no code implementations • ICLR 2019 • Yaohua Tang, Kaixiang Mo, Qian Xu, Chao Zhang, Qiang Yang
When building models for novel natural language domains, a major challenge is the lack of data in the new domains, no matter whether the data is annotated or not.
no code implementations • EMNLP 2020 • Zheng Li, Mukul Kumar, William Headden, Bing Yin, Ying WEI, Yu Zhang, Qiang Yang
Recent emergence of multilingual pre-training language model (mPLM) has enabled breakthroughs on various downstream cross-lingual transfer (CLT) tasks.
no code implementations • 30 Jan 2023 • Hanlin Gu, Jiahuan Luo, Yan Kang, Lixin Fan, Qiang Yang
Vertical federated learning (VFL) allows an active party with labeled feature to leverage auxiliary features from the passive parties to improve model performance.
no code implementations • 24 Nov 2022 • Hanlin Gu, Lixin Fan, Xingxing Tang, Qiang Yang
Extensive experimental results under a variety of settings justify the superiority of FedCut, which demonstrates extremely robust model performance (MP) under various attacks.
no code implementations • 23 Nov 2022 • Yang Liu, Yan Kang, Tianyuan Zou, Yanhong Pu, Yuanqin He, Xiaozhou Ye, Ye Ouyang, Ya-Qin Zhang, Qiang Yang
Vertical Federated Learning (VFL) is a federated learning setting where multiple parties with different features about the same set of users jointly train machine learning models without exposing their raw data or model parameters.
no code implementations • 14 Nov 2022 • Shuo Shao, Wenyuan Yang, Hanlin Gu, Jian Lou, Zhan Qin, Lixin Fan, Qiang Yang, Kui Ren
Copyright protection of the Federated Learning (FL) model has become a major concern since malicious clients in FL can stealthily distribute or sell the FL model to other parties.
no code implementations • 10 Oct 2022 • Dashan Gao, Xin Yao, Qiang Yang
Therefore, heterogeneous FL is proposed to address the problem of heterogeneity in FL.
no code implementations • 8 Sep 2022 • Yan Kang, Jiahuan Luo, Yuanqin He, Xiaojin Zhang, Lixin Fan, Qiang Yang
We then use this framework as a guide to comprehensively evaluate a broad range of protection mechanisms against most of the state-of-the-art privacy attacks for three widely-deployed VFL algorithms.
no code implementations • 1 Sep 2022 • Xiaojin Zhang, Yan Kang, Kai Chen, Lixin Fan, Qiang Yang
In addition, it is a mandate for a federated learning system to achieve high \textit{efficiency} in order to enable large-scale model training and deployment.
1 code implementation • 28 Aug 2022 • Yinghua Zhang, Yangqiu Song, Kun Bai, Qiang Yang
To successfully attack fine-tuned models under both settings, we propose to first train an adversarial generator against the source model, which adopts an encoder-decoder architecture and maps a clean input to an adversarial example.
no code implementations • 18 Aug 2022 • Yuanqin He, Yan Kang, Jiahuan Luo, Lixin Fan, Qiang Yang
The core idea of FedHSSL is to utilize cross-party views (i. e., dispersed features) of samples aligned among parties and local views (i. e., augmentations) of samples within each party to improve the representation learning capability of the joint VFL model through SSL (e. g., SimSiam).
no code implementations • 21 Jun 2022 • Youlong Ding, Xueyang Wu, Zhitao Li, Zeheng Wu, Shengqi Tan, Qian Xu, Weike Pan, Qiang Yang
Recently, the artificial intelligence of things (AIoT) has been gaining increasing attention, with an intriguing vision of providing highly intelligent services through the network connection of things, leading to an advanced AI-driven ecology.
no code implementations • 21 Jun 2022 • Xueyang Wu, Shengqi Tan, Qian Xu, Qiang Yang
The experimental results demonstrate that WrapperFL can be successfully applied to a wide range of applications under practical settings and improves the local model with federated learning at a low cost.
no code implementations • 27 May 2022 • Nannan Wu, Ning Zhang, Wenjun Wang, Lixin Fan, Qiang Yang
The proposed algorithm FadMan is a vertical federated learning framework for public node aligned with many private nodes of different features, and is validated on two tasks correlated anomaly detection on multiple attributed networks and anomaly detection on an attributeless network using five real-world datasets.
no code implementations • 3 May 2022 • Yuxiang Feng, Weilin Xie, Yinxia Meng, Jiang Yang, Qiang Yang, Yan Ren, Tianwai Bo, Zhongwei Tan, Wei Wei, Yi Dong
Coherent fading has been regarded as a critical issue in phase-sensitive optical frequency domain reflectometry ({\phi}-OFDR) based distributed fiber-optic sensing.
no code implementations • 21 Apr 2022 • Tao Yang, Jinming Wang, Weijie Hao, Qiang Yang, Wenhai Wang
The sensor data detection model based on Gaussian and Bayesian algorithms can detect the anomalous sensor data in real-time and upload them to the cloud for further analysis, filtering the normal sensor data and reducing traffic load.
no code implementations • 11 Mar 2022 • Xiaojin Zhang, Hanlin Gu, Lixin Fan, Kai Chen, Qiang Yang
In a federated learning scenario where multiple parties jointly learn a model from their respective data, there exist two conflicting goals for the choice of appropriate algorithms.
no code implementations • 15 Dec 2021 • Huiming Chen, Huandong Wang, Quanming Yao, Yong Li, Depeng Jin, Qiang Yang
Federated optimization (FedOpt), which targets at collaboratively training a learning model across a large number of distributed clients, is vital for federated learning.
no code implementations • 10 Dec 2021 • Yang Liu, Tianyuan Zou, Yan Kang, Wenhan Liu, Yuanqin He, Zhihao Yi, Qiang Yang
An immediate defense strategy is to protect sample-level messages communicated with Homomorphic Encryption (HE), and in this way only the batch-averaged local gradients are exposed to each party (termed black-boxed VFL).
no code implementations • 22 Nov 2021 • Yan Kang, Yang Liu, Yuezhou Wu, Guoqiang Ma, Qiang Yang
We present a novel privacy-preserving federated adversarial domain adaptation approach ($\textbf{PrADA}$) to address an under-studied but practical cross-silo federated domain adaptation problem, in which the party of the target domain is insufficient in both samples and features.
1 code implementation • 16 Nov 2021 • Yuezhou Wu, Yan Kang, Jiahuan Luo, Yuanqin He, Qiang Yang
Federated learning (FL) aims to protect data privacy by enabling clients to build machine learning models collaboratively without sharing their private data.
1 code implementation • 21 Oct 2021 • Weijing Chen, Guoqiang Ma, Tao Fan, Yan Kang, Qian Xu, Qiang Yang
Gradient boosting decision tree (GBDT) is a widely used ensemble algorithm in the industry.
2 code implementations • 12 Oct 2021 • Jiaan Wang, Zhixu Li, Qiang Yang, Jianfeng Qu, Zhigang Chen, Qingsheng Liu, Guoping Hu
Sports game summarization aims to generate news articles from live text commentaries.
no code implementations • 29 Sep 2021 • Jing Xie, Xiang Yin, Xiyi Zhang, Juan Chen, Quan Wen, Qiang Yang, Xuan Mo
In SPFL, the server uses the Softmax Normalized Gradient Similarity (SNGS) to weight the relationship between clients, and sends the personalized global model to each client.
no code implementations • 27 Sep 2021 • Hanlin Gu, Lixin Fan, Bowen Li, Yan Kang, Yuan YAO, Qiang Yang
To address the aforementioned perplexity, we propose a novel Bayesian Privacy (BP) framework which enables Bayesian restoration attacks to be formulated as the probability of reconstructing private data from observed public information.
1 code implementation • 27 Sep 2021 • Bowen Li, Lixin Fan, Hanlin Gu, Jie Li, Qiang Yang
To address these risks, the ownership verification of federated learning models is a prerequisite that protects federated learning model intellectual property rights (IPR) i. e., FedIPR.
no code implementations • 19 Sep 2021 • Shijie Chen, Yu Zhang, Qiang Yang
Deep learning approaches have achieved great success in the field of Natural Language Processing (NLP).
no code implementations • 9 Sep 2021 • Zhifeng Jiang, Wei Wang, Bo Li, Qiang Yang
The increasing demand for privacy-preserving collaborative learning has given rise to a new computing paradigm called federated learning (FL), in which clients collaboratively train a machine learning (ML) model without revealing their private training data.
no code implementations • 19 Aug 2021 • Danqing Zhang, Zheng Li, Tianyu Cao, Chen Luo, Tony Wu, Hanqing Lu, Yiwei Song, Bing Yin, Tuo Zhao, Qiang Yang
We study the problem of query attribute value extraction, which aims to identify named entities from user queries as diverse surface form attribute values and afterward transform them into formally canonical forms.
no code implementations • 18 Aug 2021 • Liu Yang, Junxue Zhang, Di Chai, Leye Wang, Kun Guo, Kai Chen, Qiang Yang
In this paper, we proposed federated masked matrix factorization (FedMMF) to protect the data privacy in federated recommender systems without sacrificing efficiency and effectiveness.
no code implementations • Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining 2021 • Dingyuan Shi, Yongxin Tong, Zimu Zhou, Bingchen Song, Weifeng Lv, Qiang Yang
Ride hailing is a widespread shared mobility application where the central issue is to assign taxi requests to drivers with various objectives.
1 code implementation • 6 Aug 2021 • Jiaqian Ren, Hao Peng, Lei Jiang, Jia Wu, Yongxin Tong, Lihong Wang, Xu Bai, Bo wang, Qiang Yang
Experiments on both synthetic and real-world datasets show the framework to be highly effective at detection in both multilingual data and in languages where training samples are scarce.
no code implementations • 30 Jun 2021 • Xu Geng, Yilun Jin, Zhengfei Zheng, Yu Yang, Yexin Li, Han Tian, Peibo Duan, Leye Wang, Jiannong Cao, Hai Yang, Qiang Yang, Kai Chen
Data-driven approaches have been applied to many problems in urban computing.
no code implementations • CVPR 2021 • Ding Sheng Ong, Chee Seng Chan, Kam Woh Ng, Lixin Fan, Qiang Yang
Ever since Machine Learning as a Service emerges as a viable business that utilizes deep learning models to generate lucrative revenue, Intellectual Property Right (IPR) has become a major concern because these deep learning models can easily be replicated, shared, and re-distributed by any unauthorized third parties.
no code implementations • 17 Jun 2021 • Long-Kai Huang, Ying WEI, Yu Rong, Qiang Yang, Junzhou Huang
Transferability estimation has been an essential tool in selecting a pre-trained model and the layers in it for transfer learning, to transfer, so as to maximize the performance on a target task and prevent negative transfer.
no code implementations • 16 Mar 2021 • Chang Liu, Lixin Fan, Kam Woh Ng, Yilun Jin, Ce Ju, Tianyu Zhang, Chee Seng Chan, Qiang Yang
This paper proposes a novel ternary hash encoding for learning to hash methods, which provides a principled more efficient coding scheme with performances better than those of the state-of-the-art binary hashing counterparts.
no code implementations • 1 Mar 2021 • Alysa Ziying Tan, Han Yu, Lizhen Cui, Qiang Yang
In parallel with the rapid adoption of Artificial Intelligence (AI) empowered by advances in AI research, there have been growing awareness and concerns of data privacy.
1 code implementation • 8 Feb 2021 • Ding Sheng Ong, Chee Seng Chan, Kam Woh Ng, Lixin Fan, Qiang Yang
Ever since Machine Learning as a Service (MLaaS) emerges as a viable business that utilizes deep learning models to generate lucrative revenue, Intellectual Property Right (IPR) has become a major concern because these deep learning models can easily be replicated, shared, and re-distributed by any unauthorized third parties.
no code implementations • 28 Jan 2021 • Xinle Liang, Yang Liu, Jiahuan Luo, Yuanqin He, Tianjian Chen, Qiang Yang
Federated Learning (FL) provides both model performance and data privacy for machine learning tasks where samples or features are distributed among different parties.
no code implementations • EACL 2021 • GuangNeng Hu, Qiang Yang
To take advantage of the existing corpus, we propose a transfer learning model (dubbed as TrNews) for news recommendation to transfer the knowledge from a source corpus to a target corpus.
no code implementations • 7 Dec 2020 • Lingjuan Lyu, Han Yu, Xingjun Ma, Chen Chen, Lichao Sun, Jun Zhao, Qiang Yang, Philip S. Yu
Besides training powerful global models, it is of paramount importance to design FL systems that have privacy guarantees and are resistant to different types of adversaries.
1 code implementation • NeurIPS 2020 • Wenzheng Feng, Jie Zhang, Yuxiao Dong, Yu Han, Huanbo Luan, Qian Xu, Qiang Yang, Evgeny Kharlamov, Jie Tang
We study the problem of semi-supervised learning on graphs, for which graph neural networks (GNNs) have been extensively explored.
no code implementations • 27 Nov 2020 • Yilun Jin, Lixin Fan, Kam Woh Ng, Ce Ju, Qiang Yang
Deep neural networks (DNNs) are known to be prone to adversarial attacks, for which many remedies are proposed.
1 code implementation • 19 Nov 2020 • Di Chai, Leye Wang, Liu Yang, Junxue Zhang, Kai Chen, Qiang Yang
In this paper, we propose a holistic evaluation framework for FL called FedEval, and present a benchmarking study on seven state-of-the-art FL algorithms.
no code implementations • Findings of the Association for Computational Linguistics 2020 • GuangNeng Hu, Qiang Yang
Existing research focuses on the recommendation performance of the target domain while ignores the privacy leakage of the source domain.
1 code implementation • 25 Aug 2020 • Yinghua Zhang, Yangqiu Song, Jian Liang, Kun Bai, Qiang Yang
To systematically measure the effect of both white-box and black-box attacks, we propose a new metric to evaluate how transferable are the adversarial examples produced by a source model to a target model.
1 code implementation • 25 Aug 2020 • Jian Han Lim, Chee Seng Chan, Kam Woh Ng, Lixin Fan, Qiang Yang
By and large, existing Intellectual Property (IP) protection on deep neural networks typically i) focus on image classification task only, and ii) follow a standard digital watermarking framework that was conventionally used to protect the ownership of multimedia and video content.
4 code implementations • 27 Jul 2020 • Chaoyang He, Songze Li, Jinhyun So, Xiao Zeng, Mi Zhang, Hongyi Wang, Xiaoyang Wang, Praneeth Vepakomma, Abhishek Singh, Hang Qiu, Xinghua Zhu, Jianzong Wang, Li Shen, Peilin Zhao, Yan Kang, Yang Liu, Ramesh Raskar, Qiang Yang, Murali Annavaram, Salman Avestimehr
Federated learning (FL) is a rapidly growing research field in machine learning.
no code implementations • 10 Jul 2020 • Longbing Cao, Qiang Yang, Philip S. Yu
Financial technology (FinTech) has been playing an increasingly critical role in driving modern economies, society, technology, and many other areas.
no code implementations • 3 Jul 2020 • Dashan Gao, Ben Tan, Ce Ju, Vincent W. Zheng, Qiang Yang
Matrix Factorization has been very successful in practical recommendation applications and e-commerce.
no code implementations • 20 Jun 2020 • Lixin Fan, Kam Woh Ng, Ce Ju, Tianyu Zhang, Chang Liu, Chee Seng Chan, Qiang Yang
This paper investigates capabilities of Privacy-Preserving Deep Learning (PPDL) mechanisms against various forms of privacy attacks.
3 code implementations • 18 Jun 2020 • Qiang Yang, Hind Alamro, Somayah Albaradei, Adil Salhi, Xiaoting Lv, Changsheng Ma, Manal Alshehri, Inji Jaber, Faroug Tifratene, Wei Wang, Takashi Gojobori, Carlos M. Duarte, Xin Gao, Xiangliang Zhang
Since the first alert launched by the World Health Organization (5 January, 2020), COVID-19 has been spreading out to over 180 countries and territories.
no code implementations • 31 May 2020 • Wei Yang Bryan Lim, Jer Shyuan Ng, Zehui Xiong, Dusit Niyato, Cyril Leung, Chunyan Miao, Qiang Yang
In 5G and Beyond networks, Artificial Intelligence applications are expected to be increasingly ubiquitous.
6 code implementations • 22 May 2020 • Wenzheng Feng, Jie Zhang, Yuxiao Dong, Yu Han, Huanbo Luan, Qian Xu, Qiang Yang, Evgeny Kharlamov, Jie Tang
We study the problem of semi-supervised learning on graphs, for which graph neural networks (GNNs) have been extensively explored.
no code implementations • 20 May 2020 • Yuanfei Luo, Hao Zhou, Wei-Wei Tu, Yuqiang Chen, Wenyuan Dai, Qiang Yang
As a result, the intra-field information and the non-linear interactions between those operations (e. g. neural network and factorization machines) are ignored.
1 code implementation • 12 Mar 2020 • Yinghua Zhang, Yu Zhang, Ying WEI, Kun Bai, Yangqiu Song, Qiang Yang
Though the learned representations are separable in the source domain, they usually have a large variance and samples with different class labels tend to overlap in the target domain, which yields suboptimal adaptation performance.
no code implementations • 4 Mar 2020 • Lingjuan Lyu, Han Yu, Qiang Yang
It is thus of paramount importance to make FL system designers to be aware of the implications of future FL algorithm design on privacy-preservation.
no code implementations • 26 Feb 2020 • Yilun Jin, Xiguang Wei, Yang Liu, Qiang Yang
Federated Learning (FL) proposed in recent years has received significant attention from researchers in that it can bring separate data sources together and build machine learning models in a collaborative but private manner.
no code implementations • 23 Jan 2020 • Anbu Huang, YuanYuan Chen, Yang Liu, Tianjian Chen, Qiang Yang
Federated learning is a distributed machine learning framework which enables different parties to collaboratively train a model while protecting data privacy and security.
no code implementations • 17 Jan 2020 • Yang Liu, Anbu Huang, Yun Luo, He Huang, Youzhi Liu, YuanYuan Chen, Lican Feng, Tianjian Chen, Han Yu, Qiang Yang
Federated learning (FL) is a promising approach to resolve this challenge.
no code implementations • 24 Dec 2019 • Yang Liu, Yan Kang, Xinwei Zhang, Liping Li, Yong Cheng, Tianjian Chen, Mingyi Hong, Qiang Yang
We introduce a collaborative learning framework allowing multiple parties having different sets of attributes about the same user to jointly build models without exposing their raw data or model parameters.
7 code implementations • 10 Dec 2019 • Peter Kairouz, H. Brendan McMahan, Brendan Avent, Aurélien Bellet, Mehdi Bennis, Arjun Nitin Bhagoji, Kallista Bonawitz, Zachary Charles, Graham Cormode, Rachel Cummings, Rafael G. L. D'Oliveira, Hubert Eichner, Salim El Rouayheb, David Evans, Josh Gardner, Zachary Garrett, Adrià Gascón, Badih Ghazi, Phillip B. Gibbons, Marco Gruteser, Zaid Harchaoui, Chaoyang He, Lie He, Zhouyuan Huo, Ben Hutchinson, Justin Hsu, Martin Jaggi, Tara Javidi, Gauri Joshi, Mikhail Khodak, Jakub Konečný, Aleksandra Korolova, Farinaz Koushanfar, Sanmi Koyejo, Tancrède Lepoint, Yang Liu, Prateek Mittal, Mehryar Mohri, Richard Nock, Ayfer Özgür, Rasmus Pagh, Mariana Raykova, Hang Qi, Daniel Ramage, Ramesh Raskar, Dawn Song, Weikang Song, Sebastian U. Stich, Ziteng Sun, Ananda Theertha Suresh, Florian Tramèr, Praneeth Vepakomma, Jianyu Wang, Li Xiong, Zheng Xu, Qiang Yang, Felix X. Yu, Han Yu, Sen Zhao
FL embodies the principles of focused data collection and minimization, and can mitigate many of the systemic privacy risks and costs resulting from traditional, centralized machine learning and data science approaches.
no code implementations • 1 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.
no code implementations • 17 Nov 2019 • Zhuo Yang, Yufei Han, Guoxian Yu, Qiang Yang, Xiangliang Zhang
We propose to formulate multi-label learning as a estimation of class distribution in a non-linear embedding space, where for each label, its positive data embeddings and negative data embeddings distribute compactly to form a positive component and negative component respectively, while the positive component and negative component are pushed away from each other.
no code implementations • IJCNLP 2019 • Yuanfeng Song, Di Jiang, Weiwei Zhao, Qian Xu, Raymond Chi-Wing Wong, Qiang Yang
With this demonstration, the audience can experience the effect of LMA in an interactive and real-time fashion.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
1 code implementation • IJCNLP 2019 • Zheng Li, Xin Li, Ying WEI, Lidong Bing, Yu Zhang, Qiang Yang
Joint extraction of aspects and sentiments can be effectively formulated as a sequence labeling problem.
Aspect-Based Sentiment Analysis
Unsupervised Domain Adaptation
no code implementations • 25 Oct 2019 • Yuanfeng Song, Di Jiang, Xuefang Zhao, Qian Xu, Raymond Chi-Wing Wong, Lixin Fan, Qiang Yang
Modern Automatic Speech Recognition (ASR) systems primarily rely on scores from an Acoustic Model (AM) and a Language Model (LM) to rescore the N-best lists.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
no code implementations • 14 Oct 2019 • Xinle Liang, Yang Liu, Tianjian Chen, Ming Liu, Qiang Yang
Reinforcement learning (RL) is widely used in autonomous driving tasks and training RL models typically involves in a multi-step process: pre-training RL models on simulators, uploading the pre-trained model to real-life robots, and fine-tuning the weight parameters on robot vehicles.
1 code implementation • 14 Oct 2019 • Jiahuan Luo, Xueyang Wu, Yun Luo, Anbu Huang, Yun-Feng Huang, Yang Liu, Qiang Yang
Federated learning is a new machine learning paradigm which allows data parties to build machine learning models collaboratively while keeping their data secure and private.
no code implementations • 25 Sep 2019 • Xu Geng, Lingyu Zhang, Shulin Li, Yuanbo Zhang, Lulu Zhang, Leye Wang, Qiang Yang, Hongtu Zhu, Jieping Ye
Deep learning based approaches have been widely used in various urban spatio-temporal forecasting problems, but most of them fail to account for the unsmoothness issue of urban data in their architecture design, which significantly deteriorates their prediction performance.
1 code implementation • 17 Sep 2019 • Jindong Wang, Yiqiang Chen, Wenjie Feng, Han Yu, Meiyu Huang, Qiang Yang
Since the source and the target domains are usually from different distributions, existing methods mainly focus on adapting the cross-domain marginal or conditional distributions.
Ranked #6 on
Domain Adaptation
on ImageCLEF-DA
1 code implementation • 11 Sep 2019 • Dashan Gao, Ce Ju, Xiguang Wei, Yang Liu, Tianjian Chen, Qiang Yang
To verify the effectiveness of our approach, we conduct experiments on a real-world EEG dataset, consisting of heterogeneous data collected from diverse devices.
1 code implementation • AAAI 2019 • Xu Geng, Yaguang Li, Leye Wang, Lingyu Zhang, Qiang Yang, Jieping Ye, Yan Liu
This task is challenging due to the complicated spatiotemporal dependencies among regions.
no code implementations • 12 Jun 2019 • Di Chai, Leye Wang, Kai Chen, Qiang Yang
The key principle of federated learning is training a machine learning model without needing to know each user's personal raw private data.
1 code implementation • 28 May 2019 • Wenyi Xiao, Huan Zhao, Haojie Pan, Yangqiu Song, Vincent W. Zheng, Qiang Yang
An effective content recommendation in modern social media platforms should benefit both creators to bring genuine benefits to them and consumers to help them get really interesting content.
no code implementations • 27 May 2019 • Xu Geng, Xiyu Wu, Lingyu Zhang, Qiang Yang, Yan Liu, Jieping Ye
To incorporate multiple relationships into spatial feature extraction, we define the problem as a multi-modal machine learning problem on multi-graph convolution networks.
no code implementations • 29 Apr 2019 • Yuanfei Luo, Mengshuo Wang, Hao Zhou, Quanming Yao, Wei-Wei Tu, Yuqiang Chen, Qiang Yang, Wenyuan Dai
Feature crossing captures interactions among categorical features and is useful to enhance learning from tabular data in real-world businesses.
1 code implementation • 2 Apr 2019 • Jindong Wang, Yiqiang Chen, Han Yu, Meiyu Huang, Qiang Yang
In this paper, we propose a practically Easy Transfer Learning (EasyTL) approach which requires no model selection and hyperparameter tuning, while achieving competitive performance.
Ranked #5 on
Transfer Learning
on Office-Home
1 code implementation • CVPR 2019 • Zhangjie Cao, Kaichao You, Mingsheng Long, Jian-Min Wang, Qiang Yang
Under the condition that target labels are unknown, the key challenge of PDA is how to transfer relevant examples in the shared classes to promote positive transfer, and ignore irrelevant ones in the specific classes to mitigate negative transfer.
Ranked #4 on
Partial Domain Adaptation
on ImageNet-Caltech
no code implementations • 12 Mar 2019 • Hugo Jair Escalante, Wei-Wei Tu, Isabelle Guyon, Daniel L. Silver, Evelyne Viegas, Yuqiang Chen, Wenyuan Dai, Qiang Yang
We organized a competition on Autonomous Lifelong Machine Learning with Drift that was part of the competition program of NeurIPS 2018.
1 code implementation • 13 Feb 2019 • Qiang Yang, Yang Liu, Tianjian Chen, Yongxin Tong
We propose a possible solution to these challenges: secure federated learning.
1 code implementation • 25 Jan 2019 • Kewei Cheng, Tao Fan, Yilun Jin, Yang Liu, Tianjian Chen, Dimitrios Papadopoulos, Qiang Yang
This federated learning system allows the learning process to be jointly conducted over multiple parties with common user samples but different feature sets, which corresponds to a vertically partitioned data set.
no code implementations • 24 Jan 2019 • Hankz Hankui Zhuo, Wenfeng Feng, Yufeng Lin, Qian Xu, Qiang Yang
In deep reinforcement learning, building policies of high-quality is challenging when the feature space of states is small and the training data is limited.
no code implementations • 22 Jan 2019 • Guang-Neng Hu, Yu Zhang, Qiang Yang
Another thread is to transfer knowledge from other source domains such as improving the movie recommendation with the knowledge from the book domain, leading to transfer learning methods.
no code implementations • 8 Dec 2018 • Yang Liu, Yan Kang, Chaoping Xing, Tianjian Chen, Qiang Yang
A secure transfer cross validation approach is also proposed to guard the FTL performance under the federation.
no code implementations • 7 Dec 2018 • Han Yu, Zhiqi Shen, Chunyan Miao, Cyril Leung, Victor R. Lesser, Qiang Yang
As artificial intelligence (AI) systems become increasingly ubiquitous, the topic of AI governance for ethical decision-making by AI has captured public imagination.
no code implementations • 23 Nov 2018 • Quanming Yao, Xiawei Guo, James T. Kwok, WeiWei Tu, Yuqiang Chen, Wenyuan Dai, Qiang Yang
To meet the standard of differential privacy, noise is usually added into the original data, which inevitably deteriorates the predicting performance of subsequent learning algorithms.
1 code implementation • AAAI 2019 2018 • Zheng Li, Ying WEI, Yu Zhang, Xiang Zhang, Xin Li, Qiang Yang
Aspect-level sentiment classification (ASC) aims at identifying sentiment polarities towards aspects in a sentence, where the aspect can behave as a general Aspect Category (AC) or a specific Aspect Term (AT).
1 code implementation • 31 Oct 2018 • Quanming Yao, Mengshuo Wang, Yuqiang Chen, Wenyuan Dai, Yu-Feng Li, Wei-Wei Tu, Qiang Yang, Yang Yu
We hope this survey can serve as not only an insightful guideline for AutoML beginners but also an inspiration for future research.
no code implementations • 5 Aug 2018 • Leye Wang, Bin Guo, Qiang Yang
To address this problem, transfer learning can be leveraged to accelerate the smart city development, which we term the urban transfer learning paradigm.
1 code implementation • 28 Jul 2018 • Di Chai, Leye Wang, Qiang Yang
We propose a new multi-graph convolutional neural network model to predict the bike flow at station-level, where the key novelty is viewing the bike sharing system from the graph perspective.
no code implementations • ICML 2018 • Ying WEI, Yu Zhang, Junzhou Huang, Qiang Yang
In transfer learning, what and how to transfer are two primary issues to be addressed, as different transfer learning algorithms applied between a source and a target domain result in different knowledge transferred and thereby the performance improvement in the target domain.
no code implementations • NeurIPS 2018 • Yu Zhang, Ying WEI, Qiang Yang
Based on such training set, L2MT first uses a proposed layerwise graph neural network to learn task embeddings for all the tasks in a multitask problem and then learns an estimation function to estimate the relative test error based on task embeddings and the representation of the multitask model based on a unified formulation.
1 code implementation • Thirty-Second AAAI Conference on Artificial Intelligence 2018 • Zheng Li, Ying WEI, Yu Zhang, Qiang Yang
Existing cross-domain sentiment classification meth- ods cannot automatically capture non-pivots, i. e., the domain- specific sentiment words, and pivots, i. e., the domain-shared sentiment words, simultaneously.
no code implementations • 23 Apr 2018 • Yinghua Zhang, Yu Zhang, Qiang Yang
Unfortunately, the transferability is usually defined as discrete states and it differs with domains and network architectures.
no code implementations • 20 Apr 2018 • Kaixiang Mo, Yu Zhang, Qiang Yang, Pascale Fung
Also, they depend on either common slots or slot entropy, which are not available when the source and target slots are totally disjoint and no database is available to calculate the slot entropy.
1 code implementation • 18 Apr 2018 • Guang-Neng Hu, Yu Zhang, Qiang Yang
CoNet enables dual knowledge transfer across domains by introducing cross connections from one base network to another and vice versa.
no code implementations • 17 Apr 2018 • GuangNeng Hu, Yu Zhang, Qiang Yang
By modeling content information as local memories, LCMR attentively learns what to exploit with the guidance of user-item interaction.
no code implementations • 1 Feb 2018 • Leye Wang, Xu Geng, Xiaojuan Ma, Feng Liu, Qiang Yang
RegionTrans aims to effectively transfer knowledge from a data-rich source city to a data-scarce target city.
no code implementations • 11 Nov 2017 • Kaixiang Mo, Yu Zhang, Qiang Yang, Pascale Fung
Training a personalized dialogue system requires a lot of data, and the data collected for a single user is usually insufficient.
no code implementations • 10 Nov 2017 • Weiyan Wang, Yuxiang Wu, Yu Zhang, Zhongqi Lu, Kaixiang Mo, Qiang Yang
Then the built user model is used as a leverage to train the agent model by deep reinforcement learning.
no code implementations • 13 Sep 2017 • Wenya Zhu, Kaixiang Mo, Yu Zhang, Zhangbin Zhu, Xuezheng Peng, Qiang Yang
Although existing generative question answering (QA) systems can be applied to knowledge grounded conversation, they either have at most one entity in a response or cannot deal with out-of-vocabulary entities.
no code implementations • 18 Aug 2017 • Ying Wei, Yu Zhang, Qiang Yang
We establish the L2T framework in two stages: 1) we first learn a reflection function encrypting transfer learning skills from experiences; and 2) we infer what and how to transfer for a newly arrived pair of domains by optimizing the reflection function.
1 code implementation • 25 Jul 2017 • Yu Zhang, Qiang Yang
Multi-Task Learning (MTL) is a learning paradigm in machine learning and its aim is to leverage useful information contained in multiple related tasks to help improve the generalization performance of all the tasks.
no code implementations • 23 May 2017 • Leye Wang, Xu Geng, Jintao Ke, Chen Peng, Xiaojuan Ma, Daqing Zhang, Qiang Yang
Finally, we use the resulting ensemble of RF and CNN to identify the ridesourcing cars in the candidate pool.
no code implementations • 6 Apr 2017 • Long-Kai Huang, Qiang Yang, Wei-Shi Zheng
Specifically, a new loss function is proposed to measure the similarity loss between a pair of data samples in hamming space.
1 code implementation • 20 Feb 2017 • Chunjie Luo, Jianfeng Zhan, Lei Wang, Qiang Yang
We compare cosine normalization with batch, weight and layer normalization in fully-connected neural networks as well as convolutional networks on the data sets of MNIST, 20NEWS GROUP, CIFAR-10/100 and SVHN.
no code implementations • 10 Oct 2016 • Kaixiang Mo, Shuangyin Li, Yu Zhang, Jiajun Li, Qiang Yang
One way to solve this problem is to consider a collection of multiple users' data as a source domain and an individual user's data as a target domain, and to perform a transfer learning from the source to the target domain.
no code implementations • 28 Aug 2016 • Zhongqi Lu, Qiang Yang
We report the "Recurrent Deterioration" (RD) phenomenon observed in online recommender systems.
no code implementations • 15 Aug 2016 • Zhangjie Cao, Mingsheng Long, Qiang Yang
Hashing has been widely applied to large-scale multimedia retrieval due to the storage and retrieval efficiency.
1 code implementation • 2 Feb 2014 • Shu Kong, Zhuolin Jiang, Qiang Yang
However, measuring pairwise distance of RF's for building the similarity graph is a nontrivial problem.
no code implementations • 22 Jan 2014 • Shu Kong, Zhuolin Jiang, Qiang Yang
We now know that mid-level features can greatly enhance the performance of image learning, but how to automatically learn the image features efficiently and in an unsupervised manner is still an open question.
no code implementations • NeurIPS 2012 • Hankz H. Zhuo, Qiang Yang, Subbarao Kambhampati
Previous MAPR approaches required a library of team activity sequences (team plans) be given as input.