Alert button
Picture for Lu Zhou

Lu Zhou

Alert button

Sparse Federated Training of Object Detection in the Internet of Vehicles

Sep 07, 2023
Luping Rao, Chuan Ma, Ming Ding, Yuwen Qian, Lu Zhou, Zhe Liu

Figure 1 for Sparse Federated Training of Object Detection in the Internet of Vehicles
Figure 2 for Sparse Federated Training of Object Detection in the Internet of Vehicles
Figure 3 for Sparse Federated Training of Object Detection in the Internet of Vehicles
Figure 4 for Sparse Federated Training of Object Detection in the Internet of Vehicles

As an essential component part of the Intelligent Transportation System (ITS), the Internet of Vehicles (IoV) plays a vital role in alleviating traffic issues. Object detection is one of the key technologies in the IoV, which has been widely used to provide traffic management services by analyzing timely and sensitive vehicle-related information. However, the current object detection methods are mostly based on centralized deep training, that is, the sensitive data obtained by edge devices need to be uploaded to the server, which raises privacy concerns. To mitigate such privacy leakage, we first propose a federated learning-based framework, where well-trained local models are shared in the central server. However, since edge devices usually have limited computing power, plus a strict requirement of low latency in IoVs, we further propose a sparse training process on edge devices, which can effectively lighten the model, and ensure its training efficiency on edge devices, thereby reducing communication overheads. In addition, due to the diverse computing capabilities and dynamic environment, different sparsity rates are applied to edge devices. To further guarantee the performance, we propose, FedWeg, an improved aggregation scheme based on FedAvg, which is designed by the inverse ratio of sparsity rates. Experiments on the real-life dataset using YOLO show that the proposed scheme can achieve the required object detection rate while saving considerable communication costs.

Viaarxiv icon

Temporal-Channel Topology Enhanced Network for Skeleton-Based Action Recognition

Feb 25, 2023
Jinzhao Luo, Lu Zhou, Guibo Zhu, Guojing Ge, Beiying Yang, Jinqiao Wang

Figure 1 for Temporal-Channel Topology Enhanced Network for Skeleton-Based Action Recognition
Figure 2 for Temporal-Channel Topology Enhanced Network for Skeleton-Based Action Recognition
Figure 3 for Temporal-Channel Topology Enhanced Network for Skeleton-Based Action Recognition
Figure 4 for Temporal-Channel Topology Enhanced Network for Skeleton-Based Action Recognition

Skeleton-based action recognition has become popular in recent years due to its efficiency and robustness. Most current methods adopt graph convolutional network (GCN) for topology modeling, but GCN-based methods are limited in long-distance correlation modeling and generalizability. In contrast, the potential of convolutional neural network (CNN) for topology modeling has not been fully explored. In this paper, we propose a novel CNN architecture, Temporal-Channel Topology Enhanced Network (TCTE-Net), to learn spatial and temporal topologies for skeleton-based action recognition. The TCTE-Net consists of two modules: the Temporal-Channel Focus module, which learns a temporal-channel focus matrix to identify the most critical feature representations, and the Dynamic Channel Topology Attention module, which dynamically learns spatial topological features, and fuses them with an attention mechanism to model long-distance channel-wise topology. We conduct experiments on NTU RGB+D, NTU RGB+D 120, and FineGym datasets. TCTE-Net shows state-of-the-art performance compared to CNN-based methods and achieves superior performance compared to GCN-based methods. The code is available at https://github.com/aikuniverse/TCTE-Net.

Viaarxiv icon

PromptAttack: Prompt-based Attack for Language Models via Gradient Search

Sep 05, 2022
Yundi Shi, Piji Li, Changchun Yin, Zhaoyang Han, Lu Zhou, Zhe Liu

Figure 1 for PromptAttack: Prompt-based Attack for Language Models via Gradient Search
Figure 2 for PromptAttack: Prompt-based Attack for Language Models via Gradient Search
Figure 3 for PromptAttack: Prompt-based Attack for Language Models via Gradient Search
Figure 4 for PromptAttack: Prompt-based Attack for Language Models via Gradient Search

As the pre-trained language models (PLMs) continue to grow, so do the hardware and data requirements for fine-tuning PLMs. Therefore, the researchers have come up with a lighter method called \textit{Prompt Learning}. However, during the investigations, we observe that the prompt learning methods are vulnerable and can easily be attacked by some illegally constructed prompts, resulting in classification errors, and serious security problems for PLMs. Most of the current research ignores the security issue of prompt-based methods. Therefore, in this paper, we propose a malicious prompt template construction method (\textbf{PromptAttack}) to probe the security performance of PLMs. Several unfriendly template construction approaches are investigated to guide the model to misclassify the task. Extensive experiments on three datasets and three PLMs prove the effectiveness of our proposed approach PromptAttack. We also conduct experiments to verify that our method is applicable in few-shot scenarios.

* 12 pages 
Viaarxiv icon

Ontology Design Facilitating Wikibase Integration -- and a Worked Example for Historical Data

May 27, 2022
Cogan Shimizu, Andrew Eells, Seila Gonzalez, Lu Zhou, Pascal Hitzler, Alicia Sheill, Catherine Foley, Dean Rehberger

Figure 1 for Ontology Design Facilitating Wikibase Integration -- and a Worked Example for Historical Data
Figure 2 for Ontology Design Facilitating Wikibase Integration -- and a Worked Example for Historical Data
Figure 3 for Ontology Design Facilitating Wikibase Integration -- and a Worked Example for Historical Data
Figure 4 for Ontology Design Facilitating Wikibase Integration -- and a Worked Example for Historical Data

Wikibase -- which is the software underlying Wikidata -- is a powerful platform for knowledge graph creation and management. However, it has been developed with a crowd-sourced knowledge graph creation scenario in mind, which in particular means that it has not been designed for use case scenarios in which a tightly controlled high-quality schema, in the form of an ontology, is to be imposed, and indeed, independently developed ontologies do not necessarily map seamlessly to the Wikibase approach. In this paper, we provide the key ingredients needed in order to combine traditional ontology modeling with use of the Wikibase platform, namely a set of \emph{axiom} patterns that bridge the paradigm gap, together with usage instructions and a worked example for historical data.

Viaarxiv icon

Hyper Attention Recurrent Neural Network: Tackling Temporal Covariate Shift in Time Series Analysis

Feb 22, 2022
Wenying Duan, Xiaoxi He, Lu Zhou, Zimu Zhou, Lothar Thiele, Hong Rao

Figure 1 for Hyper Attention Recurrent Neural Network: Tackling Temporal Covariate Shift in Time Series Analysis
Figure 2 for Hyper Attention Recurrent Neural Network: Tackling Temporal Covariate Shift in Time Series Analysis
Figure 3 for Hyper Attention Recurrent Neural Network: Tackling Temporal Covariate Shift in Time Series Analysis
Figure 4 for Hyper Attention Recurrent Neural Network: Tackling Temporal Covariate Shift in Time Series Analysis

Analyzing long time series with RNNs often suffers from infeasible training. Segmentation is therefore commonly used in data pre-processing. However, in non-stationary time series, there exists often distribution shift among different segments. RNN is easily swamped in the dilemma of fitting bias in these segments due to the lack of global information, leading to poor generalization, known as Temporal Covariate Shift (TCS) problem, which is only addressed by a recently proposed RNN-based model. One of the assumptions in TCS is that the distribution of all divided intervals under the same segment are identical. This assumption, however, may not be true on high-frequency time series, such as traffic flow, that also have large stochasticity. Besides, macro information across long periods isn't adequately considered in the latest RNN-based methods. To address the above issues, we propose Hyper Attention Recurrent Neural Network (HARNN) for the modeling of temporal patterns containing both micro and macro information. An HARNN consists of a meta layer for parameter generation and an attention-enabled main layer for inference. High-frequency segments are transformed into low-frequency segments and fed into the meta layers, while the first main layer consumes the same high-frequency segments as conventional methods. In this way, each low-frequency segment in the meta inputs generates a unique main layer, enabling the integration of both macro information and micro information for inference. This forces all main layers to predict the same target which fully harnesses the common knowledge in varied distributions when capturing temporal patterns. Evaluations on multiple benchmarks demonstrated that our model outperforms a couple of RNN-based methods on a federation of key metrics.

* 6 pages, 4 figures 
Viaarxiv icon

Neuro-Symbolic Artificial Intelligence: Current Trends

May 14, 2021
Md Kamruzzaman Sarker, Lu Zhou, Aaron Eberhart, Pascal Hitzler

Figure 1 for Neuro-Symbolic Artificial Intelligence: Current Trends
Figure 2 for Neuro-Symbolic Artificial Intelligence: Current Trends
Figure 3 for Neuro-Symbolic Artificial Intelligence: Current Trends
Figure 4 for Neuro-Symbolic Artificial Intelligence: Current Trends

Neuro-Symbolic Artificial Intelligence -- the combination of symbolic methods with methods that are based on artificial neural networks -- has a long-standing history. In this article, we provide a structured overview of current trends, by means of categorizing recent publications from key conferences. The article is meant to serve as a convenient starting point for research on the general topic.

* under review 
Viaarxiv icon

Neuro-Symbolic Artificial Intelligence Current Trends

May 11, 2021
Md Kamruzzaman Sarker, Lu Zhou, Aaron Eberhart, Pascal Hitzler

Figure 1 for Neuro-Symbolic Artificial Intelligence Current Trends
Figure 2 for Neuro-Symbolic Artificial Intelligence Current Trends
Figure 3 for Neuro-Symbolic Artificial Intelligence Current Trends
Figure 4 for Neuro-Symbolic Artificial Intelligence Current Trends

Neuro-Symbolic Artificial Intelligence -- the combination of symbolic methods with methods that are based on artificial neural networks -- has a long-standing history. In this article, we provide a structured overview of current trends, by means of categorizing recent publications from key conferences. The article is meant to serve as a convenient starting point for research on the general topic.

* under review 
Viaarxiv icon

Completion Reasoning Emulation for the Description Logic EL+

Dec 11, 2019
Aaron Eberhart, Monireh Ebrahimi, Lu Zhou, Cogan Shimizu, Pascal Hitzler

Figure 1 for Completion Reasoning Emulation for the Description Logic EL+
Figure 2 for Completion Reasoning Emulation for the Description Logic EL+
Figure 3 for Completion Reasoning Emulation for the Description Logic EL+
Figure 4 for Completion Reasoning Emulation for the Description Logic EL+

We present a new approach to integrating deep learning with knowledge-based systems that we believe shows promise. Our approach seeks to emulate reasoning structure, which can be inspected part-way through, rather than simply learning reasoner answers, which is typical in many of the black-box systems currently in use. We demonstrate that this idea is feasible by training a long short-term memory (LSTM) artificial neural network to learn EL+ reasoning patterns with two different data sets. We also show that this trained system is resistant to noise by corrupting a percentage of the test data and comparing the reasoner's and LSTM's predictions on corrupt data with correct answers.

Viaarxiv icon