no code implementations • 28 May 2024 • Zhuonan Zheng, Yuanchen Bei, Sheng Zhou, Yao Ma, Ming Gu, Hongjia Xu, Chengyu Lai, Jiawei Chen, Jiajun Bu
Based on HTMP and empirical analysis, we reveal that the success of message passing in existing HTGNNs is attributed to implicitly enhancing the compatibility matrix among classes.
no code implementations • 6 May 2024 • Qinyu Chen, Kwantae Kim, Chang Gao, Sheng Zhou, Taekwang Jang, Tobi Delbruck, Shih-Chii Liu
This paper introduces, to the best of the authors' knowledge, the first fine-grained temporal sparsity-aware keyword spotting (KWS) IC leveraging temporal similarities between neighboring feature vectors extracted from input frames and network hidden states, eliminating unnecessary operations and memory accesses.
no code implementations • 25 Apr 2024 • Yuanchen Bei, Sheng Zhou, Jinke Shi, Yao Ma, Haishuai Wang, Jiajun Bu
Recent advances have utilized Graph Neural Networks (GNNs) to learn effective node representations by aggregating information from neighborhoods.
no code implementations • 18 Apr 2024 • Siyi Lin, Chongming Gao, Jiawei Chen, Sheng Zhou, Binbin Hu, Chun Chen, Can Wang
Building on these insights, we propose a novel debiasing strategy that leverages a spectral norm regularizer to penalize the magnitude of the principal singular value.
1 code implementation • 18 Apr 2024 • Sirui Chen, Jiawei Chen, Sheng Zhou, Bohao Wang, Shen Han, Chanfei Su, Yuqing Yuan, Can Wang
Integrating both positive and negative feedback to form a signed graph can lead to a more comprehensive understanding of user preferences.
no code implementations • 22 Mar 2024 • Yukuan Jia, Jiawen Zhang, Shimeng Lu, Baokang Fan, Ruiqing Mao, Sheng Zhou, Zhisheng Niu
Environmental perception in Automated Valet Parking (AVP) has been a challenging task due to severe occlusions in parking garages.
1 code implementation • 20 Feb 2024 • Bohao Wang, Jiawei Chen, Changdong Li, Sheng Zhou, Qihao Shi, Yang Gao, Yan Feng, Chun Chen, Can Wang
DR-GNN addresses two core challenges: 1) To enable DRO to cater to graph data intertwined with GNN, we reinterpret GNN as a graph smoothing regularizer, thereby facilitating the nuanced application of DRO; 2) Given the typically sparse nature of recommendation data, which might impede robust optimization, we introduce slight perturbations in the training distribution to expand its support.
1 code implementation • 8 Feb 2024 • Meihan Liu, Zeyu Fang, Zhen Zhang, Ming Gu, Sheng Zhou, Xin Wang, Jiajun Bu
Motivated by our empirical analysis, we reevaluate the role of GNNs in graph domain adaptation and uncover the pivotal role of the propagation process in GNNs for adapting to different graph domains.
no code implementations • 3 Feb 2024 • Hongjia Xu, Liangliang Zhang, Yao Ma, Sheng Zhou, Zhuonan Zheng, Bu Jiajun
Analytics on large-scale graphs have posed significant challenges to computational efficiency and resource requirements.
1 code implementation • 26 Jan 2024 • Hao Chen, Yuanchen Bei, Qijie Shen, Yue Xu, Sheng Zhou, Wenbing Huang, Feiran Huang, Senzhang Wang, Xiao Huang
Predicting Click-Through Rate (CTR) in billion-scale recommender systems poses a long-standing challenge for Graph Neural Networks (GNNs) due to the overwhelming computational complexity involved in aggregating billions of neighbors.
no code implementations • 18 Jan 2024 • Tan Chen, Jintao Yan, Yuxuan Sun, Sheng Zhou, Deniz Gündüz, Zhisheng Niu
Hierarchical federated learning (HFL) enables distributed training of models across multiple devices with the help of several edge servers and a cloud edge server in a privacy-preserving manner.
no code implementations • 14 Dec 2023 • Xi Chen, Chang Gao, Zuowen Wang, Longbiao Cheng, Sheng Zhou, Shih-Chii Liu, Tobi Delbruck
Implementing online training of RNNs on the edge calls for optimized algorithms for an efficient deployment on hardware.
no code implementations • 9 Dec 2023 • Yuanchen Bei, Sheng Zhou, Qiaoyu Tan, Hao Xu, Hao Chen, Zhao Li, Jiajun Bu
To address these issues, we utilize the advantages of reinforcement learning in adaptively learning in complex environments and propose a novel method that incorporates Reinforcement neighborhood selection for unsupervised graph ANomaly Detection (RAND).
no code implementations • 13 Oct 2023 • Sheng Zhou, Dan Guo, Jia Li, Xun Yang, Meng Wang
The associations between these repetitive objects are superfluous for answer reasoning; (2) two spatially distant OCR tokens detected in the image frequently have weak semantic dependencies for answer reasoning; and (3) the co-existence of nearby objects and tokens may be indicative of important visual cues for predicting answers.
no code implementations • 22 Sep 2023 • Huixuan Chi, Hao Xu, Mengya Liu, Yuanchen Bei, Sheng Zhou, Danyang Liu, Mengdi Zhang
(2) spatiotemporal collaborative signal, which indicates similar users have similar preferences at specific locations and times.
1 code implementation • 13 Aug 2023 • Zijie Song, Jiawei Chen, Sheng Zhou, Qihao Shi, Yan Feng, Chun Chen, Can Wang
In recommendation systems (RS), user behavior data is observational rather than experimental, resulting in widespread bias in the data.
1 code implementation • 10 Aug 2023 • Ming Gu, Gaoming Yang, Sheng Zhou, Ning Ma, Jiawei Chen, Qiaoyu Tan, Meihan Liu, Jiajun Bu
Graph clustering is a fundamental task in graph analysis, and recent advances in utilizing graph neural networks (GNNs) have shown impressive results.
1 code implementation • 9 Aug 2023 • Chunpeng Zhou, Kangjie Ning, Haishuai Wang, Zhi Yu, Sheng Zhou, Jiajun Bu
To address these challenges, we introduce a novel methodology for the subgrade distress detection task by leveraging the multi-view information from 3D-GPR data.
no code implementations • 18 Jul 2023 • Xiufeng Huang, Sheng Zhou
To improve the performance of multi-agent reinforcement learning under the constraint of wireless resources, we propose a message importance metric and design an importance-aware scheduling policy to effectively exchange messages.
Multi-agent Reinforcement Learning reinforcement-learning +1
no code implementations • 6 Jul 2023 • Yuanchen Bei, Hao Xu, Sheng Zhou, Huixuan Chi, Haishuai Wang, Mengdi Zhang, Zhao Li, Jiajun Bu
Dynamic graph data mining has gained popularity in recent years due to the rich information contained in dynamic graphs and their widespread use in the real world.
no code implementations • 19 Jun 2023 • Tan Chen, Jintao Yan, Yuxuan Sun, Sheng Zhou, Deniz Gunduz, Zhisheng Niu
Federated learning enables distributed training of machine learning (ML) models across multiple devices in a privacy-preserving manner.
1 code implementation • NeurIPS 2023 • Zhiyao Zhou, Sheng Zhou, Bochao Mao, Xuanyi Zhou, Jiawei Chen, Qiaoyu Tan, Daochen Zha, Yan Feng, Chun Chen, Can Wang
Moreover, we observe that the learned graph structure demonstrates a strong generalization ability across different GNN models, despite the high computational and space consumption.
no code implementations • 25 Feb 2023 • Yukuan Jia, Ruiqing Mao, Yuxuan Sun, Sheng Zhou, Zhisheng Niu
Specifically, we design a mobility-aware sensor scheduling (MASS) algorithm based on the restless multi-armed bandit (RMAB) theory to maximize the expected average perception gain.
no code implementations • 20 Feb 2023 • Sheng Zhou, Pierre Blanchart, Michel Crucianu, Marin Ferecatu
In this paper we present a heuristic method to provide individual explanations for those elements in a dataset (data points) which are wrongly predicted by a given classifier.
2 code implementations • 9 Feb 2023 • Jiawei Chen, Junkang Wu, Jiancan Wu, Sheng Zhou, Xuezhi Cao, Xiangnan He
Recent years have witnessed the great successes of embedding-based methods in recommender systems.
no code implementations • 30 Jan 2023 • Yaodan Xu, Jingzhou Sun, Sheng Zhou, Zhisheng Niu
In particular, parallel computing resources on the platforms, such as graphics processing units (GPUs), have higher computational and energy efficiency with larger batch sizes.
no code implementations • 28 Dec 2022 • Qihao Shi, Bingyang Fu, Can Wang, Jiawei Chen, Sheng Zhou, Yan Feng, Chun Chen
The approximation ratio of the algorithm depends both on the number of the removed elements and the network topology.
no code implementations • 7 Dec 2022 • Bowen Xie, Yuxuan Sun, Sheng Zhou, Zhisheng Niu, Yang Xu, Jingran Chen, Deniz Gündüz
Federated learning (FL) is a promising approach to enable the future Internet of vehicles consisting of intelligent connected vehicles (ICVs) with powerful sensing, computing and communication capabilities.
1 code implementation • 27 Nov 2022 • Gang Chen, Jiawei Chen, Fuli Feng, Sheng Zhou, Xiangnan He
Traditional solutions first train a full teacher model from the training data, and then transfer its knowledge (\ie \textit{soft labels}) to supervise the learning of a compact student model.
1 code implementation • 8 Nov 2022 • Dian Qin, Haishuai Wang, Zhe Liu, Hongjia Xu, Sheng Zhou, Jiajun Bu
Since the distilled 2D networks are supervised by the curves converted from dimensionally heterogeneous 3D features, the 2D networks are given an informative view in terms of learning structural information embedded in well-trained high-dimensional representations.
no code implementations • 27 Oct 2022 • Yuxuan Sun, Bowen Xie, Sheng Zhou, Zhisheng Niu
Accordingly, base stations (BSs) and edge servers (ESs) need to be densely deployed, leading to huge deployment and operation costs, in particular the energy costs.
1 code implementation • 29 Aug 2022 • Jingru Li, Sheng Zhou, Liangcheng Li, Haishuai Wang, Zhi Yu, Jiajun Bu
Besides, CuDFKD adapts the generation target dynamically according to the status of student model.
1 code implementation • 15 Jul 2022 • Ruiqing Mao, Jingyu Guo, Yukuan Jia, Yuxuan Sun, Sheng Zhou, Zhisheng Niu
In this work, we release DOLPHINS: Dataset for cOllaborative Perception enabled Harmonious and INterconnected Self-driving, as a new simulated large-scale various-scenario multi-view multi-modality autonomous driving dataset, which provides a ground-breaking benchmark platform for interconnected autonomous driving.
1 code implementation • 15 Jun 2022 • Sheng Zhou, Hongjia Xu, Zhuonan Zheng, Jiawei Chen, Zhao Li, Jiajun Bu, Jia Wu, Xin Wang, Wenwu Zhu, Martin Ester
Motivated by the tremendous success of deep learning in clustering, one of the most fundamental machine learning tasks, and the large number of recent advances in this direction, in this paper we conduct a comprehensive survey on deep clustering by proposing a new taxonomy of different state-of-the-art approaches.
no code implementations • 3 Jun 2022 • Wenqi Shi, Sheng Zhou, Zhisheng Niu, Miao Jiang, Lu Geng
To deal with the coupled offloading and scheduling introduced by concurrent batch processing, we first consider an offline problem with a constant edge inference latency and the same latency constraint.
2 code implementations • 24 Apr 2022 • Chao Lin, Zhao Li, Sheng Zhou, Shichang Hu, Jialun Zhang, Linhao Luo, Jiarun Zhang, Longtao Huang, Yuan He
Virtual try-on(VTON) aims at fitting target clothes to reference person images, which is widely adopted in e-commerce. Existing VTON approaches can be narrowly categorized into Parser-Based(PB) and Parser-Free(PF) by whether relying on the parser information to mask the persons' clothes and synthesize try-on images.
no code implementations • 17 Feb 2022 • Yuxuan Sun, Sheng Zhou, Zhisheng Niu, Deniz Gündüz
In this work, we propose time-correlated sparsification with hybrid aggregation (TCS-H) for communication-efficient FEEL, which exploits jointly the power of model compression and over-the-air computation.
no code implementations • 12 Feb 2022 • Yukuan Jia, Ruiqing Mao, Yuxuan Sun, Sheng Zhou, Zhisheng Niu
Cooperative perception of connected vehicles comes to the rescue when the field of view restricts stand-alone intelligence.
no code implementations • 28 Dec 2021 • Can Wang, Zhe Wang, Defang Chen, Sheng Zhou, Yan Feng, Chun Chen
However, its effect on graph neural networks is less than satisfactory since the graph topology and node attributes are likely to change in a dynamic way and in this case a static teacher model is insufficient in guiding student training.
no code implementations • 23 Sep 2021 • Yuxuan Sun, Fan Zhang, Junlin Zhao, Sheng Zhou, Zhisheng Niu, Deniz Gündüz
In this work, we consider a multi-master heterogeneous-worker distributed computing scenario, where multiple matrix multiplication tasks are encoded and allocated to workers for parallel computation.
no code implementations • 16 Sep 2021 • Zihao Zhao, Jiawei Chen, Sheng Zhou, Xiangnan He, Xuezhi Cao, Fuzheng Zhang, Wei Wu
To sufficiently exploit such important information for recommendation, it is essential to disentangle the benign popularity bias caused by item quality from the harmful popularity bias caused by conformity.
1 code implementation • 23 Aug 2021 • Dian Qin, Jiajun Bu, Zhe Liu, Xin Shen, Sheng Zhou, Jingjun Gu, Zhijua Wang, Lei Wu, Huifen Dai
To deal with this problem, we propose an efficient architecture by distilling knowledge from well-trained medical image segmentation networks to train another lightweight network.
1 code implementation • ICCV 2021 • Sheng Zhou, Yucheng Wang, Defang Chen, Jiawei Chen, Xin Wang, Can Wang, Jiajun Bu
The holistic knowledge is represented as a unified graph-based embedding by aggregating individual knowledge from relational neighborhood samples with graph neural networks, the student network is learned by distilling the holistic knowledge in a contrastive manner.
no code implementations • 14 Jul 2021 • Ning Ma, Jiajun Bu, Zhen Zhang, Sheng Zhou
Present domain adaptation methods usually perform explicit representation alignment by simultaneously accessing the source data and target data.
no code implementations • 14 Jul 2021 • Ning Ma, Jiajun Bu, Lixian Lu, Jun Wen, Zhen Zhang, Sheng Zhou, Xifeng Yan
Domain Adaptation has been widely used to deal with the distribution shift in vision, language, multimedia etc.
no code implementations • 31 May 2021 • Yuxuan Sun, Sheng Zhou, Zhisheng Niu, Deniz Gündüz
In this work, we consider an over-the-air FEEL system with analog gradient aggregation, and propose an energy-aware dynamic device scheduling algorithm to optimize the training performance under energy constraints of devices, where both communication energy for gradient aggregation and computation energy for local training are included.
1 code implementation • 16 Nov 2020 • Can Wang, Jiawei Chen, Sheng Zhou, Qihao Shi, Yan Feng, Chun Chen
However, the social network information may not be available in many recommender systems, which hinders application of SamWalker.
no code implementations • 16 Nov 2020 • Jiawei Chen, Chengquan Jiang, Can Wang, Sheng Zhou, Yan Feng, Chun Chen, Martin Ester, Xiangnan He
To deal with these problems, we propose an efficient and effective collaborative sampling method CoSam, which consists of: (1) a collaborative sampler model that explicitly leverages user-item interaction information in sampling probability and exhibits good properties of normalization, adaption, interaction information awareness, and sampling efficiency; and (2) an integrated sampler-recommender framework, leveraging the sampler model in prediction to offset the bias caused by uneven sampling.
no code implementations • 3 Aug 2020 • Ruichen Jiang, Sheng Zhou
To mitigate wireless fading, we further propose a cluster-based system and design the relay selection scheme based on the normalized detection SNR.
no code implementations • 14 Jul 2020 • Wenqi Shi, Sheng Zhou, Zhisheng Niu, Miao Jiang, Lu Geng
Then, a greedy device scheduling algorithm is introduced, which in each step selects the device consuming the least updating time obtained by the optimal bandwidth allocation, until the lower bound begins to increase, meaning that scheduling more devices will degrade the model accuracy.
no code implementations • 25 May 2020 • Xiufeng Huang, Sheng Zhou
To reduce the communication cost, lossy data compression can be exploited for inference tasks, but may bring more erroneous inference results.
no code implementations • 18 Mar 2020 • Ning Ma, Jiajun Bu, Jieyu Yang, Zhen Zhang, Chengwei Yao, Zhi Yu, Sheng Zhou, Xifeng Yan
The shared sub-structures between training classes and test classes are essential in few-shot graph classification.
no code implementations • 4 Mar 2020 • Jiawei Chen, Can Wang, Sheng Zhou, Qihao Shi, Jingbang Chen, Yan Feng, Chun Chen
A popular and effective approach for implicit recommendation is to treat unobserved data as negative but downweight their confidence.
no code implementations • 30 Jan 2020 • Sheng Zhou, Xinjiang Wang, Ping Luo, Litong Feng, Wenjie Li, Wei zhang
This phenomenon is caused by the normalization effect of BN, which induces a non-trainable region in the parameter space and reduces the network capacity as a result.
no code implementations • 3 Nov 2019 • Wenqi Shi, Sheng Zhou, Zhisheng Niu
In each iteration of FL (called round), the edge devices update local models based on their own data and contribute to the global training by uploading the model updates via wireless channels.
no code implementations • 1 Nov 2019 • Yuxuan Sun, Sheng Zhou, Deniz Gündüz
In this work, we consider analog aggregation to scale down the communication cost with respect to the number of workers, and introduce data redundancy to the system to deal with non-i. i. d.
1 code implementation • 8 Mar 2019 • Wenqi Shi, Yunzhong Hou, Sheng Zhou, Zhisheng Niu, Yang Zhang, Lu Geng
Since the output data size of a DNN layer can be larger than that of the raw data, offloading intermediate data between layers can suffer from high transmission latency under limited wireless bandwidth.
no code implementations • 6 Mar 2019 • Zhiyuan Jiang, Sheng Zhou, Zhisheng Niu
Future wireless access networks need to support diversified quality of service (QoS) metrics required by various types of Internet-of-Things (IoT) devices, e. g., age of information (AoI) for status generating sources and ultra low latency for safety information in vehicular networks.
2 code implementations • 31 Jan 2019 • Sheng Zhou, Jiajun Bu, Xin Wang, Jia-Wei Chen, Can Wang
Second, given a meta path, nodes in HIN are connected by path instances while existing works fail to fully explore the differences between path instances that reflect nodes' preferences in the semantic space.
no code implementations • 4 Dec 2018 • Sheng Chen, Zhiyuan Jiang, Sheng Zhou, Zhisheng Niu
In this paper, we propose a learning-based low-overhead beam alignment method for vehicle-to-infrastructure communication in vehicular networks.
no code implementations • 4 Dec 2018 • Zhiyuan Jiang, Ziyan He, Sheng Chen, Andreas F. Molisch, Sheng Zhou, Zhisheng Niu
Channel state information (CSI) is of vital importance in wireless communication systems.
no code implementations • 4 Dec 2018 • Ruichen Deng, Zhiyuan Jiang, Sheng Zhou, Shuguang Cui, Zhisheng Niu
Timely and accurate knowledge of channel state information (CSI) is necessary to support scheduling operations at both physical and network layers.
no code implementations • 3 Dec 2018 • Zhiyuan Jiang, Sheng Chen, Andreas F. Molisch, Rath Vannithamby, Sheng Zhou, Zhisheng Niu
Knowledge of information about the propagation channel in which a wireless system operates enables better, more efficient approaches for signal transmissions.
no code implementations • 17 Nov 2015 • Huimin Pan, Jingchu Liu, Sheng Zhou, Zhisheng Niu
Based on these characteristics, we propose a \emph{Block Regression} ({BR}) model for mobile traffic forecasting.