More Like this

1. Light-Weight RetinaNet for Object Detection on Edge Devices

   https://doi.org/10.1109/WF-IoT48130.2020.9221150  

   Li, Yixing; Dua, Akshay; Ren, Fengbo (June 2020, IEEE 6th World Forum on Internet of Things (WF-IoT))

   null (Ed.)

   This paper aims at reducing computation for Retinanet, an mAP-30-tier network, to facilitate its practical deployment on edge devices for providing IoT-based object detection services. We first validate RetinaNet has the best FLOP-mAP trade-off among all mAP-30-tier network. Then, we propose a light-weight RetinaNet structure with effective computation- accuracy trade-off by only reducing FLOPs in computationally intensive layers. Compared with the most common way of trading off computation with accuracy-input image scaling, the proposed solution shows a consistently better FLOPs-mAP trade-off curve. Light-weight RetinaNet achieves a 0.3% mAP improvement at 1.8x FLOPs reduction point over the original RetinaNet, and gains 1.8x more energy-efficiency on an Intel Arria 10 FPGA accelerator in the context of edge computing. The proposed method potentially can help a wide range of the object detection applications to move closer to a preferred corner for a better runtime and accuracy, while enjoys more energy-efficient inference at the edge. 

   more » « less
2. Controllability Backbone in Networks

   https://doi.org/10.1109/CDC49753.2023.10383398  

   Ahmad, Obaid Ullah; Shabbir, Mudassir; Abbas, Waseem (December 2023, IEEE)

   This paper studies the controllability backbone problem in dynamical networks defined over graphs. The main idea of the controllability backbone is to identify a small subset of edges in a given network such that any subnetwork containing those edges/links has at least the same network controllability as the original network while assuming the same set of input/leader vertices. We consider the strong structural controllability (SSC) in our work, which is useful but computationally challenging. Thus, we utilize two lower bounds on the network’s SSC based on the zero forcing notion and graph distances. We provide algorithms to compute controllability backbones while preserving these lower bounds. We thoroughly analyze the proposed algorithms and compute the number of edges in the controllability backbones. Finally, we compare and numerically evaluate our methods on random graphs. 

   more » « less
3. Robust Anomaly Detection with Graph Neural Networks Using Controllability

   https://doi.org/10.1109/CAI64502.2025.00157  

   Wei, Yifan; Said, Anwar; Abbas, Waseem; Koutsoukos, Xenofon (May 2025, IEEE)

   Anomaly detection in complex domains poses significant challenges due to the need for extensive labeled data and the inherently imbalanced nature of anomalous versus benign samples. Graph-based machine learning models have emerged as a promising solution that combines attribute and relational data to uncover intricate patterns. However, the scarcity of anomalous data exacerbates the challenge, which requires innovative strategies to enhance model learning with limited information. In this paper, we hypothesize that the incorporation of the influence of the nodes, quantified through average controllability, can significantly improve the performance of anomaly detection. We propose two novel approaches to integrate average controllability into graph-based frameworks: (1) using average controllability as an edge weight and (2) encoding it as a one-hot edge attribute vector. Through rigorous evaluation on real-world and synthetic networks with six state-of-the-art baselines, our proposed methods demonstrate improved performance in identifying anomalies, highlighting the critical role of controllability measures in enhancing the performance of graph machine learning models. This work underscores the potential of integrating average controllability as additional metrics to address the challenges of anomaly detection in sparse and imbalanced datasets. 

   more » « less
4. Discerning Edge Influence for Network Embedding

   https://doi.org/10.1145/3357384.3358044  

   Wang, Yaojing; Yao, Yuan; Tong, Hanghang; Xu, Feng; Lu, Jian (November 2019, CIKM)

   Network embedding, which learns the low-dimensional representations of nodes, has gained significant research attention. Despite its superior empirical success, often measured by the prediction performance of downstream tasks (e.g., multi-label classification), it is unclear why a given embedding algorithm outputs the specific node representations, and how the resulting node representations relate to the structure of the input network. In this paper, we propose to discern the edge influence as the first step towards understanding skip-gram basd network embedding methods. For this purpose, we propose an auditing framework NEAR, whose key part includes two algorithms (NEAR-ADD and NEAR-DEL) to effectively and efficiently quantify the influence of each edge. Based on the algorithms, we further identify high-influential edges by exploiting the linkage between edge influence and the network structure. Experimental results demonstrate that the proposed algorithms (NEAR-ADD and NEAR-DEL) are significantly faster (up to 2, 000×) than straightforward methods with little quality loss. Moreover, the proposed framework can efficiently identify the most influential edges for network embedding in the context of downstream prediction task and adversarial attacking. 

   more » « less
5. Controllability analysis of origami dynamics via state-space modeling

   https://doi.org/10.1016/j.matdes.2025.114771  

   Yamaguchi, Koshiro; Jeong, Suyeon; Miyazawa, Yasuhiro; Oh, Yu Bin; Dai, Ran; Mesbahi, Mehran; Yang, Jinkyu (September 2025, Materials & Design)

   We investigate the controllability of an origami system composed of Miura-ori cells. A substantial volume of research on folding architecture, kinematic behavior, and actuation techniques of origami structures has been conducted. However, understanding their transient dynamics and constructing control models remains a formidable task, primarily due to their innate flexibility and compliance. In light of this challenge, we discretize the origami system into a network composed of interconnected particle masses alongside bar and hinge elements. This yields a state-space representation of the system's dynamics, enabling us to obtain the system's controllability attributes. Informed by this computational framework, we explore the controllability Gramian-based method for finding the most efficient crease line for Miura-ori cell deployment using an actuator. We demonstrate that the deployment efficiency guided by this theoretical method agrees with the empirical results obtained from the energy consumption to deploy the origami structure. This investigation paves the way toward designing and operating an efficient the complex actuation system for origami tessellations. 

   more » « less