Search Results for author: Kai Yang

Found 68 papers, 20 papers with code

MolFM: A Multimodal Molecular Foundation Model

2 code implementations6 Jun 2023 Yizhen Luo, Kai Yang, Massimo Hong, Xing Yi Liu, Zaiqing Nie

In this study, we introduce MolFM, a multimodal molecular foundation model designed to facilitate joint representation learning from molecular structures, biomedical texts, and knowledge graphs.

Cross-Modal Retrieval Knowledge Graphs +4

Group-wise Correlation Stereo Network

2 code implementations CVPR 2019 Xiaoyang Guo, Kai Yang, Wukui Yang, Xiaogang Wang, Hongsheng Li

Previous works built cost volumes with cross-correlation or concatenation of left and right features across all disparity levels, and then a 2D or 3D convolutional neural network is utilized to regress the disparity maps.

Autonomous Driving Stereo Matching +1

A Unified Model for Multi-class Anomaly Detection

1 code implementation8 Jun 2022 Zhiyuan You, Lei Cui, Yujun Shen, Kai Yang, Xin Lu, Yu Zheng, Xinyi Le

For example, when learning a unified model for 15 categories in MVTec-AD, we surpass the second competitor on the tasks of both anomaly detection (from 88. 1% to 96. 5%) and anomaly localization (from 89. 5% to 96. 8%).

Unsupervised Anomaly Detection

SyntaxSQLNet: Syntax Tree Networks for Complex and Cross-DomainText-to-SQL Task

2 code implementations11 Oct 2018 Tao Yu, Michihiro Yasunaga, Kai Yang, Rui Zhang, Dongxu Wang, Zifan Li, Dragomir Radev

In this paper we propose SyntaxSQLNet, a syntax tree network to address the complex and cross-domain text-to-SQL generation task.

Semantic Parsing Text-To-SQL

Few-shot Object Counting with Similarity-Aware Feature Enhancement

1 code implementation22 Jan 2022 Zhiyuan You, Kai Yang, Wenhan Luo, Xin Lu, Lei Cui, Xinyi Le

This work studies the problem of few-shot object counting, which counts the number of exemplar objects (i. e., described by one or several support images) occurring in the query image.

Crowd Counting Object Counting

LSOTB-TIR:A Large-Scale High-Diversity Thermal Infrared Object Tracking Benchmark

1 code implementation3 Aug 2020 Qiao Liu, Xin Li, Zhenyu He, Chenglong Li, Jun Li, Zikun Zhou, Di Yuan, Jing Li, Kai Yang, Nana Fan, Feng Zheng

We evaluate and analyze more than 30 trackers on LSOTB-TIR to provide a series of baselines, and the results show that deep trackers achieve promising performance.

Thermal Infrared Object Tracking Vocal Bursts Intensity Prediction

Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model

1 code implementation22 Nov 2023 Kai Yang, Jian Tao, Jiafei Lyu, Chunjiang Ge, Jiaxin Chen, Qimai Li, Weihan Shen, Xiaolong Zhu, Xiu Li

The direct preference optimization (DPO) method, effective in fine-tuning large language models, eliminates the necessity for a reward model.

Denoising

Arbitrary Handwriting Image Style Transfer

1 code implementation14 Jan 2022 Kai Yang, Xiaoman Liang, Huihuang Zhao

This paper proposed a method to imitate handwriting style by style transfer.

Image Generation Saliency Detection +1

UTBoost: A Tree-boosting based System for Uplift Modeling

1 code implementation5 Dec 2023 Junjie Gao, Xiangyu Zheng, Dongdong Wang, Zhixiang Huang, Bangqi Zheng, Kai Yang

Uplift modeling refers to the set of machine learning techniques that a manager may use to estimate customer uplift, that is, the net effect of an action on some customer outcome.

Ensemble Learning

Incorporating Features Learned by an Enhanced Deep Knowledge Tracing Model for STEM/Non-STEM Job Prediction

1 code implementation6 Jun 2018 Chun-kit Yeung, Zizheng Lin, Kai Yang, Dit-yan Yeung

The 2017 ASSISTments Data Mining competition aims to use data from a longitudinal study for predicting a brand-new outcome of students which had never been studied before by the educational data mining research community.

Job Prediction Knowledge Tracing

SOTIF Entropy: Online SOTIF Risk Quantification and Mitigation for Autonomous Driving

1 code implementation8 Nov 2022 Liang Peng, Boqi Li, Wenhao Yu, Kai Yang, Wenbo Shao, Hong Wang

Therefore, this paper proposes the "Self-Surveillance and Self-Adaption System" as a systematic approach to online minimize the SOTIF risk, which aims to provide a systematic solution for monitoring, quantification, and mitigation of inherent and external risks.

Autonomous Driving Decision Making

Asynchronous Distributed Bilevel Optimization

1 code implementation20 Dec 2022 Yang Jiao, Kai Yang, Tiancheng Wu, Dongjin Song, Chengtao Jian

Bilevel optimization plays an essential role in many machine learning tasks, ranging from hyperparameter optimization to meta-learning.

Bilevel Optimization Hyperparameter Optimization +1

Exploration and Anti-Exploration with Distributional Random Network Distillation

1 code implementation18 Jan 2024 Kai Yang, Jian Tao, Jiafei Lyu, Xiu Li

To address this issue, we introduce the Distributional RND (DRND), a derivative of the RND.

D4RL

SUBIC: A Supervised Bi-Clustering Approach for Precision Medicine

no code implementations26 Sep 2017 Milad Zafar Nezhad, Dongxiao Zhu, Najibesadat Sadati, Kai Yang, Phillip Levy

Traditional medicine typically applies one-size-fits-all treatment for the entire patient population whereas precision medicine develops tailored treatment schemes for different patient subgroups.

Clustering

A predictive analytics approach to reducing avoidable hospital readmission

no code implementations24 Feb 2014 Issac Shams, Saeede Ajorlou, Kai Yang

We further propose a tree based classification method to estimate the predicted probability of readmission that can directly incorporate patient's history of readmission and risk factors changes over time.

Attribute Management

Active Learning for Wireless IoT Intrusion Detection

no code implementations4 Aug 2018 Kai Yang, Jie Ren, Yanqiao Zhu, Weiyi Zhang

This paper discusses the human-in-the-loop active learning approach for wireless intrusion detection.

Active Learning BIG-bench Machine Learning +1

Effective Feature Learning with Unsupervised Learning for Improving the Predictive Models in Massive Open Online Courses

no code implementations12 Dec 2018 Mucong Ding, Kai Yang, Dit-yan Yeung, Ting-Chuen Pong

A major challenge that has to be addressed when building such models is to design handcrafted features that are effective for the prediction task at hand.

Exploring Topic Discriminating Power of Words in Latent Dirichlet Allocation

no code implementations COLING 2016 Kai Yang, Yi Cai, Zhenhong Chen, Ho-fung Leung, Raymond Lau

Latent Dirichlet Allocation (LDA) and its variants have been widely used to discover latent topics in textual documents.

Topic Models

Federated Learning via Over-the-Air Computation

no code implementations31 Dec 2018 Kai Yang, Tao Jiang, Yuanming Shi, Zhi Ding

Instead, edge machine learning becomes increasingly attractive for performing training and inference directly at network edges without sending data to a centralized data center.

BIG-bench Machine Learning Cloud Computing +1

Multi-task Prediction of Patient Workload

no code implementations27 Dec 2018 Mohammad Hessam Olya, Dongxiao Zhu, Kai Yang

This issue becomes more critical for the healthcare facilities that provide service for chronic disease treatment because of the need for continuous treatments over the time.

Decision Making Multi-Task Learning

Energy-Efficient Processing and Robust Wireless Cooperative Transmission for Edge Inference

no code implementations29 Jul 2019 Kai Yang, Yuanming Shi, Wei Yu, Zhi Ding

Edge machine learning can deliver low-latency and private artificial intelligent (AI) services for mobile devices by leveraging computation and storage resources at the network edge.

Edge-computing

Predicting patient risk of readmission with frailty models in the Department of Veteran Affairs

no code implementations5 Mar 2014 Saeede Ajorlou, Issac Shams, Kai Yang

Reducing potentially preventable readmissions has been identified as an important issue for decreasing Medicare costs and improving quality of care provided by hospitals.

Applications 62N01, 62N02, 62P10

Inexact Primal-Dual Gradient Projection Methods for Nonlinear Optimization on Convex Set

no code implementations18 Nov 2019 Fan Zhang, Hao Wang, Jiashan Wang, Kai Yang

In this paper, we propose a novel primal-dual inexact gradient projection method for nonlinear optimization problems with convex-set constraint.

A Quasi-Newton Method Based Vertical Federated Learning Framework for Logistic Regression

no code implementations1 Dec 2019 Kai Yang, Tao Fan, Tianjian Chen, Yuanming Shi, Qiang Yang

Our approach can considerably reduce the number of communication rounds with a little additional communication cost per round.

regression Vertical Federated Learning

Communication-Efficient Edge AI: Algorithms and Systems

no code implementations22 Feb 2020 Yuanming Shi, Kai Yang, Tao Jiang, Jun Zhang, Khaled B. Letaief

By pushing inference and training processes of AI models to edge nodes, edge AI has emerged as a promising alternative.

Drug Discovery Image Classification

Federated Machine Learning for Intelligent IoT via Reconfigurable Intelligent Surface

no code implementations13 Apr 2020 Kai Yang, Yuanming Shi, Yong Zhou, Zhanpeng Yang, Liqun Fu, Wei Chen

Intelligent Internet-of-Things (IoT) will be transformative with the advancement of artificial intelligence and high-dimensional data analysis, shifting from "connected things" to "connected intelligence".

BIG-bench Machine Learning Self-Driving Cars

Communication-Efficient Edge AI Inference Over Wireless Networks

no code implementations28 Apr 2020 Kai Yang, Yong Zhou, Zhanpeng Yang, Yuanming Shi

Given the fast growth of intelligent devices, it is expected that a large number of high-stake artificial intelligence (AI) applications, e. g., drones, autonomous cars, tactile robots, will be deployed at the edge of wireless networks in the near future.

Distributed Computing Edge-computing +1

TimeAutoML: Autonomous Representation Learning for Multivariate Irregularly Sampled Time Series

no code implementations4 Oct 2020 Yang Jiao, Kai Yang, Shaoyu Dou, Pan Luo, Sijia Liu, Dongjin Song

To this end, we propose an autonomous representation learning approach for multivariate time series (TimeAutoML) with irregular sampling rates and variable lengths.

Anomaly Detection Clustering +4

Hybrid Beamforming for Terahertz Multi-Carrier Systems over Frequency Selective Fading

no code implementations14 Oct 2019 Hang Yuan, Nan Yang, Kai Yang, Chong Han, Jianping An

We consider a three-dimensional wideband THz channel by incorporating the joint effect of molecular absorption, high sparsity, and multi-path fading, and consider the carrier frequency offset in multi-carrier systems.

Uplink Sensing in Perceptive Mobile Networks with Asynchronous Transceivers

no code implementations18 Nov 2020 Zhitong Ni, J. Andrew Zhang, Xiaojing Huang, Kai Yang, Jinhong Yuan

We first adopt a cross-antenna cross-correlation (CACC) operation to remove the sensing ambiguity associated with both TOs and CFOs.

Interaction with an obstacle in the 2d focusing nonlinear Schrödinger equation

no code implementations3 Feb 2021 Oussama Landoulsi, Svetlana Roudenko, Kai Yang

Moreover, we show that the sharp threshold for global existence vs. finite time blow-up solutions in the mass critical case in the presence of the obstacle is the same as the one given by Weinstein for {\rm{NLS}} in the whole Euclidean space $\R^d$.

Analysis of PDEs Numerical Analysis Numerical Analysis

Weak Radio Frequency Signal Detection Based on Piezo-Opto-Electro-Mechanical System: Architecture Design and Sensitivity Prediction

no code implementations29 Mar 2020 Shanchi Wu, Chen Gong, Chengjie Zuo, Shangbin Li, Junyu Zhang, Zhongbin Dai, Kai Yang, Ming Zhao, Rui Ni, Zhengyuan Xu, Jinkang Zhu

We propose a novel radio-frequency (RF) receiving architecture based on micro-electro-mechanical system (MEMS) and optical coherent detection module.

Fed-EINI: An Efficient and Interpretable Inference Framework for Decision Tree Ensembles in Federated Learning

no code implementations20 May 2021 Xiaolin Chen, Shuai Zhou, Bei guan, Kai Yang, Hao Fan, Hu Wang, Yongji Wang

With this key observation, we protect data privacy and allow the disclosure of feature meaning by concealing decision paths and adapt a communication-efficient secure computation method for inference outputs.

BIG-bench Machine Learning Privacy Preserving +1

Efficient Batch Homomorphic Encryption for Vertically Federated XGBoost

no code implementations8 Dec 2021 Wuxing Xu, Hao Fan, Kaixin Li, Kai Yang

In this paper, we studied the efficiency problem of adapting widely used XGBoost model in real-world applications to vertical federated learning setting.

Quantization Vertical Federated Learning

FedGBF: An efficient vertical federated learning framework via gradient boosting and bagging

no code implementations3 Apr 2022 Yujin Han, Pan Du, Kai Yang

With the aim of obtaining an outstanding performance with less time cost, we propose a novel model in a vertically federated setting termed as Federated Gradient Boosting Forest (FedGBF).

Vertical Federated Learning

Heterogeneous Ultra-Dense Networks with Traffic Hotspots: A Unified Handover Analysis

no code implementations7 Apr 2022 He Zhou, Haibo Zhou, Jianguo Li, Kai Yang, Jianping An, Xuemin, Shen

By combining the PCP and MRWP model, the distributions of distances from a typical terminal to the BSs in different tiers are derived.

Point Processes

Task-aware Similarity Learning for Event-triggered Time Series

no code implementations17 Jul 2022 Shaoyu Dou, Kai Yang, Yang Jiao, Chengbo Qiu, Kui Ren

The proposed framework aspires to offer a stepping stone that gives rise to a systematic approach to model and learn similarities among a multitude of event-triggered time series.

Anomaly Detection Time Series +1

ADTR: Anomaly Detection Transformer with Feature Reconstruction

no code implementations5 Sep 2022 Zhiyuan You, Kai Yang, Wenhan Luo, Lei Cui, Yu Zheng, Xinyi Le

Second, CNN tends to reconstruct both normal samples and anomalies well, making them still hard to distinguish.

Anomaly Detection

Trustworthy Federated Learning via Blockchain

no code implementations13 Aug 2022 Zhanpeng Yang, Yuanming Shi, Yong Zhou, Zixin Wang, Kai Yang

In this paper, we shall propose a decentralized blockchain based FL (B-FL) architecture by using a secure global aggregation algorithm to resist malicious devices, and deploying practical Byzantine fault tolerance consensus protocol with high effectiveness and low energy consumption among multiple edge servers to prevent model tampering from the malicious server.

Autonomous Driving Federated Learning +3

Distributed Distributionally Robust Optimization with Non-Convex Objectives

no code implementations14 Oct 2022 Yang Jiao, Kai Yang, Dongjin Song

Distributionally Robust Optimization (DRO), which aims to find an optimal decision that minimizes the worst case cost over the ambiguity set of probability distribution, has been widely applied in diverse applications, e. g., network behavior analysis, risk management, etc.

Management

AI Empowered Net-RCA for 6G

no code implementations1 Dec 2022 Chengbo Qiu, Kai Yang, Ji Wang, Shenjie Zhao

6G is envisioned to offer higher data rate, improved reliability, ubiquitous AI services, and support massive scale of connected devices.

Management

Unsupervised Deep Learning for IoT Time Series

no code implementations7 Feb 2023 Ya Liu, Yingjie Zhou, Kai Yang, Xin Wang

IoT time series analysis has found numerous applications in a wide variety of areas, ranging from health informatics to network security.

Clustering Representation Learning +3

Bayesian Beta-Bernoulli Process Sparse Coding with Deep Neural Networks

no code implementations14 Mar 2023 Arunesh Mittal, Kai Yang, Paul Sajda, John Paisley

Several approximate inference methods have been proposed for deep discrete latent variable models.

Towards Unified AI Drug Discovery with Multiple Knowledge Modalities

no code implementations17 Apr 2023 Yizhen Luo, Xing Yi Liu, Kai Yang, Kui Huang, Massimo Hong, Jiahuan Zhang, Yushuai Wu, Zaiqing Nie

In recent years, AI models that mine intrinsic patterns from molecular structures and protein sequences have shown promise in accelerating drug discovery.

Drug Discovery Knowledge Graphs +2

Federated Distributionally Robust Optimization with Non-Convex Objectives: Algorithm and Analysis

no code implementations25 Jul 2023 Yang Jiao, Kai Yang, Dongjin Song

Distributionally Robust Optimization (DRO), which aims to find an optimal decision that minimizes the worst case cost over the ambiguity set of probability distribution, has been widely applied in diverse applications, e. g., network behavior analysis, risk management, etc.

Management

Local Structure-aware Graph Contrastive Representation Learning

no code implementations7 Aug 2023 Kai Yang, YuAn Liu, Zijuan Zhao, Peijin Ding, Wenqian Zhao

Traditional Graph Neural Network (GNN), as a graph representation learning method, is constrained by label information.

Contrastive Learning Graph Representation Learning +2

Lightning-Fast Dual-Layer Lossless Coding for Radiance Format High Dynamic Range Images

no code implementations20 Sep 2023 Taizo Suzuki, Sara Yukikata, Kai Yang, Taichi Yoshida

To suppress the dynamic range of the residuals in the enhancement layer, the coding directly uses the mantissa and exponent information from the Radiance format.

Few-Shot Recognition and Classification of Jamming Signal via CGAN-Based Fusion CNN Algorithm

no code implementations9 Nov 2023 Xuhui Ding, Yue Zhang, Gaoyang Li, Neng Ye, Yuting Guo, Takuya Mabuchi, Hitomi Anzai, Kai Yang

The precise classification of jamming signals holds paramount significance in the effective implementation of anti-jamming strategies within communication systems subject to intricate environmental variables.

Generative Adversarial Network

Provably Convergent Federated Trilevel Learning

no code implementations19 Dec 2023 Yang Jiao, Kai Yang, Tiancheng Wu, Chengtao Jian, Jianwei Huang

To address the aforementioned challenges, this paper proposes an asynchronous federated trilevel optimization method to solve TLO problems.

Decision Making Domain Adaptation +2

Two Stones Hit One Bird: Bilevel Positional Encoding for Better Length Extrapolation

no code implementations29 Jan 2024 Zhenyu He, Guhao Feng, Shengjie Luo, Kai Yang, Di He, Jingjing Xu, Zhi Zhang, Hongxia Yang, LiWei Wang

In this work, we leverage the intrinsic segmentation of language sequences and design a new positional encoding method called Bilevel Positional Encoding (BiPE).

Disentanglement Position

BATON: Aligning Text-to-Audio Model with Human Preference Feedback

no code implementations1 Feb 2024 Huan Liao, Haonan Han, Kai Yang, Tianjiao Du, Rui Yang, Zunnan Xu, Qinmei Xu, Jingquan Liu, Jiasheng Lu, Xiu Li

With the development of AI-Generated Content (AIGC), text-to-audio models are gaining widespread attention.

Do Efficient Transformers Really Save Computation?

no code implementations21 Feb 2024 Kai Yang, Jan Ackermann, Zhenyu He, Guhao Feng, Bohang Zhang, Yunzhen Feng, Qiwei Ye, Di He, LiWei Wang

Our results show that while these models are expressive enough to solve general DP tasks, contrary to expectations, they require a model size that scales with the problem size.

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