no code implementations • 27 May 2024 • Xinyi Gao, Tong Chen, Wentao Zhang, Yayong Li, Xiangguo Sun, Hongzhi Yin
Consequently, due to the limited generalization capacity of condensed graphs, applications that employ GC for efficient GNN training end up with sub-optimal GNNs when confronted with evolving graph structures and distributions in dynamic real-world situations.
no code implementations • 22 May 2024 • Xinyi Gao, Tong Chen, Wentao Zhang, Junliang Yu, Guanhua Ye, Quoc Viet Hung Nguyen, Hongzhi Yin
The increasing prevalence of large-scale graphs poses a significant challenge for graph neural network training, attributed to their substantial computational requirements.
no code implementations • 22 May 2024 • Jing Long, Guanhua Ye, Tong Chen, Yang Wang, Meng Wang, Hongzhi Yin
The rapid expansion of Location-Based Social Networks (LBSNs) has highlighted the importance of effective next Point-of-Interest (POI) recommendations, which leverage historical check-in data to predict users' next POIs to visit.
1 code implementation • 17 May 2024 • Tong Chen, Qingcheng Lyu, Long Bai, Erjian Guo, Huxin Gao, Xiaoxiao Yang, Hongliang Ren, Luping Zhou
We further introduce a Chroma Balancer (CB) to mitigate this issue.
1 code implementation • 4 May 2024 • Xinran Zhao, Tong Chen, Sihao Chen, Hongming Zhang, Tongshuang Wu
In this work, we study whether retrievers can recognize and respond to different perspectives of the queries -- beyond finding relevant documents for a claim, can retrievers distinguish supporting vs. opposing documents?
no code implementations • 1 Apr 2024 • Ruiqi Zheng, Liang Qu, Tong Chen, Kai Zheng, Yuhui Shi, Hongzhi Yin
Knowledge sharing also opens a backdoor for model poisoning attacks, where adversaries disguise themselves as benign clients and disseminate polluted knowledge to achieve malicious goals like promoting an item's exposure rate.
1 code implementation • 27 Mar 2024 • Xurong Liang, Tong Chen, Lizhen Cui, Yang Wang, Meng Wang, Hongzhi Yin
Graph neural networks (GNNs) are currently one of the most performant collaborative filtering methods.
1 code implementation • 17 Mar 2024 • Paul S. Scotti, Mihir Tripathy, Cesar Kadir Torrico Villanueva, Reese Kneeland, Tong Chen, Ashutosh Narang, Charan Santhirasegaran, Jonathan Xu, Thomas Naselaris, Kenneth A. Norman, Tanishq Mathew Abraham
Reconstructions of visual perception from brain activity have improved tremendously, but the practical utility of such methods has been limited.
2 code implementations • 14 Mar 2024 • Hallgrimur Thorsteinsson, Valdemar J Henriksen, Tong Chen, Raghavendra Selvan
We present experiments on two benchmark datasets showing that adversarial fine-tuning of compressed models can achieve robustness performance comparable to adversarially trained models, while also improving computational efficiency.
no code implementations • 17 Feb 2024 • Gaocheng Ma, Yinfeng Chai, Tianhao Jiang, Ming Lu, Tong Chen
Image compression has been the subject of extensive research for several decades, resulting in the development of well-known standards such as JPEG, JPEG2000, and H. 264/AVC.
no code implementations • 16 Feb 2024 • Hongbin Na, Zimu Wang, Mieradilijiang Maimaiti, Tong Chen, Wei Wang, Tao Shen, Ling Chen
Large language models (LLMs) have demonstrated promising potential in various downstream tasks, including machine translation.
1 code implementation • 8 Feb 2024 • Tong Chen, Raghavendra Selvan
This synthetic dataset retains the essential information of the original dataset, enabling models trained on it to achieve performance levels comparable to those trained on the full dataset.
no code implementations • 26 Jan 2024 • Wei Jiang, Xinyi Gao, Guandong Xu, Tong Chen, Hongzhi Yin
To comprehensively extract preference-aware homophily information latent in the social graph, we propose Social Heterophily-alleviating Rewiring (SHaRe), a data-centric framework for enhancing existing graph-based social recommendation models.
no code implementations • 26 Jan 2024 • Jing Long, Tong Chen, Guanhua Ye, Kai Zheng, Nguyen Quoc Viet Hung, Hongzhi Yin
Empirical results demonstrate that PTIA poses a significant threat to users' historical trajectories.
no code implementations • 24 Jan 2024 • Ruiqi Zheng, Liang Qu, Tong Chen, Lizhen Cui, Yuhui Shi, Hongzhi Yin
Collaborative Learning (CL) emerges to promote model sharing among users, where reference data is an intermediary that allows users to exchange their soft decisions without directly sharing their private data or parameters, ensuring privacy and benefiting from collaboration.
no code implementations • 22 Jan 2024 • Xinyi Gao, Junliang Yu, Wei Jiang, Tong Chen, Wentao Zhang, Hongzhi Yin
The burgeoning volume of graph data poses significant challenges in storage, transmission, and particularly the training of graph neural networks (GNNs).
no code implementations • 21 Jan 2024 • Hongzhi Yin, Liang Qu, Tong Chen, Wei Yuan, Ruiqi Zheng, Jing Long, Xin Xia, Yuhui Shi, Chengqi Zhang
Recently, driven by the advances in storage, communication, and computation capabilities of edge devices, there has been a shift of focus from CloudRSs to on-device recommender systems (DeviceRSs), which leverage the capabilities of edge devices to minimize centralized data storage requirements, reduce the response latency caused by communication overheads, and enhance user privacy and security by localizing data processing and model training.
no code implementations • 25 Dec 2023 • Lijian Chen, Wei Yuan, Tong Chen, Guanhua Ye, Quoc Viet Hung Nguyen, Hongzhi Yin
Visually-aware recommender systems have found widespread application in domains where visual elements significantly contribute to the inference of users' potential preferences.
no code implementations • 18 Dec 2023 • Hongzhi Yin, Tong Chen, Liang Qu, Bin Cui
Given the sheer volume of contemporary e-commerce applications, recommender systems (RSs) have gained significant attention in both academia and industry.
1 code implementation • 11 Dec 2023 • Tong Chen, Hongwei Wang, Sihao Chen, Wenhao Yu, Kaixin Ma, Xinran Zhao, Hongming Zhang, Dong Yu
We discover that the retrieval unit choice significantly impacts the performance of both retrieval and downstream tasks.
1 code implementation • 19 Nov 2023 • Yuting Sun, Guansong Pang, Guanhua Ye, Tong Chen, Xia Hu, Hongzhi Yin
The ongoing challenges in time series anomaly detection (TSAD), notably the scarcity of anomaly labels and the variability in anomaly lengths and shapes, have led to the need for a more efficient solution.
1 code implementation • 7 Nov 2023 • Sihao Chen, Hongming Zhang, Tong Chen, Ben Zhou, Wenhao Yu, Dian Yu, Baolin Peng, Hongwei Wang, Dan Roth, Dong Yu
We introduce sub-sentence encoder, a contrastively-learned contextual embedding model for fine-grained semantic representation of text.
no code implementations • 23 Oct 2023 • Yunke Qu, Tong Chen, Quoc Viet Hung Nguyen, Hongzhi Yin
Experiments have shown state-of-the-art performance on two real-world datasets when BET is paired with three popular recommender models under different memory budgets.
1 code implementation • 15 Sep 2023 • Hechuan Wen, Tong Chen, Li Kheng Chai, Shazia Sadiq, Kai Zheng, Hongzhi Yin
Due to the imbalanced nature of networked observational data, the causal effect predictions for some individuals can severely violate the positivity/overlap assumption, rendering unreliable estimations.
1 code implementation • 7 Sep 2023 • Xurong Liang, Tong Chen, Quoc Viet Hung Nguyen, JianXin Li, Hongzhi Yin
In addition, we innovatively design a regularized pruning mechanism in CERP, such that the two sparsified meta-embedding tables are encouraged to encode information that is mutually complementary.
no code implementations • 27 Aug 2023 • Guankun Wang, Long Bai, Yanan Wu, Tong Chen, Hongliang Ren
More seriously, data privacy and storage issues may lead to the unavailability of old data when updating the model.
no code implementations • 25 Aug 2023 • Guanhua Ye, Tong Chen, Quoc Viet Hung Nguyen, Hongzhi Yin
As some recent information security legislation endowed users with unconditional rights to be forgotten by any trained machine learning model, personalized IoT service providers have to put unlearning functionality into their consideration.
no code implementations • 15 Aug 2023 • Yi Liu, Hongrui Xuan, Bohan Li, Meng Wang, Tong Chen, Hongzhi Yin
However, the long-tail distribution of entities leads to sparsity in supervision signals, which weakens the quality of item representation when utilizing KG enhancement.
no code implementations • 5 Aug 2023 • Hechen Li, Yanan Wu, Long Bai, An Wang, Tong Chen, Hongliang Ren
Notably, we develop the segmentation annotations for this dataset ourselves.
no code implementations • 29 Jul 2023 • Xinyi Gao, Tong Chen, Yilong Zang, Wentao Zhang, Quoc Viet Hung Nguyen, Kai Zheng, Hongzhi Yin
To overcome this issue, we propose mapping-aware graph condensation (MCond), explicitly learning the one-to-many node mapping from original nodes to synthetic nodes to seamlessly integrate new nodes into the synthetic graph for inductive representation learning.
1 code implementation • 5 Jul 2023 • Long Bai, Tong Chen, Yanan Wu, An Wang, Mobarakol Islam, Hongliang Ren
Given the exuberant development of the denoising diffusion probabilistic model (DDPM) in computer vision, we introduce a WCE LLIE framework based on the multi-scale convolutional neural network (CNN) and reverse diffusion process.
no code implementations • 23 Jun 2023 • Hechuan Wen, Tong Chen, Li Kheng Chai, Shazia Sadiq, Junbin Gao, Hongzhi Yin
We term the co-occurrence of domain shift and inaccessible variables runtime domain corruption, which seriously impairs the generalizability of a trained counterfactual predictor.
no code implementations • 18 Jun 2023 • Ruiqi Zheng, Liang Qu, Tong Chen, Kai Zheng, Yuhui Shi, Hongzhi Yin
Given a memory budget, PEEL efficiently generates PEEs by selecting embedding blocks with the largest weights, making it adaptable to dynamic memory budgets on devices.
no code implementations • 17 Jun 2023 • Shangfei Zheng, Hongzhi Yin, Tong Chen, Quoc Viet Hung Nguyen, Wei Chen, Lei Zhao
This paper proposes a model called TMR to mine valuable information from simulated data environments.
1 code implementation • 11 May 2023 • Lingzhi Wang, Tong Chen, Wei Yuan, Xingshan Zeng, Kam-Fai Wong, Hongzhi Yin
Recent legislation of the "right to be forgotten" has led to the interest in machine unlearning, where the learned models are endowed with the function to forget information about specific training instances as if they have never existed in the training set.
no code implementations • 1 May 2023 • Xuhui Ren, Tong Chen, Quoc Viet Hung Nguyen, Lizhen Cui, Zi Huang, Hongzhi Yin
Recent conversational recommender systems (CRSs) tackle those limitations by enabling recommender systems to interact with the user to obtain her/his current preference through a sequence of clarifying questions.
no code implementations • 24 Apr 2023 • Xuhui Ren, Wei Yuan, Tong Chen, Chaoqun Yang, Quoc Viet Hung Nguyen, Hongzhi Yin
Knowledge graphs (KGs) have become important auxiliary information for helping recommender systems obtain a good understanding of user preferences.
no code implementations • 8 Apr 2023 • Jing Long, Tong Chen, Nguyen Quoc Viet Hung, Guandong Xu, Kai Zheng, Hongzhi Yin
In light of this, We propose a novel on-device POI recommendation framework, namely Model-Agnostic Collaborative learning for on-device POI recommendation (MAC), allowing users to customize their own model structures (e. g., dimension \& number of hidden layers).
no code implementations • 8 Apr 2023 • Shangfei Zheng, Hongzhi Yin, Tong Chen, Quoc Viet Hung Nguyen, Wei Chen, Lei Zhao
Although existing TKG reasoning methods have the ability to predict missing future events, they fail to generate explicit reasoning paths and lack explainability.
no code implementations • 7 Apr 2023 • Yunke Qu, Tong Chen, Xiangyu Zhao, Lizhen Cui, Kai Zheng, Hongzhi Yin
Latent factor models are the most popular backbones for today's recommender systems owing to their prominent performance.
no code implementations • 7 Mar 2023 • Yuting Sun, Tong Chen, Quoc Viet Hung Nguyen, Hongzhi Yin
With the prevalent deployment of the Industrial Internet of Things (IIoT), an enormous amount of time series data is collected to facilitate machine learning models for anomaly detection, and it is of the utmost importance to directly deploy the trained models on the IIoT devices.
no code implementations • 27 Feb 2023 • Xinyi Gao, Wentao Zhang, Tong Chen, Junliang Yu, Hung Quoc Viet Nguyen, Hongzhi Yin
To tackle the imbalance of minority classes and supplement their inadequate semantics, we present the first method for the semantic imbalance problem in imbalanced HINs named Semantic-aware Node Synthesis (SNS).
no code implementations • 22 Oct 2022 • Yang Li, Tong Chen, Peng-Fei Zhang, Zi Huang, Hongzhi Yin
In order to counteract the scarcity and incompleteness of POI check-ins, we propose a novel self-supervised learning paradigm in \ssgrec, where the trajectory representations are contrastively learned from two augmented views on geolocations and temporal transitions.
1 code implementation • 6 Sep 2022 • Junliang Yu, Xin Xia, Tong Chen, Lizhen Cui, Nguyen Quoc Viet Hung, Hongzhi Yin
Contrastive learning (CL) has recently been demonstrated critical in improving recommendation performance.
no code implementations • 1 Jul 2022 • Yu Yang, Hongzhi Yin, Jiannong Cao, Tong Chen, Quoc Viet Hung Nguyen, Xiaofang Zhou, Lei Chen
Meanwhile, we treat each edge sequence as a whole and embed its ToV of the first vertex to further encode the time-sensitive information.
1 code implementation • 16 Jun 2022 • Lei Guo, Jinyu Zhang, Tong Chen, Xinhua Wang, Hongzhi Yin
Shared-account Cross-domain Sequential Recommendation (SCSR) is an emerging yet challenging task that simultaneously considers the shared-account and cross-domain characteristics in the sequential recommendation.
1 code implementation • 16 Jun 2022 • Lei Guo, Jinyu Zhang, Li Tang, Tong Chen, Lei Zhu, Hongzhi Yin
Shared-account Cross-domain Sequential Recommendation (SCSR) task aims to recommend the next item via leveraging the mixed user behaviors in multiple domains.
no code implementations • 4 May 2022 • Yuting Sun, Tong Chen, Hongzhi Yin
Exposure to crime and violence can harm individuals' quality of life and the economic growth of communities.
1 code implementation • 6 Apr 2022 • Tong Chen, Hongzhi Yin, Jing Long, Quoc Viet Hung Nguyen, Yang Wang, Meng Wang
Such user and group preferences are commonly represented as points in the vector space (i. e., embeddings), where multiple user embeddings are compressed into one to facilitate ranking for group-item pairs.
no code implementations • 30 Mar 2022 • Jing Long, Tong Chen, Nguyen Quoc Viet Hung, Hongzhi Yin
On this basis, we propose a novel decentralized collaborative learning framework for POI recommendation (DCLR), which allows users to train their personalized models locally in a collaborative manner.
1 code implementation • 29 Mar 2022 • Junliang Yu, Hongzhi Yin, Xin Xia, Tong Chen, Jundong Li, Zi Huang
In recent years, neural architecture-based recommender systems have achieved tremendous success, but they still fall short of expectation when dealing with highly sparse data.
no code implementations • 24 Jan 2022 • Wei Yuan, Hongzhi Yin, Tieke He, Tong Chen, Qiufeng Wang, Lizhen Cui
To solve the problems, we propose a model named Unified-QG based on lifelong learning techniques, which can continually learn QG tasks across different datasets and formats.
no code implementations • 8 Jan 2022 • Mubashir Imran, Hongzhi Yin, Tong Chen, Zi Huang, Kai Zheng
Such heterogeneous network embedding (HNE) methods effectively harness the heterogeneity of small-scale HINs.
no code implementations • 17 Dec 2021 • Guanhua Ye, Hongzhi Yin, Tong Chen, Miao Xu, Quoc Viet Hung Nguyen, Jiangning Song
Actuated by the growing attention to personal healthcare and the pandemic, the popularity of E-health is proliferating.
1 code implementation • 16 Dec 2021 • Junliang Yu, Hongzhi Yin, Xin Xia, Tong Chen, Lizhen Cui, Quoc Viet Hung Nguyen
Contrastive learning (CL) recently has spurred a fruitful line of research in the field of recommendation, since its ability to extract self-supervised signals from the raw data is well-aligned with recommender systems' needs for tackling the data sparsity issue.
no code implementations • 16 Dec 2021 • Tong Chen, Zhan Ma
Deep neural network-based image compression has been extensively studied.
no code implementations • 30 Nov 2021 • Tong Chen, Sheng Wang
With the increasingly available large-scale cancer genomics datasets, machine learning approaches have played an important role in revealing novel insights into cancer development.
no code implementations • 21 Oct 2021 • Shijie Zhang, Hongzhi Yin, Tong Chen, Zi Huang, Quoc Viet Hung Nguyen, Lizhen Cui
Evaluations on two real-world datasets show that 1) our attack model significantly boosts the exposure rate of the target item in a stealthy way, without harming the accuracy of the poisoned recommender; and 2) existing defenses are not effective enough, highlighting the need for new defenses against our local model poisoning attacks to federated recommender systems.
1 code implementation • NeurIPS 2021 • Jiefeng Li, Tong Chen, Ruiqi Shi, Yujing Lou, Yong-Lu Li, Cewu Lu
In this work, we propose sampling-argmax, a differentiable training method that imposes implicit constraints to the shape of the probability map by minimizing the expectation of the localization error.
Ranked #167 on 3D Human Pose Estimation on Human3.6M
no code implementations • 14 Sep 2021 • Yuandong Wang, Hongzhi Yin, Lian Wu, Tong Chen, Chunyang Liu
In recent years, online ride-hailing platforms have become an indispensable part of urban transportation.
no code implementations • 25 Aug 2021 • Yang Li, Tong Chen, Peng-Fei Zhang, Hongzhi Yin
Modern deep neural networks (DNNs) have greatly facilitated the development of sequential recommender systems by achieving state-of-the-art recommendation performance on various sequential recommendation tasks.
no code implementations • 4 Jul 2021 • Yang Li, Tong Chen, Zi Huang
As a result, this creates a severe bottleneck when we are trying to advance the recommendation accuracy and generating fine-grained explanations since the explicit attributes have only loose connections to the actual recommendation process.
no code implementations • 2 Jul 2021 • Ruihong Qiu, Zi Huang, Tong Chen, Hongzhi Yin
According to our analysis, existing positional encoding schemes are generally forward-aware only, which can hardly represent the dynamics of the intention in a session.
no code implementations • 30 Jun 2021 • Yang Li, Tong Chen, Yadan Luo, Hongzhi Yin, Zi Huang
Furthermore, the sparse POI-POI transitions restrict the ability of a model to learn effective sequential patterns for recommendation.
no code implementations • 4 Jun 2021 • Tong Chen, Hongzhi Yin, Yujia Zheng, Zi Huang, Yang Wang, Meng Wang
The core idea is to compose elastic embeddings for each item, where an elastic embedding is the concatenation of a set of embedding blocks that are carefully chosen by an automated search function.
no code implementations • 11 May 2021 • Xuhui Ren, Hongzhi Yin, Tong Chen, Hao Wang, Zi Huang, Kai Zheng
Hence, the ability to generate suitable clarifying questions is the key to timely tracing users' dynamic preferences and achieving successful recommendations.
no code implementations • 7 May 2021 • Lei Guo, Li Tang, Tong Chen, Lei Zhu, Quoc Viet Hung Nguyen, Hongzhi Yin
Shared-account Cross-domain Sequential recommendation (SCSR) is the task of recommending the next item based on a sequence of recorded user behaviors, where multiple users share a single account, and their behaviours are available in multiple domains.
no code implementations • 5 Apr 2021 • Tong Chen, Hongzhi Yin, Xiangliang Zhang, Zi Huang, Yang Wang, Meng Wang
As a well-established approach, factorization machine (FM) is capable of automatically learning high-order interactions among features to make predictions without the need for manual feature engineering.
no code implementations • 4 Apr 2021 • Tong Chen, Hongzhi Yin, Jie Ren, Zi Huang, Xiangliang Zhang, Hao Wang
In WIDEN, we propose a novel inductive, meta path-free message passing scheme that packs up heterogeneous node features with their associated edges from both low- and high-order neighbor nodes.
no code implementations • 2 Apr 2021 • Qinyong Wang, Hongzhi Yin, Tong Chen, Junliang Yu, Alexander Zhou, Xiangliang Zhang
In the mobile Internet era, the recommender system has become an irreplaceable tool to help users discover useful items, and thus alleviating the information overload problem.
no code implementations • 24 Mar 2021 • Lei Guo, Hongzhi Yin, Tong Chen, Xiangliang Zhang, Kai Zheng
However, the representation learning for a group is most complex beyond the fusion of group member representation, as the personal preferences and group preferences may be in different spaces.
no code implementations • 29 Jan 2021 • Shijie Zhang, Hongzhi Yin, Tong Chen, Zi Huang, Lizhen Cui, Xiangliang Zhang
Specifically, in GERAI, we bind the information perturbation mechanism in differential privacy with the recommendation capability of graph convolutional networks.
no code implementations • 22 Jan 2021 • Tong Chen, Sirou Zhu, Yiming Wen, Zhaomin Zheng
Knowledge Graph Completion is a task of expanding the knowledge graph/base through estimating possible entities, or proper nouns, that can be connected using a set of predefined relations, or verb/predicates describing interconnections of two things.
1 code implementation • 13 Jan 2021 • Tong Chen, Jean-Bernard Lasserre, Victor Magron, Edouard Pauwels
We introduce a sublevel Moment-SOS hierarchy where each SDP relaxation can be viewed as an intermediate (or interpolation) between the d-th and (d+1)-th order SDP relaxations of the Moment-SOS hierarchy (dense or sparse version).
Combinatorial Optimization Optimization and Control
no code implementations • 8 Jan 2021 • Guanhua Ye, Hongzhi Yin, Tong Chen, Hongxu Chen, Lizhen Cui, Xiangliang Zhang
Obstructive Sleep Apnea (OSA) is a highly prevalent but inconspicuous disease that seriously jeopardizes the health of human beings.
no code implementations • 4 Jan 2021 • Yuandong Wang, Hongzhi Yin, Tong Chen, Chunyang Liu, Ben Wang, Tianyu Wo, Jie Xu
Consequently, the spatiotemporal passenger demand records naturally carry dynamic patterns in the constructed graphs, where the edges also encode important information about the directions and volume (i. e., weights) of passenger demands between two connected regions.
no code implementations • 1 Jan 2021 • Jin Zhang, Jianhao Wang, Hao Hu, Tong Chen, Yingfeng Chen, Changjie Fan, Chongjie Zhang
Deep reinforcement learning algorithms generally require large amounts of data to solve a single task.
no code implementations • 1 Dec 2020 • Ming Lu, Tong Chen, Dandan Ding, Fengqing Zhu, Zhan Ma
Inspired by the facts that retinal cells actually segregate the visual scene into different attributes (e. g., spatial details, temporal motion) for respective neuronal processing, we propose to first decompose the input video into respective spatial texture frames (STF) at its native spatial resolution that preserve the rich spatial details, and the other temporal motion frames (TMF) at a lower spatial resolution that retain the motion smoothness; then compress them together using any popular video coder; and finally synthesize decoded STFs and TMFs for high-fidelity video reconstruction at the same resolution as its native input.
1 code implementation • 19 Sep 2020 • Min Peng, Chongyang Wang, Yuan Gao, Tao Bi, Tong Chen, Yu Shi, Xiang-Dong Zhou
As a spontaneous expression of emotion on face, micro-expression reveals the underlying emotion that cannot be controlled by human.
1 code implementation • 19 Aug 2020 • Tian Jin, Gheorghe-Teodor Bercea, Tung D. Le, Tong Chen, Gong Su, Haruki Imai, Yasushi Negishi, Anh Leu, Kevin O'Brien, Kiyokuni Kawachiya, Alexandre E. Eichenberger
Deep neural network models are becoming increasingly popular and have been used in various tasks such as computer vision, speech recognition, and natural language processing.
1 code implementation • 6 Jul 2020 • Ruihong Qiu, Hongzhi Yin, Zi Huang, Tong Chen
On one hand, when a new session arrives, a session graph with a global attribute is constructed based on the current session and its associate user.
1 code implementation • 15 Jun 2020 • Jin Zhang, Jianhao Wang, Hao Hu, Tong Chen, Yingfeng Chen, Changjie Fan, Chongjie Zhang
Meta reinforcement learning (meta-RL) extracts knowledge from previous tasks and achieves fast adaptation to new tasks.
no code implementations • 2 Jun 2020 • Hongxu Chen, Hongzhi Yin, Xiangguo Sun, Tong Chen, Bogdan Gabrys, Katarzyna Musial
Moreover, to adapt the proposed method to be capable of handling large-scale social networks, we propose a two-phase space reconciliation mechanism to align the embedding spaces in both network partitioning based parallel training and account matching across different social networks.
no code implementations • 28 May 2020 • Tong Chen, Thomas Lumley
We show that a two-wave sampling with reasonable informative priors will end up with higher precision for the parameter of interest and be close to the underlying optimal design.
Applications
1 code implementation • 20 May 2020 • Shijie Zhang, Hongzhi Yin, Tong Chen, Quoc Viet Nguyen Hung, Zi Huang, Lizhen Cui
Therefore, it is of great practical significance to construct a robust recommender system that is able to generate stable recommendations even in the presence of shilling attacks.
no code implementations • 19 May 2020 • Tong Chen, Hongzhi Yin, Guanhua Ye, Zi Huang, Yang Wang, Meng Wang
Then, by treating attributes as the bridge between users and items, we can thoroughly model the user-item preferences (i. e., personalization) and item-item relationships (i. e., substitution) for recommendation.
2 code implementations • NeurIPS 2020 • Tong Chen, Jean-Bernard Lasserre, Victor Magron, Edouard Pauwels
The Lipschitz constant of a network plays an important role in many applications of deep learning, such as robustness certification and Wasserstein Generative Adversarial Network.
no code implementations • 13 Dec 2019 • Haojie Liu, Han Shen, Lichao Huang, Ming Lu, Tong Chen, Zhan Ma
Traditional video compression technologies have been developed over decades in pursuit of higher coding efficiency.
no code implementations • 7 Nov 2019 • Tong Chen, Hongzhi Yin, Quoc Viet Hung Nguyen, Wen-Chih Peng, Xue Li, Xiaofang Zhou
As a widely adopted solution, models based on Factorization Machines (FMs) are capable of modelling high-order interactions among features for effective sparse predictive analytics.
1 code implementation • 11 Oct 2019 • Tong Chen, Haojie Liu, Zhan Ma, Qiu Shen, Xun Cao, Yao Wang
This paper proposes a novel Non-Local Attention optmization and Improved Context modeling-based image compression (NLAIC) algorithm, which is built on top of the deep nerual network (DNN)-based variational auto-encoder (VAE) structure.
2 code implementations • 26 Sep 2019 • Jianqiang Wang, Hao Zhu, Zhan Ma, Tong Chen, Haojie Liu, Qiu Shen
This paper presents a novel end-to-end Learned Point Cloud Geometry Compression (a. k. a., Learned-PCGC) framework, to efficiently compress the point cloud geometry (PCG) using deep neural networks (DNN) based variational autoencoders (VAE).
no code implementations • 25 Sep 2019 • Woojeong Jin, He Jiang, Meng Qu, Tong Chen, Changlin Zhang, Pedro Szekely, Xiang Ren
We present Recurrent Event Network (RE-Net), a novel autoregressive architecture for modeling temporal sequences of multi-relational graphs (e. g., temporal knowledge graph), which can perform sequential, global structure inference over future time stamps to predict new events.
2 code implementations • IJCNLP 2019 • Cong Fu, Tong Chen, Meng Qu, Woojeong Jin, Xiang Ren
We propose a novel reinforcement learning framework to train two collaborative agents jointly, i. e., a multi-hop graph reasoner and a fact extractor.
no code implementations • 9 May 2019 • Di Zhao, Jiqiang Liu, Jialin Wang, Wenjia Niu, Endong Tong, Tong Chen, Gang Li
"Feint Attack" is simulated by the real attack inserted in the normal causal attack chain, and the addition of the real attack destroys the causal relationship of the original attack chain.
no code implementations • 22 Apr 2019 • Haojie Liu, Tong Chen, Peiyao Guo, Qiu Shen, Xun Cao, Yao Wang, Zhan Ma
This paper proposes a novel Non-Local Attention Optimized Deep Image Compression (NLAIC) framework, which is built on top of the popular variational auto-encoder (VAE) structure.
no code implementations • 8 Apr 2019 • Chao Huang, Haojie Liu, Tong Chen, Qiu Shen, Zhan Ma
We propose a MultiScale AutoEncoder(MSAE) based extreme image compression framework to offer visually pleasing reconstruction at a very low bitrate.
1 code implementation • 7 Apr 2019 • Min Peng, Chongyang Wang, Tao Bi, Tong Chen, Xiangdong Zhou, Yu Shi
As researchers working on such topics are moving to learn from the nature of micro-expression, the practice of using deep learning techniques has evolved from processing the entire video clip of micro-expression to the recognition on apex frame.
no code implementations • 29 Mar 2019 • Zehra Sura, Tong Chen, Hyojin Sung
Our method for utilizing the known structure of input data includes: (1) pre-processing the input data to expose relevant structures, and (2) constructing neural networks by incorporating the structure of the input data as an integral part of the network design.
no code implementations • 27 Feb 2019 • Haojie Liu, Tong Chen, Peiyao Guo, Qiu Shen, Zhan Ma
Besides, a field study on perceptual quality is also given via a dedicated subjective assessment, to compare the efficiency of our proposed methods and other conventional image compression methods.
1 code implementation • 6 Nov 2018 • Chongyang Wang, Min Peng, Tao Bi, Tong Chen
The existence of micro expression in small-local areas on face and limited size of available databases still constrain the recognition accuracy on such emotional facial behavior.
Micro Expression Recognition Micro-Expression Recognition +1
no code implementations • 18 Jul 2018 • Tong Chen, Wenjia Niu, Yingxiao Xiang, Xiaoxuan Bai, Jiqiang Liu, Zhen Han, Gang Li
In addition, we propose Gradient Band-based Adversarial Training, which trained with a single randomly choose dominant adversarial example without taking any modification, to realize the "1:N" attack immunity for generalized dominant adversarial examples.
1 code implementation • 13 Jun 2018 • Binbing Liao, Jingqing Zhang, Chao Wu, Douglas McIlwraith, Tong Chen, Shengwen Yang, Yike Guo, Fei Wu
Predicting traffic conditions from online route queries is a challenging task as there are many complicated interactions over the roads and crowds involved.
Ranked #1 on Traffic Prediction on Q-Traffic
1 code implementation • 5 Jun 2018 • Haojie Liu, Tong Chen, Qiu Shen, Tao Yue, Zhan Ma
We present a lossy image compression method based on deep convolutional neural networks (CNNs), which outperforms the existing BPG, WebP, JPEG2000 and JPEG as measured via multi-scale structural similarity (MS-SSIM), at the same bit rate.
no code implementations • 14 Oct 2017 • Tong Chen, Lin Wu, Yang Wang, Jun Zhang, Hongxu Chen, Xue Li
Inspired by point process in modeling temporal point process, in this paper we present a deep prediction method based on two recurrent neural networks (RNNs) to jointly model each user's continuous browsing history and asynchronous event sequences in the context of inter-user behavioral mutual infectivity.
no code implementations • 20 Apr 2017 • Tong Chen, Lin Wu, Xue Li, Jun Zhang, Hongzhi Yin, Yang Wang
The proposed model delves soft-attention into the recurrence to simultaneously pool out distinct features with particular focus and produce hidden representations that capture contextual variations of relevant posts over time.
no code implementations • 26 May 2016 • Chongyang Wang, Ming Peng, Lingfeng Xu, Tong Chen
Palm vein recognition is a novel biometric identification technology.