arXiv subjects

Dongsheng Chen

Publications and source records attributed to Dongsheng Chen.

27 records · Page 2Linked to original sources

arXiv2023

NIPD: A Federated Learning Person Detection Benchmark Based on Real-World Non-IID Data

Federated learning (FL), a privacy-preserving distributed machine learning, has been rapidly applied in wireless communication networks. FL enables Internet of Things (IoT) clients to obtain well-trained models while preventing privacy leakage. Person detection can be deployed on edge devices with limited computing power if combined with FL to process the video data directly at the edge. However, due to the different hardware and deployment scenarios of different cameras, the data collected by the camera present non-independent and identically distributed (non-IID), and the global model derived from FL aggregation is less effective. Meanwhile, existing research lacks public data set for real-world FL object detection, which is not conducive to studying the non-IID problem on IoT cameras. Therefore, we open source a non-IID IoT person detection (NIPD) data set, which is collected from five different cameras. To our knowledge, this is the first true device-based non-IID person detection data set. Based on this data set, we explain how to establish a FL experimental platform and provide a benchmark for non-IID person detection. NIPD is expected to promote the application of FL and the security of smart city.

cs.CV↗

arXiv2023

TLAG: An Informative Trigger and Label-Aware Knowledge Guided Model for Dialogue-based Relation Extraction

Dialogue-based Relation Extraction (DRE) aims to predict the relation type of argument pairs that are mentioned in dialogue. The latest trigger-enhanced methods propose trigger prediction tasks to promote DRE. However, these methods are not able to fully leverage the trigger information and even bring noise to relation extraction. To solve these problems, we propose TLAG, which fully leverages the trigger and label-aware knowledge to guide the relation extraction. First, we design an adaptive trigger fusion module to fully leverage the trigger information. Then, we introduce label-aware knowledge to further promote our model's performance. Experimental results on the DialogRE dataset show that our TLAG outperforms the baseline models, and detailed analyses demonstrate the effectiveness of our approach.

cs.CL↗

arXiv2022

LiteVL: Efficient Video-Language Learning with Enhanced Spatial-Temporal Modeling

Recent large-scale video-language pre-trained models have shown appealing performance on various downstream tasks. However, the pre-training process is computationally expensive due to the requirement of millions of video-text pairs and the redundant data structure of each video. To mitigate these problems, we propose LiteVL, which adapts a pre-trained image-language model BLIP into a video-text model directly on downstream tasks, without heavy pre-training. To enhance the temporal modeling lacking in the image-language model, we propose to add temporal attention modules in the image encoder of BLIP with dynamic temporal scaling. Besides the model-wise adaptation, we also propose a non-parametric pooling mechanism to adaptively reweight the fine-grained video embedding conditioned on the text. Experimental results on text-video retrieval and video question answering show that the proposed LiteVL even outperforms previous video-language pre-trained models by a clear margin, though without any video-language pre-training.

cs.CV↗

arXiv2022

Secure Rate-Splitting for MIMO Broadcast Channel with Imperfect CSIT and a Jammer

In this paper, we investigate the secure rate-splitting for the two-user multiple-input multiple-output (MIMO) broadcast channel with imperfect channel state information at the transmitter (CSIT) and a multiple-antenna jammer, where each receiver has an equal number of antennas and the jammer has perfect channel state information (CSI). Specifically, we design a secure rate-splitting multiple-access strategy, where the security of split private and common messages is ensured by precoder design with joint nulling and aligning the leakage information, regarding different antenna configurations. Moreover, we show that the sum-secure degrees-of-freedom (SDoF) achieved by secure rate-splitting is optimal and outperforms that by conventional zero-forcing. Therefore, we reveal the sum-SDoF of the two-user MIMO broadcast channel with imperfect CSIT and a jammer, and validate the superiority of rate-splitting for the security purpose in this scenario with emphasis of MIMO.

cs.IT↗

arXiv2022

Energy-Efficient UAV-Sensor Data Harvesting: Dynamic Adaptive Modulation and Height Control

Leveraging unmanned aerial vehicle (UAV) is convenient to collect data from ground sensor. However, in the presence of unknown urban environment, the data collection is subject to the blockage of urban buildings. In this paper, considering the urban environment during flight, we propose dynamic adaptive modulation and height control for UAV-sensor data harvesting in urban areas. In each time slot, the modulation format and flight height are selected based on current system states, with the aim of minimizing the expected transmission energy of sensor under data volume and flight height constraints. The dynamic adaptive modulation and height control problem is formulated as constrained finite-horizon Markov decision processes (CMDP), which can be solved by backward induction algorithm. The advantage of proposed joint design over modulation selection only is illustrated via the computer simulations, where 48.23% expected transmission energy can be saved for ground sensor.

eess.SP↗

arXiv2021

Towards Joint Intent Detection and Slot Filling via Higher-order Attention

Intent detection (ID) and Slot filling (SF) are two major tasks in spoken language understanding (SLU). Recently, attention mechanism has been shown to be effective in jointly optimizing these two tasks in an interactive manner. However, latest attention-based works concentrated only on the first-order attention design, while ignoring the exploration of higher-order attention mechanisms. In this paper, we propose a BiLinear attention block, which leverages bilinear pooling to simultaneously exploit both the contextual and channel-wise bilinear attention distributions to capture the second-order interactions between the input intent or slot features. Higher and even infinity order interactions are built by stacking numerous blocks and assigning Exponential Linear Unit (ELU) to blocks. Before the decoding stage, we introduce the Dynamic Feature Fusion Layer to implicitly fuse intent and slot information in a more effective way. Technically, instead of simply concatenating intent and slot features, we first compute two correlation matrices to weight on two features. Furthermore, we present Higher-order Attention Network for the SLU tasks. Experiments on two benchmark datasets show that our approach yields improvements compared with the state-of-the-art approach. We also provide discussion to demonstrate the effectiveness of the proposed approach.

cs.CL↗

arXiv2021

HAN: Higher-order Attention Network for Spoken Language Understanding

Spoken Language Understanding (SLU), including intent detection and slot filling, is a core component in human-computer interaction. The natural attributes of the relationship among the two subtasks make higher requirements on fine-grained feature interaction, i.e., the token-level intent features and slot features. Previous works mainly focus on jointly modeling the relationship between the two subtasks with attention-based models, while ignoring the exploration of attention order. In this paper, we propose to replace the conventional attention with our proposed Bilinear attention block and show that the introduced Higher-order Attention Network (HAN) brings improvement for the SLU task. Importantly, we conduct wide analysis to explore the effectiveness brought from the higher-order attention.

cs.CL↗

arXiv2021

Directly Visualizing the Crossover from Incoherent to Coherent Phonons in Two-dimensional Periodic MoS2/MoSe2 Arrayed Heterostructure

Recently, massive efforts have been done on controlling thermal transport via coherent phonons in the various periodic nanostructures. However, the intrinsic lattice difference between the constituent materials inevitably generates the disorder at the interfaces, thus limiting the opportunity of directly observing the coherent phonon transport. Here, we investigate the controllability and visualization of the coherent phonon transport in a periodic MoS2/MoSe2 arrayed heterostructure with minimum lattice mismatching using non-equilibrium molecular dynamics simulation. It is found that the coherent phonon transport can be destroyed and rebuilt through adjusting the density of MoSe2 nanodot arrays. The phonon localization induced by the destruction of correlation is visualized based on the spatial energy distribution and anharmonic analysis. Furthermore, the eigen vector diagrams provide a distinct visualization of the localized phonon modes. Besides, the correlation of phonon can be rebuilt by reducing the period length, which is verified by the enhanced group velocities extracted from phonon dispersion curves. Interestingly, the crossover from incoherent to coherent phonon transport is directly observed by the spatial energy distributions and the spectral phonon transmission coefficients. Finally, the size and temperature dependence of thermal conductivity are also discussed. This study of the phonon coherence and its visualizing manipulation on thermal conductivity will be beneficial to fine heat control and management in the real applications.

cond-mat.mes-hall↗

arXiv2018

Dimensional crossover of heat conduction in amorphous Polyimide nanofibers

The mechanism of thermal conductivity in amorphous polymers, especially polymer fibers, is unclear in comparison with that in inorganic materials. Here, we report the observation of across over of heat conduction behavior from three dimensions (3D) to quasi-one dimension (1D) in Polyimide(PI) nanofibers at a given temperature. A theoretical model based on the random walk theory has been proposed to quantitatively describe the interplay between the inter-chain hopping and the intra-chain hopping in nanofibers. This model explains well the diameter dependence of thermal conductivity and also speculates the upper limit of thermal conductivity of amorphous polymers in the quasi-1D limit.

physics.app-ph↗