1 code implementation • 28 May 2025 • Anjie Xu, Ruiqing Ding, Leye Wang
Scientific research heavily depends on suitable datasets for method validation, but existing academic platforms with dataset management like PapersWithCode suffer from inefficiencies in their manual workflow.
no code implementations • 18 May 2025 • Jianheng Tang, Huiping Zhuang, Di Fang, Jiaxu Li, Feijiang Han, Yajiang Huang, Kejia Fan, Leye Wang, Zhanxing Zhu, Shanghang Zhang, Houbing Herbert Song, Yunhuai Liu
The development of artificial intelligence demands that models incrementally update knowledge by Continual Learning (CL) to adapt to open-world environments.
no code implementations • 18 May 2025 • Jianheng Tang, Huiping Zhuang, Jingyu He, Run He, JingChao Wang, Kejia Fan, Anfeng Liu, Tian Wang, Leye Wang, Zhanxing Zhu, Shanghang Zhang, Houbing Herbert Song, Yunhuai Liu
Federated Continual Learning (FCL) enables distributed clients to collaboratively train a global model from online task streams in dynamic real-world scenarios.
1 code implementation • 15 May 2025 • Jie Zhu, Jirong Zha, Ding Li, Leye Wang
In this setting, considering that self-supervised model could be trained by completely different self-supervised paradigms, e. g., masked image modeling and contrastive learning, with complex training details, we propose a unified membership inference method called PartCrop.
1 code implementation • 24 Feb 2025 • Linian Wang, Leye Wang
Privacy concerns in machine learning are heightened by regulations such as the GDPR, which enforces the "right to be forgotten" (RTBF), driving the emergence of machine unlearning as a critical research field.
1 code implementation • 20 Jan 2025 • Chung-ju Huang, Yuanpeng He, Xiao Han, Wenpin Jiao, Zhi Jin, Leye Wang
Next, each hospital learns a local knowledge transfer module offline, enabling the transfer of knowledge from the federated representation of overlapping patients to the enriched representation of local non-overlapping patients in a domain-adaptive manner.
no code implementations • 13 Jan 2025 • Tao Xie, David Harel, Dezhi Ran, Zhenwen Li, Maoliang Li, Zhi Yang, Leye Wang, Xiang Chen, Ying Zhang, Wentao Zhang, Meng Li, Chen Zhang, Linyi Li, Assaf Marron
Sustainable AI is a subfield of AI for concerning developing and using AI systems in ways of aiming to reduce environmental impact and achieve sustainability.
1 code implementation • 7 Jan 2025 • Liyue Chen, Jiangyi Fang, Tengfei Liu, Fangyuan Gao, Leye Wang
Developing a multifaceted dataset with rich types of contextual features and STCFP scenarios is crucial for establishing a principled context modeling paradigm.
no code implementations • 30 Oct 2024 • Jie Zhu, Yixiong Chen, Mingyu Ding, Ping Luo, Leye Wang, Jingdong Wang
These datasets collectively provide a rich prior knowledge base to enhance the human-centric image generation capabilities of the diffusion model.
no code implementations • 11 Aug 2024 • Ji Liu, Juncheng Jia, Hong Zhang, Yuhui Yun, Leye Wang, Yang Zhou, Huaiyu Dai, Dejing Dou
First, we propose a simple dynamic server update algorithm, which takes advantage of the shared insensitive data on the server while dynamically adjusting the update steps on the server in order to speed up the convergence and improve the accuracy.
1 code implementation • 5 Jun 2024 • Yucheng Wu, Liyue Chen, Yu Cheng, Shuai Chen, Jinyu Xu, Leye Wang
Learning representations of user behavior sequences is crucial for various online services, such as online fraudulent transaction detection mechanisms.
1 code implementation • 20 May 2024 • Linian Wang, Jianghong Liu, Huibin Zhang, Leye Wang
Accurate day-ahead electricity price forecasting is essential for residential welfare, yet current methods often fall short in forecast accuracy.
1 code implementation • 3 May 2024 • Yue Cui, Chung-ju Huang, Yuzhu Zhang, Leye Wang, Lixin Fan, Xiaofang Zhou, Qiang Yang
Vertical Federated Learning (VFL) has emerged as a critical approach in machine learning to address privacy concerns associated with centralized data storage and processing.
1 code implementation • 3 Apr 2024 • Jie Zhu, Jirong Zha, Ding Li, Leye Wang
In this setting, considering that self-supervised model could be trained by completely different self-supervised paradigms, e. g., masked image modeling and contrastive learning, with complex training details, we propose a unified membership inference method called PartCrop.
1 code implementation • 10 Mar 2024 • Liyue Chen, Jiangyi Fang, Tengfei Liu, Shaosheng Cao, Leye Wang
Spatio-Temporal (ST) prediction is crucial for making informed decisions in urban location-based applications like ride-sharing.
1 code implementation • 31 Jan 2024 • Yucheng Wu, Leye Wang, Xiao Han, Han-Jia Ye
However, such stochastic augmentations may severely damage the intrinsic properties of a graph and deteriorate the following representation learning process.
2 code implementations • 2 Jan 2024 • Jie Zhu, Leye Wang, Xiao Han, Anmin Liu, Tao Xie
To mitigate this issue, AI software compression plays a crucial role, which aims to compress model size while keeping high performance.
1 code implementation • 23 Aug 2023 • Di Chai, Leye Wang, Liu Yang, Junxue Zhang, Kai Chen, Qiang Yang
Evaluation is a systematic approach to assessing how well a system achieves its intended purpose.
no code implementations • 17 Aug 2023 • Liyue Chen, Linian Wang, Jinyu Xu, Shuai Chen, Weiqiang Wang, Wenbiao Zhao, Qiyu Li, Leye Wang
For example, consider cross-domain fraud detection, where there are two types of transactions: credit and non-credit.
1 code implementation • 7 Jun 2023 • Jiangyi Fang, Liyue Chen, Di Chai, Yayao Hong, Xiuhuai Xie, Longbiao Chen, Leye Wang
To address these issues, we design and implement a spatiotemporal crowd flow prediction toolbox called UCTB (Urban Computing Tool Box), which integrates multiple spatiotemporal domain knowledge and state-of-the-art models simultaneously.
no code implementations • 5 Jun 2023 • Liyue Chen, Jiangyi Fang, Zhe Yu, Yongxin Tong, Shaosheng Cao, Leye Wang
In this paper, we propose RegionGen, a data-driven region generation framework that can specify regions with key characteristics (e. g., good spatial semantic meaning and predictability) by modeling region generation as a multi-objective optimization problem.
no code implementations • 4 Apr 2023 • Liu Yang, Di Chai, Junxue Zhang, Yilun Jin, Leye Wang, Hao liu, Han Tian, Qian Xu, Kai Chen
From the hardware layer to the vertical federated system layer, researchers contribute to various aspects of VFL.
no code implementations • 11 Feb 2023 • Ruiqing Ding, Fangjie Rong, Xiao Han, Leye Wang
In this paper, for a common disease in ICU patients, sepsis, we propose a novel cross-center collaborative learning framework guided by medical knowledge, SofaNet, to achieve early recognition of this disease.
no code implementations • 11 Feb 2023 • Chung-ju Huang, Leye Wang, Xiao Han
In order to improve the information-sharing capability and innovation of various healthcare-related institutions, and then to establish a next-generation open medical collaboration network, we propose a unified framework for vertical federated knowledge transfer mechanism (VFedTrans) based on a novel cross-hospital representation distillation component.
1 code implementation • 27 Jan 2023 • Jie Zhu, Jiyang Qi, Mingyu Ding, Xiaokang Chen, Ping Luo, Xinggang Wang, Wenyu Liu, Leye Wang, Jingdong Wang
The study is mainly motivated by that random views, used in contrastive learning, and random masked (visible) patches, used in masked image modeling, are often about object parts.
no code implementations • 10 Dec 2022 • Ruiqing Ding, Xiao Han, Leye Wang
We propose KnowledgeDA, a unified domain language model development service to enhance the task-specific training procedure with domain knowledge graphs.
2 code implementations • 11 Aug 2022 • Jie Zhu, Leye Wang, Xiao Han
By simulating the attack mechanism as the safety test, SafeCompress can automatically compress a big model to a small one following the dynamic sparse training paradigm.
no code implementations • 28 Jun 2022 • Shuowei Cai, Di Chai, Liu Yang, Junxue Zhang, Yilun Jin, Leye Wang, Kun Guo, Kai Chen
In this paper, we focus on SplitNN, a well-known neural network framework in VFL, and identify a trade-off between data security and model performance in SplitNN.
no code implementations • 28 May 2022 • Xiao Han, Leye Wang, Junjie Wu, Yuncong Yang
Basically, we propose to perturb the original network by adding or removing links, and expect the embedding generated on the perturbed network can leak little information about private links but hold high utility for various downstream tasks.
no code implementations • 11 Apr 2022 • Leye Wang
With the worldwide emergence of data protection regulations, how to conduct law-regulated big data analytics becomes a challenging and fundamental problem.
no code implementations • 15 Dec 2021 • Xiao Han, Leye Wang, Junjie Wu, Xiao Fang
In response, we propose FedValue, a privacy-preserving, task-specific but model-free data valuation method for VFL, which consists of a data valuation metric and a federated computation method.
1 code implementation • 14 Dec 2021 • Jie Zhu, Huabin Huang, Banghuai Li, Leye Wang
In this paper, we notice that the class weights of categories that tend to share many adjacent boundary pixels lack discrimination, thereby limiting the performance.
no code implementations • 3 Dec 2021 • Jie Zhu, Huabin Huang, Banghuai Li, Yong liu, Leye Wang
Inspired by the generated sharp edges of superpixel blocks, we employ superpixel to guide the information passing within feature map.
1 code implementation • 22 Oct 2021 • Bingyan Liu, Yifeng Cai, Ziqi Zhang, Yuanchun Li, Leye Wang, Ding Li, Yao Guo, Xiangqun Chen
Previous studies focus on the "symptoms" directly, as they try to improve the accuracy or detect possible attacks by adding extra steps to conventional FL models.
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.
1 code implementation • 30 Jun 2021 • Liyue Chen, Xiaoxiang Wang, Leye Wang
Contextual features are important data sources for building citywide crowd mobility prediction models.
1 code implementation • 18 Jun 2021 • Ruiqing Ding, Yu Zhou, Jie Xu, Yan Xie, Qiqiang Liang, He Ren, YiXuan Wang, Yanlin Chen, Leye Wang, Man Huang
To address this issue, we propose a novel semi-supervised transfer learning framework based on optimal transport theory and self-paced ensemble for Sepsis early detection, called SPSSOT, which can efficiently transfer knowledge from the source hospital (with rich labeled data) to the target hospital (with scarce labeled data).
no code implementations • 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 • 6 Nov 2020 • Leye Wang, Han Yu, Xiao Han
In particular, we first propose a federated crowdsensing framework, which analyzes the privacy concerns of each crowdsensing stage (i. e., task creation, task assignment, task execution, and data aggregation) and discuss how federated learning techniques may take effect.
1 code implementation • 20 Sep 2020 • Leye Wang, Di Chai, Xuanzhe Liu, Liyue Chen, Kai Chen
The Spatio-Temporal Traffic Prediction (STTP) problem is a classical problem with plenty of prior research efforts that benefit from traditional statistical learning and recent deep learning approaches.
no code implementations • 19 Oct 2019 • Xiao Han, Ruiqing Ding, Leye Wang, Hailiang Huang
Credit investigation is critical for financial services.
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 • 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.
no code implementations • 1 Nov 2018 • Xu Chu, Yang Lin, Jingyue Gao, Jiangtao Wang, Yasha Wang, Leye Wang
However, the shallow models leveraging bilinear forms suffer from limitations on capturing complicated nonlinear interactions between drug pairs.
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 • 19 Apr 2018 • Leye Wang, wenbin liu, Daqing Zhang, Yasha Wang, En Wang, Yongjian Yang
Since the sensed data from different cells (sub-areas) of the target sensing area will probably lead to diverse levels of inference data quality, cell selection (i. e., choose which cells of the target area to collect sensed data from participants) is a critical issue that will impact the total amount of data that requires to be collected (i. e., data collection costs) for ensuring a certain level of quality.
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 • 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.