no code implementations • CCL 2020 • Ting Jiang, Bing Xu, Tiejun Zhao, Sheng Li
In the first layer, in order to extract textual features of utterances, we propose a convolutional self-attention network(CAN).
no code implementations • ACL (WOAH) 2021 • Sumer Singh, Sheng Li
Our approach introduces domain adaptation (DA) training procedures to ALBERT, such that it can effectively exploit auxiliary data from source domains to improve the OLD performance in a target domain.
no code implementations • 11 Apr 2022 • Zhengdong Yang, Wangjin Zhou, Chenhui Chu, Sheng Li, Raj Dabre, Raphael Rubino, Yi Zhao
This challenge aims to predict MOS scores of synthetic speech on two tracks, the main track and a more challenging sub-track: out-of-domain (OOD).
no code implementations • 8 Apr 2022 • Qianying Liu, Yuhang Yang, Zhuo Gong, Sheng Li, Chenchen Ding, Nobuaki Minematsu, Hao Huang, Fei Cheng, Sadao Kurohashi
Low resource speech recognition has been long-suffering from insufficient training data.
no code implementations • 10 Mar 2022 • Zhixuan Chu, Stephen L. Rathbun, Sheng Li
In our paper, the basket trial is employed as an intuitive example to present this new causal inference setting.
no code implementations • 22 Feb 2022 • Zhixuan Chu, Stephen Rathbun, Sheng Li
In this paper, we reveal the weaknesses of these strategies, i. e., they lead to the loss of predictive information when enforcing the domain invariance; and the treatment effect estimation performance is unstable, which heavily relies on the characteristics of the domain distributions and the choice of domain divergence metrics.
no code implementations • 29 Dec 2021 • Kejiang Chen, Xianhan Zeng, Qichao Ying, Sheng Li, Zhenxing Qian, Xinpeng Zhang
We develop a reversible adversarial example generator (RAEG) that introduces slight changes to the images to fool traditional classification models.
no code implementations • 23 Nov 2021 • Xiaoshui Huang, Zongyi Xu, Guofeng Mei, Sheng Li, Jian Zhang, Yifan Zuo, Yucheng Wang
To solve this challenge, we propose a new data-driven registration algorithm by investigating deep generative neural networks to point cloud registration.
no code implementations • 15 Oct 2021 • Zhuowen Yuan, Sheng Li, Xinpeng Zhang, Zhenxin Qian, Alex Kot
Our virtual face images are visually different from the original ones for privacy protection.
no code implementations • ICLR 2022 • Ronghang Zhu, Sheng Li
In this paper, we propose a challenging and untouched problem: \textit{Open-Set Single Domain Generalization} (OS-SDG), where target domains include unseen categories out of source label space.
no code implementations • 29 Sep 2021 • Weili Shi, Ronghang Zhu, Sheng Li
In this paper, we propose a pairwise adversarial training approach to augment training data for unsupervised class-imbalanced domain adaptation.
no code implementations • 9 Jul 2021 • Ronghang Zhu, Zhiqiang Tao, Yaliang Li, Sheng Li
Owing to the remarkable capability of extracting effective graph embeddings, graph convolutional network (GCN) and its variants have been successfully applied to a broad range of tasks, such as node classification, link prediction, and graph classification.
no code implementations • 8 Jun 2021 • Ziyu Guan, Hongchang Wu, Qingyu Cao, Hao liu, Wei Zhao, Sheng Li, Cai Xu, Guang Qiu, Jian Xu, Bo Zheng
Although a few studies use multi-agent reinforcement learning to set up a cooperative game, they still suffer the following drawbacks: (1) They fail to avoid collusion solutions where all the advertisers involved in an auction collude to bid an extremely low price on purpose.
no code implementations • 5 Jun 2021 • Zhixuan Chu, Stephen L. Rathbun, Sheng Li
The foremost challenge in treatment effect estimation is how to capture hidden confounders.
no code implementations • 13 May 2021 • Matthew Junge, Sheng Li, Samitha Samaranayake, Matthew Zalesak
We construct an agent-based SEIR model to simulate COVID-19 spread at a 16000-student mostly non-residential urban university during the Fall 2021 Semester.
no code implementations • NAACL 2021 • Saed Rezayi, Handong Zhao, Sungchul Kim, Ryan A. Rossi, Nedim Lipka, Sheng Li
Knowledge graphs suffer from sparsity which degrades the quality of representations generated by various methods.
no code implementations • 24 Feb 2021 • Sheng Li, Yutai Zhou, Ross Allen, Mykel J. Kochenderfer
Communication is a important factor that enables agents work cooperatively in multi-agent reinforcement learning (MARL).
no code implementations • CVPR 2021 • Sheng Li, Mingxing Tan, Ruoming Pang, Andrew Li, Liqun Cheng, Quoc Le, Norman P. Jouppi
On top of our DC accelerator optimized neural architecture search space, we further propose a latency-aware compound scaling (LACS), the first multi-objective compound scaling method optimizing both accuracy and latency.
no code implementations • 1 Jan 2021 • Zhixuan Chu, Stephen Rathbun, Sheng Li
We propose a Continual Causal Effect Representation Learning method for estimating causal effect with observational data, which are incrementally available from non-stationary data distributions.
no code implementations • 1 Jan 2021 • Ronghang Zhu, Xiaodong Jiang, Jiasen Lu, Sheng Li
In this paper, we propose a novel Transferable Feature Learning approach on Graphs (TFLG) for unsupervised adversarial domain adaptation, which jointly incorporates sample-level and class-level structure information across two domains.
no code implementations • 25 Oct 2020 • Xiaodong Jiang, Ronghang Zhu, Pengsheng Ji, Sheng Li
CensNet is a general graph embedding framework, which embeds both nodes and edges to a latent feature space.
no code implementations • 15 Sep 2020 • Zhixuan Chu, Stephen L. Rathbun, Sheng Li
The dramatically growing availability of observational data is being witnessed in various domains of science and technology, which facilitates the study of causal inference.
no code implementations • 14 Sep 2020 • Yue Bai, Zhiqiang Tao, Lichen Wang, Sheng Li, Yu Yin, Yun Fu
Extensive experiments on four action datasets illustrate the proposed CAM achieves better results for each view and also boosts multi-view performance.
1 code implementation • 19 Jun 2020 • Sheng Li, Jayesh K. Gupta, Peter Morales, Ross Allen, Mykel J. Kochenderfer
Coordination graph based formalization allows reasoning about the joint action based on the structure of interactions.
no code implementations • 29 Apr 2020 • Mohammadhossein Toutiaee, Soheyla Amirian, John A. Miller, Sheng Li
The proposed approach aids labeling new data (fictitious output images) by minimizing a penalized version of the least squares cost function between realistic pictures and target pictures.
no code implementations • 13 Feb 2020 • Hongwei Yi, Shaoshuai Shi, Mingyu Ding, Jiankai Sun, Kui Xu, Hui Zhou, Zhe Wang, Sheng Li, Guoping Wang
First, the semantic context information in LiDAR is seldom explored in previous works, which may help identify ambiguous vehicles.
1 code implementation • 5 Feb 2020 • Liuyi Yao, Zhixuan Chu, Sheng Li, Yaliang Li, Jing Gao, Aidong Zhang
Embraced with the rapidly developed machine learning area, various causal effect estimation methods for observational data have sprung up.
no code implementations • 27 Dec 2019 • Xugang Lu, Peng Shen, Sheng Li, Yu Tsao, Hisashi Kawai
However, a potential limitation of the network is that the discriminative features from the bottom layers (which can model the short-range dependency) are smoothed out in the final representation.
no code implementations • 26 Dec 2019 • Jiahuan Ren, Zhao Zhang, Sheng Li, Yang Wang, Guangcan Liu, Shuicheng Yan, Meng Wang
Specifically, J-RFDL performs the robust representation by DL in a factorized compressed space to eliminate the negative effects of noise and outliers on the results, which can also make the DL process efficient.
no code implementations • 20 Dec 2019 • Sheng Li, Maxim Egorov, Mykel Kochenderfer
New methodologies will be needed to ensure the airspace remains safe and efficient as traffic densities rise to accommodate new unmanned operations.
no code implementations • 24 Nov 2019 • Yue Bai, Lichen Wang, Zhiqiang Tao, Sheng Li, Yun Fu
Multi-view time series classification (MVTSC) aims to improve the performance by fusing the distinctive temporal information from multiple views.
no code implementations • 28 Sep 2019 • Zhengming Ding, Ming Shao, Handong Zhao, Sheng Li
It is always demanding to learn robust visual representation for various learning problems; however, this learning and maintenance process usually suffers from noise, incompleteness or knowledge domain mismatch.
no code implementations • 2 Sep 2019 • Zhao Zhang, Yan Zhang, Sheng Li, Guangcan Liu, Dan Zeng, Shuicheng Yan, Meng Wang
For auto-weighting, RFA-LCF jointly preserves the manifold structures in the basis concept space and new coordinate space in an adaptive manner by minimizing the reconstruction errors on clean data, anchor points and coordinates.
no code implementations • 21 Aug 2019 • Zhao Zhang, Lei Wang, Sheng Li, Yang Wang, Zheng Zhang, Zheng-Jun Zha, Meng Wang
Specifically, AS-LRC performs the latent decomposition of given data into a low-rank reconstruction by a block-diagonal codes matrix, a group sparse locality-adaptive salient feature part and a sparse error part.
no code implementations • Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI-19) 2019 • Xiaodong Jiang, Pengsheng Ji, Sheng Li
In this paper, we present CensNet, Convolution with Edge-Node Switching graph neural network, for semi-supervised classification and regression in graph-structured data with both node and edge features.
Ranked #1 on
Graph Regression
on Lipophilicity
(RMSE@80%Train metric)
no code implementations • 4 Aug 2019 • Zhao Zhang, Jiahuan Ren, Sheng Li, Richang Hong, Zheng-Jun Zha, Meng Wang
Leveraging on the Frobenius-norm based latent low-rank representation model, rBDLR jointly learns the coding coefficients and salient features, and improves the results by enhancing the robustness to outliers and errors in given data, preserving local information of salient features adaptively and ensuring the block-diagonal structures of the coefficients.
no code implementations • 25 May 2019 • Zhao Zhang, Weiming Jiang, Zheng Zhang, Sheng Li, Guangcan Liu, Jie Qin
More importantly, LC-PDL avoids using the complementary data matrix to learn the sub-dictionary over each class.
no code implementations • 25 May 2019 • Zhao Zhang, Yan Zhang, Sheng Li, Guangcan Liu, Meng Wang, Shuicheng Yan
RFA-LCF integrates the robust flexible CF, robust sparse local-coordinate coding and the adaptive reconstruction weighting learning into a unified model.
no code implementations • CVPR 2019 • Sheng Li, Fengxiang He, Bo Du, Lefei Zhang, Yonghao Xu, DaCheng Tao
Recently, deep learning based video super-resolution (SR) methods have achieved promising performance.
no code implementations • 3 Apr 2019 • Zheng Zhang, Guo-Sen Xie, Yang Li, Sheng Li, Zi Huang
Due to its low storage cost and fast query speed, hashing has been recognized to accomplish similarity search in large-scale multimedia retrieval applications.
no code implementations • CVPR 2019 • Jiuxiang Gu, Handong Zhao, Zhe Lin, Sheng Li, Jianfei Cai, Mingyang Ling
Scene graph generation has received growing attention with the advancements in image understanding tasks such as object detection, attributes and relationship prediction,~\etc.
no code implementations • 8 Jan 2019 • Tuan Manh Lai, Trung Bui, Nedim Lipka, Sheng Li
Popular e-commerce websites such as Amazon offer community question answering systems for users to pose product related questions and experienced customers may provide answers voluntarily.
1 code implementation • NeurIPS 2018 • Liuyi Yao, Sheng Li, Yaliang Li, Mengdi Huai, Jing Gao, Aidong Zhang
Estimating individual treatment effect (ITE) is a challenging problem in causal inference, due to the missing counterfactuals and the selection bias.
no code implementations • ECCV 2018 • Zhengming Ding, Sheng Li, Ming Shao, Yun Fu
However, existing approaches separate target label optimization and domain-invariant feature learning as different steps.
no code implementations • 6 Aug 2018 • Longfei Liu, Sheng Li, Yisong Chen, Guoping Wang
Image reconstruction including image restoration and denoising is a challenging problem in the field of image computing.
no code implementations • COLING 2018 • Tuan Manh Lai, Trung Bui, Sheng Li
Given a question and a set of candidate answers, answer selection is the task of identifying which of the candidates answers the question correctly.
no code implementations • WS 2018 • Tuan Lai, Trung Bui, Sheng Li, Nedim Lipka
When evaluating a potential product purchase, customers may have many questions in mind.
no code implementations • ACL 2018 • Xinzhou Jiang, Zhenghua Li, Bo Zhang, Min Zhang, Sheng Li, Luo Si
Treebank conversion is a straightforward and effective way to exploit various heterogeneous treebanks for boosting parsing performance.
no code implementations • 5 Jan 2018 • Jingang Wang, Junfeng Tian, Long Qiu, Sheng Li, Jun Lang, Luo Si, Man Lan
It is a challenging and practical research problem to obtain effective compression of lengthy product titles for E-commerce.
no code implementations • NeurIPS 2017 • Sheng Li, Yun Fu
Estimating treatment effects from observational data is challenging due to the missing counterfactuals.
1 code implementation • 28 Feb 2017 • Sheng Li, Jongsoo Park, Ping Tak Peter Tang
Sparse methods and the use of Winograd convolutions are two orthogonal approaches, each of which significantly accelerates convolution computations in modern CNNs.
1 code implementation • 18 Nov 2016 • Shihao Ji, Nadathur Satish, Sheng Li, Pradeep Dubey
Word2vec is a widely used algorithm for extracting low-dimensional vector representations of words.
1 code implementation • 4 Aug 2016 • Jongsoo Park, Sheng Li, Wei Wen, Ping Tak Peter Tang, Hai Li, Yiran Chen, Pradeep Dubey
Pruning CNNs in a way that increase inference speed often imposes specific sparsity structures, thus limiting the achievable sparsity levels.
no code implementations • 15 Apr 2016 • Shihao Ji, Nadathur Satish, Sheng Li, Pradeep Dubey
In combination, these techniques allow us to scale up the computation near linearly across cores and nodes, and process hundreds of millions of words per second, which is the fastest word2vec implementation to the best of our knowledge.
no code implementations • ICCV 2015 • Sheng Li, Kang Li, Yun Fu
Subspace clustering is an effective technique for segmenting data drawn from multiple subspaces.