Session-1

## Mobile Device and RFID

Conference
11:15 AM — 12:45 PM CST
Local
Jul 26 Mon, 11:15 PM — 12:45 AM EDT

### Real-Time Deep Video Analytics on Mobile Devices

Jian He (University of Texas at Austin, USA), Ghufran Baig (University of Texas at Austin, USA), Lili Qiu (University of Texas at Austin, USA)

0
Real-time mobile video analytics plays an increasingly important role in our daily life, such as smart driving, unmanned delivery, cashier free stores, and video surveillance. The existing video analytics runs complex deep models to detect and recognize objects in video frames. However, running deep models on mobile devices can not meet the real-time requirement. This paper develops a novel mobile video analytics system. Its unique features include (i) high accuracy, (ii) real-time, and (iii) running exclusively on a mobile device without the need of edge/cloud server or network connectivity. At its heart lies an effective technique to reliably extract motion from video frames and use the motion to speed up video analytics. Unlike the existing motion extraction, our technique is robust to background noise and changes in object sizes. Extensive evaluation results show that we can support real-time object tracking at 30 frames/second (fps) on Nvidia Jetson TX2. For single-object tracking, Sight improves the average Intersection-over-Union (IoU) by 88%, improves the mean Average Precision (mAP) by 207% and reduces the average power consumption by 39% over state-of-the-art approach. For multi-object tracking, Sight improves IoU by 69%, improves mAP by 173% and reduces resource usage by around 32% over state-of-the-art approach.

### Rotation Sensing Using Passive RFID Tags

Swadhin Pradhan (University of Texas at Austin, USA), Shuozhe Li (University of Texas at Austin, USA), Lili Qiu (University of Texas at Austin, USA)

0
Rotational movement is important in many applications, yet has been under-explored. In this paper, we explore the feasibility of using a single RFID reader antenna to simultaneously sense rotation and translation movement (i.e., speed, direction, spin, and rotation axis). We exploit the polarization in RFID to enable motion sensing. We develop an analytical model to capture the impact of polarization on the received signal and an optimization framework to incorporate the model to estimate the movement. We implement our system, Tag based Inertial Measurement Unit (TIMU), and demonstrate its effectiveness through extensive evaluation. To our knowledge, this is the first system that tracks general motion using a single RFID reader antenna.

### The Tags Are Alright: Robust Large-Scale RFID Clone Detection Through Federated Data-Augmented Radio Fingerprinting

Mauro Piva (Sapienza University, Italy), Gaia Maselli (Sapienza University, Italy), Francesco Restuccia (Northeastern University, USA)

1
Millions of RFID tags are pervasively used all around the globe to inexpensively identify a wide variety of everyday-use objects. One of the key issues of RFID is that tags cannot use energy-hungry cryptography, and thus can be easily cloned. For this reason, radio fingerprinting is a compelling approach that leverages the unique imperfections in the tag's wireless circuitry to achieve large-scale RFID clone detection. Recent work, however, has unveiled that time-varying channel conditions can significantly decrease the accuracy of the radio fingerprinting process. Prior art in RFID identification does not consider this critical aspect, and instead focuses on custom-tailored feature extraction techniques and data collection with static channel conditions. For this reason, we propose the first large-scale investigation into radio fingerprinting of RFID tags with dynamic channel conditions. Specifically, we perform a massive data collection campaign on a testbed composed by 200 off-the-shelf identical RFID tags and a software-defined radio (SDR) tag reader. We collect data with different tag-reader distances in an over-the-air configuration. To emulate implanted RFID tags, we also collect data with two different kinds of porcine meat inserted between the tag and the reader. We use this rich dataset to train and test several convolutional neural network (CNN)-based classifiers in a variety of channel conditions. Our investigation reveals that training and testing on different channel conditions drastically degrades the classifier's accuracy. For this reason, we propose a novel training framework based on federated machine learning (FML) and data augmentation (DAG) to boost the accuracy. Extensive experimental results indicate that (i) our FML approach improves accuracy by up to 48%; (ii) our DAG approach improves the FML performance by up to 19% and the single-dataset performance by 31%. To the best of our knowledge, this is the first paper experimentally demonstrating the efficacy of FML and DAG on a large device population. To allow full replicability, we are sharing with the research community our fully-labeled 200-GB RFID waveform dataset, as well as the entirety of our code and trained models, concurrently with our submission.

###### Session Chair

Jiaxin Ding (SJTU)

Session-2

## Learning Algorithms

Conference
3:00 PM — 5:00 PM CST
Local
Jul 27 Tue, 3:00 AM — 5:00 AM EDT

### Learning-NUM: Network Utility Maximization with Unknown Utility Functions and Queueing Delay

Xinzhe Fu (Massachusetts Institute of Technology, USA), Eytan Modiano (Massachusetts Institute of Technology, USA)

0
Network Utility Maximization (NUM) studies the problems of allocating traffic rates to network users in order to maximize the users' total utility subject to network resource constraints. In this paper, we propose a new NUM framework, Learning-NUM, where the users' utility functions are unknown apriori and the utility function values of the traffic rates can be observed only after the corresponding traffic is delivered to the destination, which means that the utility feedback experiences \textit{queueing delay}.The goal is to design a policy that gradually learns the utility functions and makes rate allocation and network scheduling/routing decisions so as to maximize the total utility obtained over a finite time horizon $T$. Apart from unknown utility functions and stochastic constraints, a central challenge of our problem lies in the queueing delay of the observations, which may be unbounded and depends on the decisions of the policy.We first show that the expected total utility obtained by the best dynamic policy is upper bounded by the solution to a static optimization problem. We then design an algorithm based on the ideas of gradient estimation, drift-plus-penalty optimization and Max-Weight scheduling, and embed it in a parallel-instance paradigm to form a policy that achieves $\tilde{O}(T^{3/4})$-regret, i.e., the difference between the expected utility obtained by the best dynamic policy and our policy is in $\tilde{O}(T^{3/4})$. Finally, to demonstrate the practical applicability of the Learning-NUM framework, we apply it to three application scenarios including database query, job scheduling and video streaming. We further conduct simulations on the job scheduling application to evaluate the empirical performance of our policy.

### Robust Multi-Agent Multi-Armed Bandits

Daniel Vial (University of Texas at Austin, USA), Sanjay Shakkottai (University of Texas at Austin, USA), R. Srikant (University of Illinois at Urbana-Champaign, USA)

0
Recent works have shown that agents facing independent instances of a stochastic $K$-armed bandit can collaborate to decrease regret. However, these works assume that each agent always recommends their individual best-arm estimates to other agents, which is unrealistic in envisioned applications (machine faults in distributed computing or spam in social recommendation systems). Hence, we generalize the setting to include $n$ honest and $m$ malicious agents who recommend best-arm estimates and arbitrary arms, respectively. We first show that even with a single malicious agent, existing collaboration-based algorithms fail to improve regret guarantees over a single-agent baseline. We propose a scheme where honest agents learn who is malicious and dynamically reduce communication with (i.e., "block") them. We show that collaboration indeed decreases regret for this algorithm, assuming $m$ is small compared to $K$ but without assumptions on malicious agents' behavior, thus ensuring that our algorithm is robust against any malicious recommendation strategy.

### Accelerating Distributed Online Meta-Learning via Multi-Agent Collaboration under Limited Communication

Sen Lin (Arizona State University, USA), Mehmet Dedeoglu (Arizona State University, USA), Junshan Zhang (Arizona State University, USA)

1
Online meta-learning is emerging as an enabling technique for achieving edge intelligence in the IoT ecosystem. Nevertheless, to learn a good meta-model for within-task fast adaptation, a single agent alone has to learn over many tasks, and this is the so-called cold-start' problem. Observing that in a multi-agent network the learning tasks across different agents often share some model similarity, we ask the following fundamental question: `Is it possible to accelerate the online meta-learning across agents via limited communication and if yes how much benefit can be achieved? " To answer this question, we propose a multi-agent online meta-learning framework and cast it as an equivalent \emph{two-level nested online convex optimization (OCO)} problem. By characterizing the upper bound of the agent-task-averaged regret, we show that the performance of multi-agent online meta-learning depends heavily on how much an agent can benefit from the distributed network-level OCO for meta-model updates via limited communication, which however is not well understood. To tackle this challenge, we devise a distributed online gradient descent algorithm with \emph{gradient tracking} where each agent tracks the global gradient using only one communication step with its neighbors per iteration, and it results in an average regret $O(\sqrt{T/N})$ per agent, indicating that a factor of $\sqrt{1/N}$ speedup over the optimal single-agent regret $O(\sqrt{T})$ after $T$ iterations, where $N$ is the number of agents. Building on this sharp performance speedup, we next develop a multi-agent online meta-learning algorithm and show that it can achieve the optimal task-average regret at a faster rate of $O(1/\sqrt{NT})$ via limited communication, compared to single-agent online meta-learning. Extensive experiments corroborate the theoretic results.

### GT-STORM: Taming Sample, Communication, and Memory Complexities in Decentralized Non-Convex Learning

Xin Zhang (Iowa State University, USA), Jia Liu (The Ohio State University, USA), Zhengyuan Zhu (Iowa State University, USA), Elizabeth Serena Bentley (Air Force Research Laboratory Information Directorate, USA)

0
Decentralized nonconvex optimization has received increasing attention in recent years in machine learning due to its advantages in system robustness, data privacy, and implementation simplicity. However, three fundamental challenges in designing decentralized optimization algorithms are how to reduce their sample, communication, and memory complexities. In this paper, we propose a gradient-tracking-based stochastic recursive momentum (GT-STORM) algorithm for efficiently solving nonconvex optimization in decentralized learning. We show that to reach an $\epsilon^2$-stationary solution, the total number of sample evaluations of our algorithm is $\tilde{O}(m^{1/2}\epsilon^{-3})$ and the number of communication rounds is $\tilde{O}(m^{-1/2}\epsilon^{-3})$, which improve the $O(\epsilon^{-4})$ costs of sample evaluations and communications for the existing decentralized stochastic gradient algorithms. We conduct extensive experiments with a variety of learning models, including non-convex logistical regression and convolutional neural networks, to verify our theoretical findings. Collectively, our results contribute to the state of the art of theories and algorithms for decentralized network optimization.

###### Session Chair

Haiming Jin (SJTU)