no code implementations • NeurIPS 2018 • Jiecao Chen, Erfan Sadeqi Azer, Qin Zhang
We study the classic $k$-means/median clustering, which are fundamental problems in unsupervised learning, in the setting where data are partitioned across multiple sites, and where we are allowed to discard a small portion of the data by labeling them as outliers.
no code implementations • NeurIPS 2018 • Jiecao Chen, Qin Zhang, Yuan Zhou
We study the collaborative PAC learning problem recently proposed in Blum et al.~\cite{BHPQ17}, in which we have $k$ players and they want to learn a target function collaboratively, such that the learned function approximates the target function well on all players' distributions simultaneously.
no code implementations • ICML 2017 • Jiecao Chen, Xi Chen, Qin Zhang, Yuan Zhou
We study the problem of selecting $K$ arms with the highest expected rewards in a stochastic $n$-armed bandit game.
no code implementations • 19 May 2017 • Qin Zhang, Hui Wang, Junyu Dong, Guoqiang Zhong, Xin Sun
We formulate the SST prediction problem as a time series regression problem.
no code implementations • NeurIPS 2016 • Jiecao Chen, He Sun, David P. Woodruff, Qin Zhang
We would like the quality of the clustering in the distributed setting to match that in the centralized setting for which all the data resides on a single site.
no code implementations • 5 Apr 2019 • Chao Tao, Qin Zhang, Yuan Zhou
Best arm identification (or, pure exploration) in multi-armed bandits is a fundamental problem in machine learning.
no code implementations • 29 Oct 2018 • Jiecao Chen, Qin Zhang
In this paper we study how to perform distinct sampling in the streaming model where data contain near-duplicates.
Data Structures and Algorithms
no code implementations • 20 Apr 2020 • Nikolai Karpov, Qin Zhang, Yuan Zhou
We give optimal time-round tradeoffs, as well as demonstrate complexity separations between top-$1$ arm identification and top-$m$ arm identifications for general $m$ and between fixed-time and fixed-confidence variants.
no code implementations • ICML 2020 • Kefan Dong, Yingkai Li, Qin Zhang, Yuan Zhou
We also present the ESUCB algorithm with item switching cost $O(N \log^2 T)$.
no code implementations • 6 Nov 2020 • Hao Nie, Qin Zhang
In the situation of clinical diagnoses, when a lot of intermediate causes are unknown while the downstream results are known in a DUCG graph, the combination explosion may appear during the inference computation.
no code implementations • NeurIPS 2020 • Nikolai Karpov, Qin Zhang
We study the problem of coarse ranking in the multi-armed bandits (MAB) setting, where we have a set of arms each of which is associated with an unknown distribution.
no code implementations • 2 Dec 2020 • Nikolai Karpov, Qin Zhang
Motivated by real-world applications such as fast fashion retailing and online advertising, the Multinomial Logit Bandit (MNL-bandit) is a popular model in online learning and operations research, and has attracted much attention in the past decade.
no code implementations • 16 Aug 2021 • Qinghong Lin, Xiaojun Chen, Qin Zhang, Shangxuan Tian, Yudong Chen
Secondly, we measure the priorities of data pairs with PIC and assign adaptive weights to them, which is relies on the assumption that more dissimilar data pairs contain more discriminative information for hash learning.
no code implementations • 15 Aug 2021 • Nikolai Karpov, Qin Zhang
We study Thompson Sampling algorithms for stochastic multi-armed bandits in the batched setting, in which we want to minimize the regret over a sequence of arm pulls using a small number of policy changes (or, batches).
no code implementations • 17 Aug 2021 • Yi Li, Yan Song, Qin Zhang
We study the problem of learning to cluster data points using an oracle which can answer same-cluster queries.
no code implementations • 5 Sep 2021 • Guochen Yu, Yutian Wang, Hui Wang, Qin Zhang, Chengshi Zheng
After that, the second stage is applied to further suppress the residual noise components and estimate the clean phase by a complex spectral mapping network, which is a pure complex-valued network composed of complex 2D convolution/deconvolution and complex temporal-frequency attention blocks.
no code implementations • 17 Mar 2022 • Qinghong Lin, Xiaojun Chen, Qin Zhang, Shaotian Cai, Wenzhe Zhao, Hongfa Wang
Firstly, DSCH constructs a semantic component structure by uncovering the fine-grained semantics components of images with a Gaussian Mixture Modal~(GMM), where an image is represented as a mixture of multiple components, and the semantics co-occurrence are exploited.
no code implementations • 7 Apr 2022 • Yutian Wang, Yuankun Xie, Kun Zhao, Hui Wang, Qin Zhang
In this paper, we propose a novel prosody disentangle method for prosodic Text-to-Speech (TTS) model, which introduces the vector quantization (VQ) method to the auxiliary prosody encoder to obtain the decomposed prosody representations in an unsupervised manner.
no code implementations • 16 Jul 2022 • Nikolai Karpov, Qin Zhang
In this paper, we study the tradeoffs between the time and the number of communication rounds of the best arm identification problem in the heterogeneous collaborative learning model, where multiple agents interact with possibly different environments and they want to learn in parallel an objective function in the aggregated environment.
no code implementations • 18 Aug 2022 • Nikolai Karpov, Qin Zhang
We investigate top-$m$ arm identification, a basic problem in bandit theory, in a multi-agent learning model in which agents collaborate to learn an objective function.
no code implementations • 21 Aug 2022 • Shaotian Cai, Liping Qiu, Xiaojun Chen, Qin Zhang, Longteng Chen
In this paper, we propose to investigate the task of image clustering with the help of a visual-language pre-training model.
no code implementations • 15 Nov 2022 • Qin Zhang, Shangsi Chen, Dongkuan Xu, Qingqing Cao, Xiaojun Chen, Trevor Cohn, Meng Fang
Thus, a trade-off between accuracy, memory consumption and processing speed is pursued.
no code implementations • 12 Dec 2022 • Linrui Zhang, Qin Zhang, Li Shen, Bo Yuan, Xueqian Wang, DaCheng Tao
Despite a large number of reinforcement learning (RL) methods focusing on safety-critical tasks, there is still a lack of high-quality evaluation of those algorithms that adheres to safety constraints at each decision step under complex and unknown dynamics.
no code implementations • 21 Dec 2022 • Ruilin Ma, Shiyao Chen, Qin Zhang
Monocular depth estimation can play an important role in addressing the issue of deriving scene geometry from 2D images.
no code implementations • 26 Jan 2023 • Nikolai Karpov, Qin Zhang
In this paper, we study the collaborative learning model, which concerns the tradeoff between parallelism and communication overhead in multi-agent multi-armed bandits.
no code implementations • 28 Jan 2023 • Qin Zhang, Linrui Zhang, Haoran Xu, Li Shen, Bowen Wang, Yongzhe Chang, Xueqian Wang, Bo Yuan, DaCheng Tao
Offline safe RL is of great practical relevance for deploying agents in real-world applications.
no code implementations • 23 Feb 2023 • Xin Zheng, Miao Zhang, Chunyang Chen, Qin Zhang, Chuan Zhou, Shirui Pan
Therefore, in this paper, we propose a novel automated graph neural network on heterophilic graphs, namely Auto-HeG, to automatically build heterophilic GNN models with expressive learning abilities.
no code implementations • 19 May 2023 • Qin Zhang, Dongsheng An, Tianjun Xiao, Tong He, Qingming Tang, Ying Nian Wu, Joseph Tighe, Yifan Xing, Stefano Soatto
In deep metric learning for visual recognition, the calibration of distance thresholds is crucial for achieving desired model performance in the true positive rates (TPR) or true negative rates (TNR).
no code implementations • 8 Jul 2023 • Qin Zhang, Linghan Xu, Qingming Tang, Jun Fang, Ying Nian Wu, Joe Tighe, Yifan Xing
Existing losses used in deep metric learning (DML) for image retrieval often lead to highly non-uniform intra-class and inter-class representation structures across test classes and data distributions.
no code implementations • 8 Aug 2023 • Zixuan He, Salik Ram Khanal, Xin Zhang, Manoj Karkee, Qin Zhang
This study proposed a YOLOv5-based custom object detection model to detect strawberries in an outdoor environment.
no code implementations • 10 Aug 2023 • Qin Zhang, Zelin Shi, Xiaolin Zhang, Xiaojun Chen, Philippe Fournier-Viger, Shirui Pan
Node classification is the task of predicting the labels of unlabeled nodes in a graph.
no code implementations • 2 Nov 2023 • Yong Bian, Xiqian Wang, Qin Zhang
Portfolio underdiversification is one of the most costly losses accumulated over a household's life cycle.
no code implementations • 22 Jan 2024 • Liping Qiu, Qin Zhang, Xiaojun Chen, Shaotian Cai
Recently, the cross-modal pretraining model has been employed to produce meaningful pseudo-labels to supervise the training of an image clustering model.
no code implementations • 3 Feb 2024 • Junyou Li, Qin Zhang, Yangbin Yu, Qiang Fu, Deheng Ye
We find that, simply via a sampling-and-voting method, the performance of large language models (LLMs) scales with the number of agents instantiated.
no code implementations • 26 Feb 2024 • Man Wu, Xin Zheng, Qin Zhang, Xiao Shen, Xiong Luo, Xingquan Zhu, Shirui Pan
Graph learning plays a pivotal role and has gained significant attention in various application scenarios, from social network analysis to recommendation systems, for its effectiveness in modeling complex data relations represented by graph structural data.
no code implementations • 27 Feb 2024 • Qin Zhang, Hao Ge, Xiaojun Chen, Meng Fang
Unsupervised question answering is a promising yet challenging task, which alleviates the burden of building large-scale annotated data in a new domain.
no code implementations • 28 Feb 2024 • Qin Zhang, Xiaowei Li, Jiexin Lu, Liping Qiu, Shirui Pan, Xiaojun Chen, Junyang Chen
In specific, ROG$_{PL}$ consists of two modules, i. e., denoising via label propagation and open-set prototype learning via regions.
no code implementations • 23 Mar 2024 • Xin Zhang, Tianjie Ju, Huijia Liang, Ying Fu, Qin Zhang
The interest in updating Large Language Models (LLMs) without retraining from scratch is substantial, yet it comes with some challenges. This is especially true for situations demanding complex reasoning with limited samples, a scenario we refer to as the Paucity-Constrained Complex Reasoning Adaptation for LLMs (PCRA-LLM). Traditional methods like Low-Rank Adaptation (LoRA) and Retrieval-Augmented Generation (RAG) are inadequate for this critical issue, particularly evident in our exploration of a specific medical context that epitomize the PCRA-LLM's distinct needs. To address the issue, we propose a Sequential Fusion method to incorporate knowledge from complex context into LLMs.
1 code implementation • 1 Feb 2017 • Haoyu Zhang, Qin Zhang
Edit similarity join is a fundamental problem in data cleaning/integration, bioinformatics, collaborative filtering and natural language processing, and has been identified as a primitive operator for database systems.
Databases
1 code implementation • 3 Feb 2024 • Yangbin Yu, Qin Zhang, Junyou Li, Qiang Fu, Deheng Ye
The emergence of large language models (LLMs) has significantly advanced the simulation of believable interactive agents.
1 code implementation • 17 Jun 2022 • Linrui Zhang, Qin Zhang, Li Shen, Bo Yuan, Xueqian Wang
Safe reinforcement learning (RL) has achieved significant success on risk-sensitive tasks and shown promise in autonomous driving (AD) as well.