1 code implementation • 17 Apr 2024 • Wei Duan, Jie Lu, Junyu Xuan
To overcome these limitations, we present a novel approach to infer the Group-Aware Coordination Graph (GACG), which is designed to capture both the cooperation between agent pairs based on current observations and group-level dependencies from behaviour patterns observed across trajectories.
no code implementations • 7 Apr 2024 • Zhen Fang, Yixuan Li, Feng Liu, Bo Han, Jie Lu
Based on this observation, we next give several necessary and sufficient conditions to characterize the learnability of OOD detection in some practical scenarios.
no code implementations • 29 Mar 2024 • Luchang Li, Sheng Qian, Jie Lu, Lunxi Yuan, Rui Wang, Qin Xie
The Large Language Model (LLM) is widely employed for tasks such as intelligent assistants, text summarization, translation, and multi-modality on mobile phones.
1 code implementation • 28 Mar 2024 • Wei Duan, Jie Lu, Junyu Xuan
The LTS-CG leverages agents' historical observations to calculate an agent-pair probability matrix, where a sparse graph is sampled from and used for knowledge exchange between agents, thereby simultaneously capturing agent dependencies and relation uncertainty.
no code implementations • 18 Mar 2024 • Wei Duan, Jie Lu, Yu Guang Wang, Junyu Xuan
Experiments on various real-world graph datasets demonstrate the effectiveness of our approach in improving the diversity of negative samples and overall learning performance.
no code implementations • 17 Dec 2023 • En Yu, Jie Lu, Bin Zhang, Guangquan Zhang
Specifically, OBAL operates in a dual-phase mechanism, in the first of which we design an Adaptive COvariate Shift Adaptation (AdaCOSA) algorithm to construct an initialized ensemble model using archived data from various source streams, thus mitigating the covariate shift while learning the dynamic correlations via an adaptive re-weighting strategy.
no code implementations • ICCV 2023 • Xinheng Wu, Jie Lu, Zhen Fang, Guangquan Zhang
To address CAOOD, we develop meta OOD learning (MOL) by designing a learning-to-adapt diagram such that a good initialized OOD detection model is learned during the training process.
1 code implementation • 5 Dec 2022 • Wei Duan, Junyu Xuan, Maoying Qiao, Jie Lu
However, there are more non-neighbour nodes in the whole graph, which provide diverse and useful information for the representation update.
no code implementations • 26 Oct 2022 • Zhen Fang, Yixuan Li, Jie Lu, Jiahua Dong, Bo Han, Feng Liu
Based on this observation, we next give several necessary and sufficient conditions to characterize the learnability of OOD detection in some practical scenarios.
1 code implementation • 16 Oct 2022 • Tianyu Liu, Jie Lu, Zheng Yan, Guangquan Zhang
The framework offers both a guarantee of generalized performance and good accuracy.
1 code implementation • 3 Oct 2022 • Wei Duan, Junyu Xuan, Maoying Qiao, Jie Lu
An interesting way to understand GCNs is to think of them as a message passing mechanism where each node updates its representation by accepting information from its neighbours (also known as positive samples).
1 code implementation • 9 Jun 2022 • Guangzhi Ma, Jie Lu, Feng Liu, Zhen Fang, Guangquan Zhang
Hence, in this paper, we propose a novel framework to address a new realistic problem called multi-class classification with imprecise observations (MCIMO), where we need to train a classifier with fuzzy-feature observations.
no code implementations • 27 Sep 2021 • Junyu Xuan, Jie Lu, Guangquan Zhang
Transfer learning where the behavior of extracting transferable knowledge from the source domain(s) and reusing this knowledge to target domain has become a research area of great interest in the field of artificial intelligence.
no code implementations • 20 Sep 2021 • Adi Lin, Jie Lu, Junyu Xuan, Fujin Zhu, Guangquan Zhang
Causal effect estimation for dynamic treatment regimes (DTRs) contributes to sequential decision making.
1 code implementation • 30 Jun 2021 • Zhen Fang, Jie Lu, Anjin Liu, Feng Liu, Guangquan Zhang
In this paper, we target a more challenging and realistic setting: open-set learning (OSL), where there exist test samples from the classes that are unseen during training.
1 code implementation • NeurIPS 2021 • Feng Liu, Wenkai Xu, Jie Lu, Danica J. Sutherland
In realistic scenarios with very limited numbers of data samples, however, it can be challenging to identify a kernel powerful enough to distinguish complex distributions.
no code implementations • 4 May 2021 • Hang Yu, Tianyu Liu, Jie Lu, Guangquan Zhang
Many methods have been proposed to detect concept drift, i. e., the change in the distribution of streaming data, due to concept drift causes a decrease in the prediction accuracy of algorithms.
1 code implementation • 4 Apr 2021 • He Wang, Yifei Shen, Ziyuan Wang, Dongsheng Li, Jun Zhang, Khaled B. Letaief, Jie Lu
In this paper, we investigate the decentralized statistical inference problem, where a network of agents cooperatively recover a (structured) vector from private noisy samples without centralized coordination.
no code implementations • 25 Feb 2021 • Xuyang Wu, He Wang, Jie Lu
In this paper, we develop a novel distributed algorithm for addressing convex optimization with both nonlinear inequality and linear equality constraints, where the objective function can be a general nonsmooth convex function and all the constraints can be fully coupled.
Distributed Optimization Optimization and Control
1 code implementation • 7 Feb 2021 • Tianyu Liu, Jie Lu, Zheng Yan, Guangquan Zhang
By leveraging experience from previous tasks, meta-learning algorithms can achieve effective fast adaptation ability when encountering new tasks.
no code implementations • 30 Dec 2020 • Li Zhong, Zhen Fang, Feng Liu, Jie Lu, Bo Yuan, Guangquan Zhang
Experiments show that the proxy can effectively curb the increase of the combined risk when minimizing the source risk and distribution discrepancy.
no code implementations • 21 Sep 2020 • Weikai Yang, Xiting Wang, Jie Lu, Wenwen Dou, Shixia Liu
The novelty of our approach includes 1) automatically constructing constraints for hierarchical clustering using knowledge (knowledge-driven) and intrinsic data distribution (data-driven), and 2) enabling the interactive steering of clustering through a visual interface (user-driven).
1 code implementation • 9 Aug 2020 • Anjin Liu, Jie Lu, Guangquan Zhang
Our solution comprises a novel masked distance learning (MDL) algorithm to reduce the cumulative errors caused by iteratively estimating each missing value in an observation and a fuzzy-weighted frequency (FWF) method for identifying discrepancies in the data distribution.
1 code implementation • 4 Aug 2020 • Yiyang Zhang, Feng Liu, Zhen Fang, Bo Yuan, Guangquan Zhang, Jie Lu
We consider two cases of this setting, one is that the source domain only contains complementary-label data (completely complementary unsupervised domain adaptation, CC-UDA), and the other is that the source domain has plenty of complementary-label data and a small amount of true-label data (partly complementary unsupervised domain adaptation, PC-UDA).
1 code implementation • 29 Jul 2020 • Yiyang Zhang, Feng Liu, Zhen Fang, Bo Yuan, Guangquan Zhang, Jie Lu
To mitigate this problem, we consider a novel problem setting where the classifier for the target domain has to be trained with complementary-label data from the source domain and unlabeled data from the target domain named budget-friendly UDA (BFUDA).
no code implementations • 23 Jun 2020 • Li Zhong, Zhen Fang, Feng Liu, Bo Yuan, Guangquan Zhang, Jie Lu
To achieve this aim, a previous study has proven an upper bound of the target-domain risk, and the open set difference, as an important term in the upper bound, is used to measure the risk on unknown target data.
no code implementations • 13 Apr 2020 • Jie Lu, Anjin Liu, Fan Dong, Feng Gu, Joao Gama, Guangquan Zhang
To help researchers identify which research topics are significant and how to apply related techniques in data analysis tasks, it is necessary that a high quality, instructive review of current research developments and trends in the concept drift field is conducted.
no code implementations • 13 Apr 2020 • Anjin Liu, Jie Lu, Guangquan Zhang
Concept drift refers to changes in the distribution of underlying data and is an inherent property of evolving data streams.
1 code implementation • ICML 2020 • Feng Liu, Wenkai Xu, Jie Lu, Guangquan Zhang, Arthur Gretton, Danica J. Sutherland
We propose a class of kernel-based two-sample tests, which aim to determine whether two sets of samples are drawn from the same distribution.
Ranked #1 on Two-sample testing on HIGGS Data Set
2 code implementations • 8 Oct 2019 • Mahardhika Pratama, Marcus de Carvalho, Renchunzi Xie, Edwin Lughofer, Jie Lu
It automatically evolves its network structure from scratch with/without the presence of ground truth to overcome independent concept drifts in the source and target domain.
no code implementations • 25 Sep 2019 • Feng Liu, Jie Lu, Bo Han, Gang Niu, Guangquan Zhang, Masashi Sugiyama
Hence, we consider a new, more realistic and more challenging problem setting, where classifiers have to be trained with noisy labeled data from SD and unlabeled data from TD---we name it wildly UDA (WUDA).
Unsupervised Domain Adaptation Wildly Unsupervised Domain Adaptation
no code implementations • 1 Aug 2019 • Shan Xue, Jie Lu, Guangquan Zhang
By generating the random walks from a structural rich domain and transferring the knowledge on the random walks across domains, it enables a network representation for the structural scarce domain as well.
1 code implementation • 19 Jul 2019 • Zhen Fang, Jie Lu, Feng Liu, Junyu Xuan, Guangquan Zhang
The aim of unsupervised domain adaptation is to leverage the knowledge in a labeled (source) domain to improve a model's learning performance with an unlabeled (target) domain -- the basic strategy being to mitigate the effects of discrepancies between the two distributions.
Ranked #20 on Domain Adaptation on Office-Home
1 code implementation • 19 May 2019 • Feng Liu, Jie Lu, Bo Han, Gang Niu, Guangquan Zhang, Masashi Sugiyama
Hence, we consider a new, more realistic and more challenging problem setting, where classifiers have to be trained with noisy labeled data from SD and unlabeled data from TD -- we name it wildly UDA (WUDA).
Unsupervised Domain Adaptation Wildly Unsupervised Domain Adaptation
no code implementations • 19 Mar 2019 • Mohammad Siami, Mohsen Naderpour, Jie Lu
The application of mobile telematics has been explored in many areas, such as insurance and road safety.
3 code implementations • 22 Dec 2018 • Bin Wang, Jie Lu, Zheng Yan, Huaishao Luo, Tianrui Li, Yu Zheng, Guangquan Zhang
We cast the weather forecasting problem as an end-to-end deep learning problem and solve it by proposing a novel negative log-likelihood error (NLE) loss function.
no code implementations • 15 Oct 2018 • Anpei Chen, Minye Wu, Yingliang Zhang, Nianyi Li, Jie Lu, Shenghua Gao, Jingyi Yu
A surface light field represents the radiance of rays originating from any points on the surface in any directions.
1 code implementation • 17 Oct 2017 • Li Yi, Lin Shao, Manolis Savva, Haibin Huang, Yang Zhou, Qirui Wang, Benjamin Graham, Martin Engelcke, Roman Klokov, Victor Lempitsky, Yuan Gan, Pengyu Wang, Kun Liu, Fenggen Yu, Panpan Shui, Bingyang Hu, Yan Zhang, Yangyan Li, Rui Bu, Mingchao Sun, Wei Wu, Minki Jeong, Jaehoon Choi, Changick Kim, Angom Geetchandra, Narasimha Murthy, Bhargava Ramu, Bharadwaj Manda, M. Ramanathan, Gautam Kumar, P Preetham, Siddharth Srivastava, Swati Bhugra, Brejesh lall, Christian Haene, Shubham Tulsiani, Jitendra Malik, Jared Lafer, Ramsey Jones, Siyuan Li, Jie Lu, Shi Jin, Jingyi Yu, Qi-Xing Huang, Evangelos Kalogerakis, Silvio Savarese, Pat Hanrahan, Thomas Funkhouser, Hao Su, Leonidas Guibas
We introduce a large-scale 3D shape understanding benchmark using data and annotation from ShapeNet 3D object database.
no code implementations • 18 Jul 2017 • Junyu Xuan, Jie Lu, Guangquan Zhang, Richard Yi Da Xu
The cooperative hierarchical structure is a common and significant data structure observed in, or adopted by, many research areas, such as: text mining (author-paper-word) and multi-label classification (label-instance-feature).
no code implementations • 23 Feb 2017 • Jianfei Chen, Jun Zhu, Jie Lu, Shixia Liu
Finally, we propose an efficient distributed implementation of PCGS through vectorization, pre-processing, and a careful design of the concurrent data structures and communication strategy.
no code implementations • 10 Jan 2017 • Feng Liu, Guanquan Zhang, Jie Lu
To contribute to the research in this emerging field, this paper presents: (1) an unsupervised knowledge transfer theorem that guarantees the correctness of transferring knowledge; and (2) a principal angle-based metric to measure the distance between two pairs of domains: one pair comprises the original source and target domains and the other pair comprises two homogeneous representations of two domains.
no code implementations • 12 Jul 2015 • Junyu Xuan, Jie Lu, Guangquan Zhang, Richard Yi Da Xu, Xiangfeng Luo
Under this same framework, two classes of correlation function are proposed (1) using Bivariate beta distribution and (2) using Copula function.
no code implementations • 30 Mar 2015 • Junyu Xuan, Jie Lu, Guangquan Zhang, Richard Yi Da Xu, Xiangfeng Luo
Traditional Relational Topic Models provide a way to discover the hidden topics from a document network.
no code implementations • 30 Mar 2015 • Junyu Xuan, Jie Lu, Guangquan Zhang, Richard Yi Da Xu, Xiangfeng Luo
One branch of these works is the so-called Author Topic Model (ATM), which incorporates the authors's interests as side information into the classical topic model.