Xin Guo, Zheng-Chu Guo, Lei Shi

This article provides convergence analysis of online stochastic gradient descent algorithms for functional linear models.

SiamTrans: Zero-Shot Multi-Frame Image Restoration with Pre-Trained Siamese Transformers

no code implementations17 Dec 2021 Lin Liu, Shanxin Yuan, Jianzhuang Liu, Xin Guo, Youliang Yan, Qi Tian

For zero-shot image restoration, we design a novel model, termed SiamTrans, which is constructed by Siamese transformers, encoders, and decoders.

Denoising Image Restoration +1

Extracting and Measuring Uncertain Biomedical Knowledge from Scientific Statements

no code implementations5 Dec 2021 Xin Guo, Yuming Chen, Jian Du, Erdan Dong

Design/methodology/approach: Taking cardiovascular research publications in China as a sample, we extracted the SPO triples as knowledge unit and the hedging/conflicting uncertainties as the knowledge context.

Convergence of GANs Training: A Game and Stochastic Control Methodology

no code implementations1 Dec 2021 Othmane Mounjid, Xin Guo

Training generative adversarial networks (GANs) is known to be difficult, especially for financial time series.

Time Series Time Series Analysis

Theoretical Guarantees of Fictitious Discount Algorithms for Episodic Reinforcement Learning and Global Convergence of Policy Gradient Methods

no code implementations13 Sep 2021 Xin Guo, Anran Hu, Junzi Zhang

To our best knowledge, this is the first theoretical guarantee on fictitious discount algorithms for the episodic reinforcement learning of finite-time-horizon MDPs, which also leads to the (first) global convergence of policy gradient methods for finite-time-horizon episodic reinforcement learning.

Policy Gradient Methods reinforcement-learning +1

FedSkel: Efficient Federated Learning on Heterogeneous Systems with Skeleton Gradients Update

1 code implementation20 Aug 2021 Junyu Luo, Jianlei Yang, Xucheng Ye, Xin Guo, Weisheng Zhao

Federated learning aims to protect users' privacy while performing data analysis from different participants.

Federated Learning

RoSearch: Search for Robust Student Architectures When Distilling Pre-trained Language Models

no code implementations7 Jun 2021 Xin Guo, Jianlei Yang, Haoyi Zhou, Xucheng Ye, JianXin Li

In order to overcome these security problems, RoSearch is proposed as a comprehensive framework to search the student models with better adversarial robustness when performing knowledge distillation.

Adversarial Robustness Knowledge Distillation +1

Adversarial Training for Gradient Descent: Analysis Through its Continuous-time Approximation

no code implementations17 May 2021 Haotian Gu, Xin Guo, Xinyu Li

Adversarial training has gained great popularity as one of the most effective defenses for deep neural network and more generally for gradient-based machine learning models against adversarial perturbations on data points.

Discriminative-Generative Dual Memory Video Anomaly Detection

no code implementations29 Apr 2021 Xin Guo, Zhongming Jin, Chong Chen, Helei Nie, Jianqiang Huang, Deng Cai, Xiaofei He, Xiansheng Hua

In this paper, we propose a DiscRiminative-gEnerative duAl Memory (DREAM) anomaly detection model to take advantage of a few anomalies and solve data imbalance.

Anomaly Detection Video Anomaly Detection

Generative Adversarial Network: Some Analytical Perspectives

no code implementations25 Apr 2021 Haoyang Cao, Xin Guo

Ever since its debut, generative adversarial networks (GANs) have attracted tremendous amount of attention.

Generative Adversarial Network

Reinforcement learning for linear-convex models with jumps via stability analysis of feedback controls

no code implementations19 Apr 2021 Xin Guo, Anran Hu, Yufei Zhang

We study finite-time horizon continuous-time linear-convex reinforcement learning problems in an episodic setting.

Reinforcement Learning (RL)

Delay Analysis of Wireless Federated Learning Based on Saddle Point Approximation and Large Deviation Theory

no code implementations31 Mar 2021 Lintao Li, Longwei Yang, Xin Guo, Yuanming Shi, Haiming Wang, Wei Chen, Khaled B. Letaief

Federated learning (FL) is a collaborative machine learning paradigm, which enables deep learning model training over a large volume of decentralized data residing in mobile devices without accessing clients' private data.

Federated Learning

Edge-Labeling based Directed Gated Graph Network for Few-shot Learning

1 code implementation27 Jan 2021 Peixiao Zheng, Xin Guo, Lin Qi

In this paper, we proposed an edge-labeling-based directed gated graph network (DGGN) for few-shot learning, which utilizes gated recurrent units to implicitly update the similarity between nodes.

Few-Shot Learning

DanceIt: Music-inspired Dancing Video Synthesis

1 code implementation17 Sep 2020 Xin Guo, Yifan Zhao, Jia Li

To explore the relationship between music and dance movements, we propose a cross-modal alignment module that focuses on dancing video clips, accompanied on pre-designed music, to learn a system that can judge the consistency between the visual features of pose sequences and the acoustic features of music.

cross-modal alignment

Kernel-based L_2-Boosting with Structure Constraints

no code implementations16 Sep 2020 Yao Wang, Xin Guo, Shao-Bo Lin

Numerically, we carry out a series of simulations to show the promising performance of KReBooT in terms of its good generalization, near over-fitting resistance and structure constraints.

Out-of-distribution Generalization via Partial Feature Decorrelation

no code implementations30 Jul 2020 Xin Guo, Zhengxu Yu, Chao Xiang, Zhongming Jin, Jianqiang Huang, Deng Cai, Xiaofei He, Xian-Sheng Hua

Most deep-learning-based image classification methods assume that all samples are generated under an independent and identically distributed (IID) setting.

Classification General Classification +3

Logarithmic regret for episodic continuous-time linear-quadratic reinforcement learning over a finite-time horizon

no code implementations27 Jun 2020 Matteo Basei, Xin Guo, Anran Hu, Yufei Zhang

We study finite-time horizon continuous-time linear-quadratic reinforcement learning problems in an episodic setting, where both the state and control coefficients are unknown to the controller.

Reinforcement Learning (RL)

PAC-Bayesian Generalization Bounds for MultiLayer Perceptrons

no code implementations16 Jun 2020 Xinjie Lan, Xin Guo, Kenneth E. Barner

We study PAC-Bayesian generalization bounds for Multilayer Perceptrons (MLPs) with the cross entropy loss.

Generalization Bounds Variational Inference

Early Detection of Retinopathy of Prematurity (ROP) in Retinal Fundus Images Via Convolutional Neural Networks

no code implementations12 Jun 2020 Xin Guo, Yusuke Kikuchi, Guan Wang, Jinglin Yi, Qiong Zou, Rui Zhou

Retinopathy of prematurity (ROP) is an abnormal blood vessel development in the retina of a prematurely-born infant or an infant with low birth weight.

Specificity

SDE approximations of GANs training and its long-run behavior

no code implementations3 Jun 2020 Haoyang Cao, Xin Guo

This paper analyzes the training process of GANs via stochastic differential equations (SDEs).

Escaping Saddle Points Efficiently with Occupation-Time-Adapted Perturbations

no code implementations9 May 2020 Xin Guo, Jiequn Han, Mahan Tajrobehkar, Wenpin Tang

Motivated by the super-diffusivity of self-repelling random walk, which has roots in statistical physics, this paper develops a new perturbation mechanism for optimization algorithms.

A General Framework for Learning Mean-Field Games

no code implementations13 Mar 2020 Xin Guo, Anran Hu, Renyuan Xu, Junzi Zhang

This paper presents a general mean-field game (GMFG) framework for simultaneous learning and decision-making in stochastic games with a large population.

Decision Making Multi-agent Reinforcement Learning +3

Prediction and analysis of Coronavirus Disease 2019

no code implementations11 Mar 2020 Lin Jia, Kewen Li, Yu Jiang, Xin Guo, Ting zhao

According to the current trend, based on the three models, the total number of people expected to be infected is 49852-57447 in Wuhan, 12972-13405 in non-Hubei areas and 80261-85140 in China respectively.

Populations and Evolution

Mean-Field Controls with Q-learning for Cooperative MARL: Convergence and Complexity Analysis

no code implementations10 Feb 2020 Haotian Gu, Xin Guo, Xiaoli Wei, Renyuan Xu

Multi-agent reinforcement learning (MARL), despite its popularity and empirical success, suffers from the curse of dimensionality.

Multi-agent Reinforcement Learning Q-Learning

Connecting GANs, MFGs, and OT

no code implementations10 Feb 2020 Haoyang Cao, Xin Guo, Mathieu Laurière

Generative adversarial networks (GANs) have enjoyed tremendous success in image generation and processing, and have recently attracted growing interests in financial modelings.

Image Generation

Accelerating CNN Training by Pruning Activation Gradients

no code implementations ECCV 2020 Xucheng Ye, Pengcheng Dai, Junyu Luo, Xin Guo, Yingjie Qi, Jianlei Yang, Yiran Chen

Sparsification is an efficient approach to accelerate CNN inference, but it is challenging to take advantage of sparsity in training procedure because the involved gradients are dynamically changed.

POG: Personalized Outfit Generation for Fashion Recommendation at Alibaba iFashion

1 code implementation6 May 2019 Wen Chen, Pipei Huang, Jiaming Xu, Xin Guo, Cheng Guo, Fei Sun, Chao Li, Andreas Pfadler, Huan Zhao, Binqiang Zhao

In particular, there exist two requirements for fashion outfit recommendation: the Compatibility of the generated fashion outfits, and the Personalization in the recommendation process.

Transaction Cost Analytics for Corporate Bonds

no code implementations21 Mar 2019 Xin Guo, Charles-Albert Lehalle, Renyuan Xu

This part is on the time scale of each transaction of liquid corporate bonds, and is by applying a transient impact model to estimate the price impact kernel using a non-parametric method.

Sparsemax and Relaxed Wasserstein for Topic Sparsity

no code implementations22 Oct 2018 Tianyi Lin, Zhiyue Hu, Xin Guo

As topic sparsity of individual documents in online social media increases, so does the difficulty of analyzing the online text sources using traditional methods.

A class of stochastic games and moving free boundary problems

no code implementations10 Sep 2018 Xin Guo, Wenpin Tang, Renyuan Xu

In this paper we propose and analyze a class of $N$-player stochastic games that include finite fuel stochastic games as a special case.

Smile detection in the wild based on transfer learning

no code implementations17 Jan 2018 Xin Guo, Luisa F. Polanía, Kenneth E. Barner

Compared to the size of databases for face recognition, far less labeled data is available for training smile detection systems.

4k Face Recognition +1

Ambiguity set and learning via Bregman and Wasserstein

no code implementations23 May 2017 Xin Guo, Johnny Hong, Nan Yang

Construction of ambiguity set in robust optimization relies on the choice of divergences between probability distributions.

BIG-bench Machine Learning

Relaxed Wasserstein with Applications to GANs

no code implementations19 May 2017 Xin Guo, Johnny Hong, Tianyi Lin, Nan Yang

Wasserstein Generative Adversarial Networks (WGANs) provide a versatile class of models, which have attracted great attention in various applications.

Image Generation

Distributed learning with regularized least squares

no code implementations11 Aug 2016 Shao-Bo Lin, Xin Guo, Ding-Xuan Zhou

We study distributed learning with the least squares regularization scheme in a reproducing kernel Hilbert space (RKHS).

Robust Object Co-detection

no code implementations CVPR 2013 Xin Guo, Dong Liu, Brendan Jou, Mojun Zhu, Anni Cai, Shih-Fu Chang

Object co-detection aims at simultaneous detection of objects of the same category from a pool of related images by exploiting consistent visual patterns present in candidate objects in the images.

Clustering Object +2

Cannot find the paper you are looking for? You can Submit a new open access paper.