Zimu Zhou

Last Name

Zhou

First Name

Zimu

ORCID

0000-0002-5457-6967

Show all metadata

Search Results

Publications 1 - 10 of 18

Preference-aware task assignment in on-demand taxi dispatching: an online stable matching approach
Zhao, Boming; Xu, Pan; Shi, Yexuan; et al. (2019)
Proceedings of the AAAI Conference on Artificial Intelligence
A central issue in on-demand taxi dispatching platforms is task assignment, which designs matching policies among dynamically arrived drivers (workers) and passengers (tasks). Previous matching policies maximize the profit of the platform without considering the preferences of workers and tasks (e.g., workers may prefer high-rewarding tasks while tasks may prefer nearby workers). Such ignorance of preferences impairs user experience and will decrease the profit of the platform in the long run. To address this problem, we propose preference-aware task assignment using online stable matching. Specifically, we define a new model, Online Stable Matching under Known Identical Independent Distributions (OSM-KIID). It not only maximizes the expected total profits (OBJ-1), but also tries to satisfy the preferences among workers and tasks by minimizing the expected total number of blocking pairs (OBJ-2). The model also features a practical arrival assumption validated on real-world dataset. Furthermore, we present a linear program based online algorithm LP-ALG, which achieves an online ratio of at least 1−1/e on OBJ-1 and has at most 0.6·|E| blocking pairs expectedly, where |E| is the total number of edges in the compatible graph. We also show that a natural Greedy can have an arbitrarily bad performance on OBJ-1 while maintaining around 0.5·|E| blocking pairs. Evaluations on both synthetic and real datasets confirm our theoretical analysis and demonstrate that LP-ALG strictly dominates all the baselines on both objectives when tasks notably outnumber workers.
SLADE: A smart large-scale task decomposer in crowdsourcing
Tong, Yongxin; Chen, Lei; Zhou, Zimu; et al. (2019)
2019 IEEE 35th International Conference on Data Engineering (ICDE)
Stitching Weight-Shared Deep Neural Networks for Efficient Multitask Inference on GPU
Wang, Zeyu; He, Xiaoxi; Zhou, Zimu; et al. (2022)
2022 19th Annual IEEE International Conference on Sensing, Communication, and Networking (SECON)
Intelligent personal and home applications demand multiple deep neural networks (DNNs) running on resource-constrained platforms for compound inference tasks, known as multitask inference. To fit multiple DNNs into low-resource devices, emerging techniques resort to weight sharing among DNNs to reduce their storage. However, such reduction in storage fails to translate into efficient execution on common accelerators such as GPUs. Most DNN graph rewriters are blind for multi-DNN optimization, while GPU vendors provide inefficient APIs for parallel multi-DNN execution at runtime. A few prior graph rewriters suggest cross-model graph fusion for low-latency multi-DNN execution. Yet they request duplication of the shared weights, erasing the memory saving of weight-shared DNNs. In this paper, we propose MTS, a novel graph rewriter for efficient multitask inference with weight-shared DNNs. MTS adopts a model stitching algorithm which outputs a single computational graph for weight-shared DNNs without duplicating any shared weight. MTS also utilizes a model grouping strategy to avoid overwhelming the GPU when co-running tens of DNNs. Extensive experiments show that MTS accelerates multitask inference by up to 6.0x compared to sequentially executing multiple weight-shared DNNs. MTS also yields up to 2.5x lower latency and 3.7x less memory usage compared with NETFUSE, a state-of-the-art multi-DNN graph rewriter.
Spatial crowdsourcing: a survey
Tong, Yongxin; Zhou, Zimu; Zeng, Yuxiang; et al. (2020)
The VLDB Journal
Latency-oriented task completion via spatial crowdsourcing
Zeng, Yuxiang; Tong, Yongxin; Chen, Lei; et al. (2018)
2018 IEEE 34th International Conference on Data Engineering (ICDE)
Spatio-Temporal Analysis and Prediction of Cellular Traffic in Metropolis
Wang, Xu; Zhou, Zimu; Xiao, Fu; et al. (2019)
IEEE Transactions on Mobile Computing
Localised Adaptive Spatial-Temporal Graph Neural Network
Duan, Wenying; He, Xiaoxi; Zhou, Zimu; et al. (2023)
KDD '23: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
Spatial-temporal graph models are prevailing for abstracting and modelling spatial and temporal dependencies. In this work, we ask the following question: whether and to what extent can we localise spatial-temporal graph models? We limit our scope to adaptive spatial-temporal graph neural networks (ASTGNNs), the state-of-the-art model architecture. Our approach to localisation involves sparsifying the spatial graph adjacency matrices. To this end, we propose Adaptive Graph Sparsification (AGS), a graph sparsification algorithm which successfully enables the localisation of ASTGNNs to an extreme extent (fully localisation). We apply AGS to two distinct ASTGNN architectures and nine spatial-temporal datasets. Intriguingly, we observe that spatial graphs in ASTGNNs can be sparsified by over 99.5% without any decline in test accuracy. Furthermore, even when ASTGNNs are fully localised, becoming graph-less and purely temporal, we record no drop in accuracy for the majority of tested datasets, with only minor accuracy deterioration observed in the remaining datasets. However, when the partially or fully localised ASTGNNs are reinitialised and retrained on the same data, there is a considerable and consistent drop in accuracy. Based on these observations, we reckon that (i) in the tested data, the information provided by the spatial dependencies is primarily included in the information provided by the temporal dependencies and, thus, can be essentially ignored for inference; and (ii) although the spatial dependencies provide redundant information, it is vital for the effective training of ASTGNNs and thus cannot be ignored during training. Furthermore, the localisation of ASTGNNs holds the potential to reduce the heavy computation overhead required on large-scale spatial-temporal data and further enable the distributed deployment of ASTGNNs.
A survey on sensor calibration in air pollution monitoring deployments
Maag, Balz; Zhou, Zimu; Thiele, Lothar (2018)
IEEE Internet of Things Journal
Adaptive Loss-Aware Quantization for Multi-Bit Networks
Qu, Zhongnan; Zhou, Zimu; Cheng, Yun; et al. (2020)
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
We investigate the compression of deep neural networks by quantizing their weights and activations into multiple binary bases, known as multi-bit networks (MBNs), which accelerate the inference and reduce the storage for the deployment on low-resource mobile and embedded platforms. We propose Adaptive Loss-aware Quantization (ALQ), a new MBN quantization pipeline that is able to achieve an average bitwidth below one-bit without notable loss in inference accuracy. Unlike previous MBN quantization solutions that train a quantizer by minimizing the error to reconstruct full precision weights, ALQ directly minimizes the quantization-induced error on the loss function involving neither gradient approximation nor full precision maintenance. ALQ also exploits strategies including adaptive bitwidth, smooth bitwidth reduction, and iterative trained quantization to allow a smaller network size without loss in accuracy. Experiment results on popular image datasets show that ALQ outperforms state-of-the-art compressed networks in terms of both storage and accuracy.
ICT: In-field Calibration Transfer for Air Quality Sensor Deployments
Cheng, Yun; He, Xiaoxi; Zhou, Zimu; et al. (2019)
Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
Recent years have witnessed a growing interest in urban air pollution monitoring, where hundreds of low-cost air quality sensors are deployed city-wide. To guarantee data accuracy and consistency, these sensors need periodic calibration after deployment. Since access to ground truth references is often limited in large-scale deployments, it is difficult to conduct city-wide post-deployment sensor calibration. In this work we propose In-field Calibration Transfer (ICT), a calibration scheme that transfers the calibration parameters of source sensors (with access to references) to target sensors (without access to references). On observing that (i) the distributions of ground truth in both source and target locations are similar and (ii) the transformation is approximately linear, ICT derives the transformation based on the similarity of distributions with a novel optimization formulation. The performance of ICT is further improved by exploiting spatial prediction of air quality levels and multi-source fusion. Experiments show that ICT is able to calibrate the target sensors as if they had direct access to the references.

Publications 1 - 10 of 18

Zimu Zhou

Last Name

First Name

ORCID

Organisational unit

Filters

Search Results