no code implementations • ICML 2020 • Hengrui Cai, Wenbin Lu, Rui Song
Estimation of optimal decision rules (ODR) has been extensively investigated recently, however, at present, no testing procedure is proposed to verify whether these ODRs are significantly better than the naive decision rule that always assigning individuals to a fixed treatment option.
no code implementations • CCL 2022 • Rui Song, Zhimin Wang
“本文以2019-2021年《人民日报》文章中单项形容词定语77845个词例为研究对象, 从实用性的角度考察了粘合式与组合式定语词例的分布特征、音节组配模式及“的”字的隐现倾向性。通过研究我们发现, 粘合式定语的词例数量明显少于组合式定语词例数量, 但使用频数却高出组合式定语的4-5倍。两种定语结构中, 形容词和名词重复使用的比例很高, 但其共现组合的比例偏少, 同时, 真实文本中“的”字的隐现具有“两极分化”的特征, 绝大部分词例在使用过程中带“的”或不带“的”都具有很强的倾向性,“的”字出现具有区分词义和突显信息的作用,“的”字隐藏能促使语义更加凝练, 进一步固化句式结构, 使得某些句式形成了特指或隐喻的表达方式。本文为形容词定语结构的词汇语义研究提供依据和参考。”
3 code implementations • 2 Mar 2024 • Walter Zimmer, Gerhard Arya Wardana, Suren Sritharan, Xingcheng Zhou, Rui Song, Alois C. Knoll
We propose CoopDet3D, a cooperative multi-modal fusion model, and TUMTraf-V2X, a perception dataset, for the cooperative 3D object detection and tracking task.
no code implementations • 12 Feb 2024 • Rui Song, Chenwei Liang, Hu Cao, Zhiran Yan, Walter Zimmer, Markus Gross, Andreas Festag, Alois Knoll
Additionally, due to the lack of a collaborative perception dataset designed for semantic occupancy prediction, we augment a current collaborative perception dataset to include 3D collaborative semantic occupancy labels for a more robust evaluation.
1 code implementation • 30 Dec 2023 • Hengrui Cai, ShengJie Liu, Rui Song
This paper explores the causal reasoning of large language models (LLMs) to enhance their interpretability and reliability in advancing artificial intelligence.
no code implementations • 28 Dec 2023 • Haitao Jiang, Lin Ge, Yuhe Gao, Jianian Wang, Rui Song
Large Language Models (LLMs) have shown their success in language understanding and reasoning on general topics.
1 code implementation • 25 Dec 2023 • Rui Song, Fausto Giunchiglia, Yingji Li, Mingjie Tian, Hao Xu
However, these methods rely on unlabeled samples provided by the target domains, which renders the model ineffective when the target domain is agnostic.
no code implementations • 25 Dec 2023 • Haoyu Wei, Runzhe Wan, Lei Shi, Rui Song
Many real applications of bandits have sparse non-zero rewards, leading to slow learning rates.
no code implementations • 20 Dec 2023 • Yu Liu, Runzhe Wan, James McQueen, Doug Hains, Jinxiang Gu, Rui Song
The selection of the assumed effect size (AES) critically determines the duration of an experiment, and hence its accuracy and efficiency.
no code implementations • 20 Aug 2023 • Yingji Li, Mengnan Du, Rui Song, Xin Wang, Ying Wang
Large Language Models (LLMs) have shown powerful performance and development prospects and are widely deployed in the real world.
1 code implementation • ICCV 2023 • Yang Hai, Rui Song, Jiaojiao Li, David Ferstl, Yinlin Hu
Most self-supervised 6D object pose estimation methods can only work with additional depth information or rely on the accurate annotation of 2D segmentation masks, limiting their application range.
no code implementations • 1 Jul 2023 • Rui Song, Fausto Giunchiglia, Yingji Li, Hao Xu
Despite large-scale pre-trained language models have achieved striking results for text classificaion, recent work has raised concerns about the challenge of shortcut learning.
1 code implementation • CVPR 2023 • Yang Hai, Rui Song, Jiaojiao Li, Yinlin Hu
In this work, we propose a shape-constraint recurrent matching framework for 6D object pose estimation.
no code implementations • 19 May 2023 • Rui Song, Lingjuan Lyu, Wei Jiang, Andreas Festag, Alois Knoll
Machine learning (ML) has revolutionized transportation systems, enabling autonomous driving and smart traffic services.
1 code implementation • 4 Apr 2023 • Rui Song, Runsheng Xu, Andreas Festag, Jiaqi Ma, Alois Knoll
Our findings suggest that FedBEVT outperforms the baseline approaches in all four use cases, demonstrating the potential of our approach for improving BEV perception in autonomous driving.
no code implementations • 2 Apr 2023 • Runzhe Wan, Yu Liu, James McQueen, Doug Hains, Rui Song
With the growing needs of online A/B testing to support the innovation in industry, the opportunity cost of running an experiment becomes non-negligible.
2 code implementations • CVPR 2023 • Yang Hai, Rui Song, Jiaojiao Li, Mathieu Salzmann, Yinlin Hu
To address this, we propose a rigidity-aware detection method exploiting the fact that, in 6D pose estimation, the target objects are rigid.
1 code implementation • CVPR 2023 • Runsheng Xu, Xin Xia, Jinlong Li, Hanzhao Li, Shuo Zhang, Zhengzhong Tu, Zonglin Meng, Hao Xiang, Xiaoyu Dong, Rui Song, Hongkai Yu, Bolei Zhou, Jiaqi Ma
To facilitate the development of cooperative perception, we present V2V4Real, the first large-scale real-world multi-modal dataset for V2V perception.
no code implementations • 3 Feb 2023 • Runzhe Wan, Haoyu Wei, Branislav Kveton, Rui Song
Despite the great interest in the bandit problem, designing efficient algorithms for complex models remains challenging, as there is typically no analytical way to quantify uncertainty.
1 code implementation • 31 Jan 2023 • Lin Ge, Jitao Wang, Chengchun Shi, Zhenke Wu, Rui Song
However, there are a number of applications (e. g., mobile health) where the treatments are sequentially assigned over time and the dynamic mediation effects are of primary interest.
1 code implementation • 29 Jan 2023 • Richard A Watson, Hengrui Cai, Xinming An, Samuel McLean, Rui Song
To characterize this heterogeneity, we first conceptualize heterogeneous causal graphs (HCGs) by generalizing the causal graphical model with confounder-based interactions and multiple mediators.
no code implementations • 3 Jan 2023 • Yuhe Gao, Chengchun Shi, Rui Song
Dynamic treatment regimes assign personalized treatments to patients sequentially over time based on their baseline information and time-varying covariates.
no code implementations • CVPR 2023 • Rui Song, Chunyang Fu, Shan Liu, Ge Li
Learning an accurate entropy model is a fundamental way to remove the redundancy in point cloud compression.
1 code implementation • CVPR 2023 • Jian Li, Ziyao Meng, Daqian Shi, Rui Song, Xiaolei Diao, Jingwen Wang, Hao Xu
Through representation learning, DNNs can map BFs into dense clusters in feature space, while the features of minority classes often show sparse clusters.
no code implementations • 30 Dec 2022 • Ye Shen, Runzhe Wan, Hengrui Cai, Rui Song
In the new era of personalization, learning the heterogeneous treatment effect (HTE) becomes an inevitable trend with numerous applications.
no code implementations • 29 Dec 2022 • Yang Xu, Chengchun Shi, Shikai Luo, Lan Wang, Rui Song
Off-Policy evaluation (OPE) is concerned with evaluating a new target policy using offline data generated by a potentially different behavior policy.
no code implementations • 29 Dec 2022 • Yang Xu, Jin Zhu, Chengchun Shi, Shikai Luo, Rui Song
Off-policy evaluation (OPE) is a method for estimating the return of a target policy using some pre-collected observational data generated by a potentially different behavior policy.
no code implementations • 25 Dec 2022 • Runzhe Wan, YingYing Li, Wenbin Lu, Rui Song
Latent factor model estimation typically relies on either using domain knowledge to manually pick several observed covariates as factor proxies, or purely conducting multivariate analysis such as principal component analysis.
no code implementations • 11 Dec 2022 • Rui Song, Liguo Zhou, Lingjuan Lyu, Andreas Festag, Alois Knoll
To address this bottleneck, we introduce a residual-based federated learning framework (ResFed), where residuals rather than model parameters are transmitted in communication networks for training.
2 code implementations • 24 Aug 2022 • Rui Song, Dai Liu, Dave Zhenyu Chen, Andreas Festag, Carsten Trinitis, Martin Schulz, Alois Knoll
In federated learning, all networked clients contribute to the model training cooperatively.
1 code implementation • journal 2022 • Bobo Xi, Jiaojiao Li, Yunsong Li, Rui Song, Danfeng Hong, Jocelyn Chanussot.
Recently, embedding and metric-based few-shot learning (FSL) has been introduced into hyperspectral image classification (HSIC) and achieved impressive progress.
no code implementations • 17 Jun 2022 • Rui Song, Anupama Hegde, Numan Senel, Alois Knoll, Andreas Festag
Specifically, when the measurement error from the sensors (also referred as measurement noise) is unknown and time varying, the performance of the data fusion process is restricted, which represents a major challenge in the calibration of sensors.
no code implementations • NAACL 2022 • Sheng Zhang, Jin Wang, Haitao Jiang, Rui Song
Some feature attribution methods have shown promising results in computer vision, especially the gradient-based methods where effectively smoothing the gradients with reference data is key to a robust and faithful result.
1 code implementation • 1 Apr 2022 • Rui Song, Liguo Zhou, Venkatnarayanan Lakshminarasimhan, Andreas Festag, Alois Knoll
Considering the individual heterogeneity of data distribution, computational and communication capabilities across traffic agents and roadside units, we employ a novel method that addresses the heterogeneity of different aggregation layers of the framework architecture, i. e., aggregation in layers of roadside units and cloud.
1 code implementation • journal 2022 • Bobo Xi, Jiaojiao Li, Yunsong Li, Rui Song, Yuchao Xiao, Qian Du,Jocelyn Chanussot
In practice, the acquirement of labeled samples for hyperspectral image (HSI) is time-consuming and labor-intensive.
no code implementations • 4 Mar 2022 • Kevin Gunn, Wenbin Lu, Rui Song
Simulation studies are conducted to assess the empirical performance of the proposed method and to compare with a fully supervised method using only the labeled data.
no code implementations • 26 Feb 2022 • Runzhe Wan, Branislav Kveton, Rui Song
High-quality data plays a central role in ensuring the accuracy of policy evaluation.
no code implementations • 26 Feb 2022 • Runzhe Wan, Lin Ge, Rui Song
In this paper, we propose a unified meta-learning framework for a general class of structured bandit problems where the parameter space can be factorized to item-level.
1 code implementation • 26 Feb 2022 • Chengchun Shi, Shikai Luo, Yuan Le, Hongtu Zhu, Rui Song
We consider reinforcement learning (RL) methods in offline domains without additional online data collection, such as mobile health applications.
no code implementations • 25 Feb 2022 • Haoyu Chen, Wenbin Lu, Rui Song, Pulak Ghosh
Machine learning has become more important in real-life decision-making but people are concerned about the ethical problems it may bring when used improperly.
no code implementations • 25 Feb 2022 • Lin Ge, Xinming An, Donglin Zeng, Samuel McLean, Ronald Kessler, Rui Song
Adverse posttraumatic neuropsychiatric sequelae (APNS) are common among veterans and millions of Americans after traumatic exposures, resulting in substantial burdens for trauma survivors and society.
1 code implementation • 22 Feb 2022 • Chengchun Shi, Jin Zhu, Ye Shen, Shikai Luo, Hongtu Zhu, Rui Song
In this paper, we show that with some auxiliary variables that mediate the effect of actions on the system dynamics, the target policy's value is identifiable in a confounded Markov decision process.
1 code implementation • 21 Feb 2022 • Chengchun Shi, Runzhe Wan, Ge Song, Shikai Luo, Rui Song, Hongtu Zhu
In this paper we consider large-scale fleet management in ride-sharing companies that involve multiple units in different areas receiving sequences of products (or treatments) over time.
no code implementations • 21 Feb 2022 • Lihan Chen, Sihang Jiang, Jingping Liu, Chao Wang, Sheng Zhang, Chenhao Xie, Jiaqing Liang, Yanghua Xiao, Rui Song
Knowledge graphs (KGs) are an important source repository for a wide range of applications and rule mining from KGs recently attracts wide research interest in the KG-related research community.
1 code implementation • 12 Feb 2022 • Chunyang Fu, Ge Li, Rui Song, Wei Gao, Shan Liu
In point cloud compression, sufficient contexts are significant for modeling the point cloud distribution.
no code implementations • 31 Jan 2022 • Elynn Y. Chen, Rui Song, Michael I. Jordan
Reinforcement Learning (RL) has the promise of providing data-driven support for decision-making in a wide range of problems in healthcare, education, business, and other domains.
no code implementations • 20 Jan 2022 • Yi Ding, YingYing Li, Rui Song
We show that our proposed Discretization and Regression with generalized fOlded concaVe penalty on Effect discontinuity (DROVE) approach enjoys desirable theoretical properties and allows for statistical inference of the optimal value associated with optimal decision-making.
1 code implementation • 29 Dec 2021 • Chaoxiong Wu, Jiaojiao Li, Rui Song, Yunsong Li, Qian Du
Spectral super-resolution (SSR) refers to the hyperspectral image (HSI) recovery from an RGB counterpart.
1 code implementation • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2021 • Yunsong Li, Bobo Xi, Jiaojiao Li, Rui Song, Yuchao Xiao, Jocelyn Chanussot.
To conquer these issues, we propose an efficient symmetric graph metric learning (SGML) framework by incorporating metric learning into the SSGCN paradigm.
no code implementations • 27 Nov 2021 • Jianian Wang, Sheng Zhang, Yanghua Xiao, Rui Song
With multiple components and relations, financial data are often presented as graph data, since it could represent both the individual features and the complicated relations.
no code implementations • 17 Nov 2021 • Hengrui Cai, Chengchun Shi, Rui Song, Wenbin Lu
To derive an optimal I2DR, our jump interval-learning method estimates the conditional mean of the outcome given the treatment and the covariates via jump penalized regression, and derives the corresponding optimal I2DR based on the estimated outcome regression function.
no code implementations • 6 Nov 2021 • Ye Liu, Rui Song, Wenbin Lu, Yanghua Xiao
A large number of models and algorithms have been proposed to perform link prediction, among which tensor factorization method has proven to achieve state-of-the-art performance in terms of computation efficiency and prediction accuracy.
no code implementations • 29 Oct 2021 • Ye Shen, Hengrui Cai, Rui Song
We use this probability to conduct valid inference on the online conditional mean estimator under each action and develop the doubly robust interval estimation (DREAM) method to infer the value under the estimated optimal policy in online learning.
no code implementations • NeurIPS 2021 • Runzhe Wan, Lin Ge, Rui Song
How to explore efficiently is a central problem in multi-armed bandits.
no code implementations • 18 Jun 2021 • Rui Song, Xingbing Chen, Zelong Liu, Haining An, Zhiqi Zhang, Xiaoguang Wang, Hao Xu
In this paper, we propose a Label Mask multi-label text classification model (LM-MTC), which is inspired by the idea of cloze questions of language model.
no code implementations • 30 May 2021 • Hengrui Cai, Zhihao Cen, Ling Leng, Rui Song
We consider the sequential decision optimization on the periodic environment, that occurs in a wide variety of real-world applications when the data involves seasonality, such as the daily demand of drivers in ride-sharing and dynamic traffic patterns in transportation.
no code implementations • 27 May 2021 • Runzhe Wan, Sheng Zhang, Chengchun Shi, Shikai Luo, Rui Song
Order dispatch is one of the central problems to ride-sharing platforms.
1 code implementation • 10 May 2021 • Chengchun Shi, Runzhe Wan, Victor Chernozhukov, Rui Song
Off-policy evaluation learns a target policy's value with a historical dataset generated by a different behavior policy.
1 code implementation • 21 Apr 2021 • Hengrui Cai, Wenbin Lu, Rui Song
We consider the optimal decision-making problem in a primary sample of interest with multiple auxiliary sources available.
no code implementations • 21 Apr 2021 • Hengrui Cai, Rui Song, Wenbin Lu
We propose an auGmented inverse propensity weighted Experimental and Auxiliary sample-based decision Rule (GEAR) by maximizing the augmented inverse propensity weighted value estimator over a class of decision rules using the experimental sample, with the primary outcome being imputed based on the auxiliary sample.
1 code implementation • 19 Apr 2021 • Yaqi Xia, Yan Xia, Wei Li, Rui Song, Kailang Cao, Uwe Stilla
We tackle the problem of object completion from point clouds and propose a novel point cloud completion network employing an Asymmetrical Siamese Feature Matching strategy, termed as ASFM-Net.
no code implementations • 3 Apr 2021 • Rui Song, Fausto Giunchiglia, Ke Zhao, Hao Xu
The complexity and non-Euclidean structure of graph data hinder the development of data augmentation methods similar to those in computer vision.
no code implementations • 11 Mar 2021 • Rui Song, Ning Hao, Ping Zhang
We propose that the hybridization between two sets of Rashba bands can lead to an unconventional topology where the two Fermi circles from different bands own in-plane helical spin textures with the same chiralities, and possess group velocities with the same directions.
Materials Science Mesoscale and Nanoscale Physics
no code implementations • ICLR 2021 • Hengrui Cai, Rui Song, Wenbin Lu
Under a general causal graph, the exposure may have a direct effect on the outcome and also an indirect effect regulated by a set of mediators.
no code implementations • 1 Jan 2021 • Chengchun Shi, Xiaoyu Wang, Shikai Luo, Rui Song, Hongtu Zhu, Jieping Ye
A/B testing, or online experiment is a standard business strategy to compare a new product with an old one in pharmaceutical, technological, and traditional industries.
no code implementations • 1 Jan 2021 • Sheng Zhang, Rui Song, Wenbin Lu
In a number of experiments on benchmark datasets, we show that the proposed GraphCGAN outperforms the baseline methods by a significant margin.
no code implementations • 1 Jan 2021 • Haoyu Chen, Wenbin Lu, Rui Song, Pulak Ghosh
Machine learning has become more important in real-life decision-making but people are concerned about the ethical problems it may bring when used improperly.
1 code implementation • 11 Dec 2020 • Bobo Xi, Jiaojiao Li, Yunsong Li, Rui Song, Yuchao Xiao, Yanzi Shi, Qian Du.
Convolutional neural networks (CNNs) have achieved prominent progress in recent years and demonstrated remarkable properties in spectral-spatial hyperspectral image (HSI) classification.
1 code implementation • NeurIPS 2021 • Hengrui Cai, Chengchun Shi, Rui Song, Wenbin Lu
To handle continuous treatments, we develop a novel estimation method for OPE using deep jump learning.
1 code implementation • EMNLP 2020 • Ye Liu, Sheng Zhang, Rui Song, Suo Feng, Yanghua Xiao
Effectively filtering out noisy articles as well as bad answers is the key to improving extraction accuracy.
1 code implementation • 14 Oct 2020 • Haoyu Chen, Wenbin Lu, Rui Song
Focusing on the statistical inference of online decision making, we establish the asymptotic normality of the parameter estimator produced by our algorithm and the online inverse probability weighted value estimator we used to estimate the optimal value.
no code implementations • 14 Oct 2020 • Haoyu Chen, Wenbin Lu, Rui Song
Based on the properties of the parameter estimators, we further show that the in-sample inverse propensity weighted value estimator is asymptotically normal.
no code implementations • 28 Sep 2020 • Hengrui Cai, Chengchun Shi, Rui Song, Wenbin Lu
To handle continuous action space, we develop a brand-new deep jump Q-evaluation method for OPE.
1 code implementation • 22 Sep 2020 • Bobo Xi, Jiaojiao Li, Yunsong Li, Rui Song, Weiwei Sun, Qian Du.
Recently, multiscale spatial features have been widely utilized to improve the hyperspectral image (HSI) classification performance.
no code implementations • 9 Sep 2020 • Runzhe Wan, Xin-Yu Zhang, Rui Song
Severe infectious diseases such as the novel coronavirus (COVID-19) pose a huge threat to public health.
1 code implementation • 19 Jul 2020 • Liangyu Zhu, Wenbin Lu, Michael R. Kosorok, Rui Song
In this article, we propose a kernel assisted learning method for estimating the optimal individualized dose rule.
1 code implementation • 25 Jun 2020 • Bobo Xi, Jiaojiao Li, Yunsong Li, Rui Song, Yanzi Shi, Songlin Liu, Qian Du
Recently, convolutional neural networks (CNNs) have attracted enormous attention in pattern recognition and demonstrated excellent performance in hyperspectral image (HSI) classification.
1 code implementation • 19 May 2020 • Jiaojiao Li, Chaoxiong Wu, Rui Song, Yunsong Li, Fei Liu
Recent promising effort for spectral reconstruction (SR) focuses on learning a complicated mapping through using a deeper and wider convolutional neural networks (CNNs).
1 code implementation • 5 Feb 2020 • Chengchun Shi, Xiaoyu Wang, Shikai Luo, Hongtu Zhu, Jieping Ye, Rui Song
A/B testing, or online experiment is a standard business strategy to compare a new product with an old one in pharmaceutical, technological, and traditional industries.
1 code implementation • ICML 2020 • Chengchun Shi, Runzhe Wan, Rui Song, Wenbin Lu, Ling Leng
The Markov assumption (MA) is fundamental to the empirical validity of reinforcement learning.
no code implementations • IWSLT (EMNLP) 2018 • Dan Liu, Junhua Liu, Wu Guo, Shifu Xiong, Zhiqiang Ma, Rui Song, Chongliang Wu, Quan Liu
This paper describes the USTC-NEL system to the speech translation task of the IWSLT Evaluation 2018.
no code implementations • 18 Sep 2017 • Rui Song, Dong Liu, Houqiang Li, Feng Wu
In this paper, we propose an arithmetic coding strategy by training neural networks, and make preliminary studies on coding of the intra prediction modes in HEVC.
Multimedia
1 code implementation • CVPR 2017 • Yinlin Hu, Yunsong Li, Rui Song
In this paper, we present a Robust Interpolation method of Correspondences (called RicFlow) to overcome the weakness.
1 code implementation • CVPR 2016 • Yinlin Hu, Rui Song, Yunsong Li
Inspired by the nearest neighbor field (NNF) algorithms, our approach, called CPM (Coarse-to-fine PatchMatch), blends an efficient random search strategy with the coarse-to-fine scheme for optical flow problem.
no code implementations • 31 Mar 2016 • Hyunsuk Ko, Rui Song, C. -C. Jay Kuo
The problem of stereoscopic image quality assessment, which finds applications in 3D visual content delivery such as 3DTV, is investigated in this work.
no code implementations • 15 Oct 2015 • Chengchun Shi, Rui Song, Wenbin Lu
In this paper, we propose a two-step estimation procedure for deriving the optimal treatment regime under NP dimensionality.
2 code implementations • 29 Jul 2014 • Shikai Luo, Rui Song, Daniela Witten
We propose {graphical sure screening}, or GRASS, a very simple and computationally-efficient screening procedure for recovering the structure of a Gaussian graphical model in the high-dimensional setting.
no code implementations • 20 May 2014 • Ailin Fan, Wenbin Lu, Rui Song
Gunter et al. (2011) proposed S-score which characterizes the magnitude of qualitative interaction of each variable with treatment individually.
no code implementations • 23 Mar 2014 • Rui Song, Hyunsuk Ko, C. -C. Jay Kuo
A new stereoscopic image quality assessment database rendered using the 2D-image-plus-depth source, called MCL-3D, is described and the performance benchmarking of several known 2D and 3D image quality metrics using the MCL-3D database is presented in this work.
no code implementations • 18 Jul 2012 • Jelena Bradic, Rui Song
To better understand the interplay of censoring and sparsity we develop finite sample properties of nonparametric Cox proportional hazard's model.