Author name cluster

Zimu Zhou

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

2 author rows

ICLR Conference 2024 Conference Paper

Graph-constrained diffusion for End-to-End Path Planning

Dingyuan Shi
Yongxin Tong
Zimu Zhou
Ke Xu 0001
Zheng Wang
Jieping Ye

Path planning underpins various applications such as transportation, logistics, and robotics. Conventionally, path planning is formulated with explicit optimization objectives such as distance or time. However, real-world data reveals that user intentions are hard-to-model, suggesting a need for data-driven path planning that implicitly incorporates the complex user intentions. In this paper, we propose GDP, a diffusion-based model for end-to-end data-driven path planning. It effectively learns path patterns via a novel diffusion process that incorporates constraints from road networks, and plans paths as conditional path generation given the origin and destination as prior evidence. GDP is the first solution that bypasses the traditional search-based frameworks, a long-standing performance bottleneck in path planning. We validate the efficacy of GDP on two real-world datasets. Our GDP beats strong baselines by 14.2% ~ 43.5% and achieves state-of-the-art performances.

Details

IS Journal 2021 Journal Article

Federated Topic Discovery: A Semantic Consistent Approach

Yexuan Shi
Yongxin Tong
Zhiyang Su
Di Jiang
Zimu Zhou
Wenbin Zhang

General-purpose topic models have widespread industrial applications. Yet high-quality topic modeling is becoming increasingly challenging because accurate models require large amounts of training data typically owned by multiple parties, who are often unwilling to share their sensitive data for collaborative training without guarantees on their data privacy. To enable effective privacy-preserving multiparty topic modeling, we propose a novel federated general-purpose topic model named private and consistent topic discovery (PC-TD). On the one hand, PC-TD seamlessly integrates differential privacy in topic modeling to provide privacy guarantees on sensitive data of different parties. On the other hand, PC-TD exploits multiple sources of semantic consistency information to retain the accuracy of topic modeling while protecting data privacy. We verify the effectiveness of PC-TD on real-life datasets. Experimental results demonstrate its superiority over the state-of-the-art general-purpose topic models.

Details DOI

AAAI Conference 2021 Conference Paper

RevMan: Revenue-aware Multi-task Online Insurance Recommendation

Yu Li
Yi Zhang
Lu Gan
Gengwei Hong
Zimu Zhou
Qiang Li

Online insurance is a new type of e-commerce with exponential growth. An effective recommendation model that maximizes the total revenue of insurance products listed in multiple customized sales scenarios is crucial for the success of online insurance business. Prior recommendation models are ineffective because they fail to characterize the complex relatedness of insurance products in multiple sales scenarios and maximize the overall conversion rate rather than the total revenue. Even worse, it is impractical to collect training data online for total revenue maximization due to the business logic of online insurance. We propose RevMan, a Revenueaware Multi-task Network for online insurance recommendation. RevMan adopts an adaptive attention mechanism to allow effective feature sharing among complex insurance products and sales scenarios. It also designs an efﬁcient ofﬂine learning mechanism to learn the rank that maximizes the expected total revenue, by reusing training data and model for conversion rate maximization. Extensive ofﬂine and online evaluations show that RevMan outperforms the state-of-theart recommendation systems for e-commerce.

PDF Details

AAAI Conference 2019 Conference Paper

Preference-Aware Task Assignment in On-Demand Taxi Dispatching: An Online Stable Matching Approach

Boming Zhao
Pan Xu
Yexuan Shi
Yongxin Tong
Zimu Zhou
Yuxiang Zeng

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.

PDF Details

NeurIPS Conference 2018 Conference Paper

Multi-Task Zipping via Layer-wise Neuron Sharing

Xiaoxi He
Zimu Zhou
Lothar Thiele

Future mobile devices are anticipated to perceive, understand and react to the world on their own by running multiple correlated deep neural networks on-device. Yet the complexity of these neural networks needs to be trimmed down both within-model and cross-model to fit in mobile storage and memory. Previous studies focus on squeezing the redundancy within a single neural network. In this work, we aim to reduce the redundancy across multiple models. We propose Multi-Task Zipping (MTZ), a framework to automatically merge correlated, pre-trained deep neural networks for cross-model compression. Central in MTZ is a layer-wise neuron sharing and incoming weight updating scheme that induces a minimal change in the error function. MTZ inherits information from each model and demands light retraining to re-boost the accuracy of individual tasks. Evaluations show that MTZ is able to fully merge the hidden layers of two VGG-16 networks with a 3. 18% increase in the test error averaged on ImageNet and CelebA, or share 39. 61% parameters between the two networks with <0. 5% increase in the test errors for both tasks. The number of iterations to retrain the combined network is at least 17. 8 times lower than that of training a single VGG-16 network. Moreover, experiments show that MTZ is also able to effectively merge multiple residual networks.

PDF Details