Paper Group ANR 230
Federated Learning for Resource-Constrained IoT Devices: Panoramas and State-of-the-art. Adaptive strategy in differential evolution via explicit exploitation and exploration controls. Fast, Compact and Highly Scalable Visual Place Recognition through Sequence-based Matching of Overloaded Representations. On Reinforcement Learning for Turn-based Ze …
Federated Learning for Resource-Constrained IoT Devices: Panoramas and State-of-the-art
| Title | Federated Learning for Resource-Constrained IoT Devices: Panoramas and State-of-the-art |
| Authors | Ahmed Imteaj, Urmish Thakker, Shiqiang Wang, Jian Li, M. Hadi Amini |
| Abstract | Nowadays, devices are equipped with advanced sensors with higher processing/computing capabilities. Further, widespread Internet availability enables communication among sensing devices. As a result, vast amounts of data are generated on edge devices to drive Internet-of-Things (IoT), crowdsourcing, and other emerging technologies. The collected extensive data can be pre-processed, scaled, classified, and finally, used for predicting future events using machine learning (ML) methods. In traditional ML approaches, data is sent to and processed in a central server, which encounters communication overhead, processing delay, privacy leakage, and security issues. To overcome these challenges, each client can be trained locally based on its available data and by learning from the global model. This decentralized learning structure is referred to as Federated Learning (FL). However, in large-scale networks, there may be clients with varying computational resource capabilities. This may lead to implementation and scalability challenges for FL techniques. In this paper, we first introduce some recently implemented real-life applications of FL. We then emphasize on the core challenges of implementing the FL algorithms from the perspective of resource limitations (e.g., memory, bandwidth, and energy budget) of client clients. We finally discuss open issues associated with FL and highlight future directions in the FL area concerning resource-constrained devices. |
| Tasks | |
| Published | 2020-02-25 |
| URL | https://arxiv.org/abs/2002.10610v1 |
| https://arxiv.org/pdf/2002.10610v1.pdf | |
| PWC | https://paperswithcode.com/paper/federated-learning-for-resource-constrained |
| Repo | |
| Framework | |
Adaptive strategy in differential evolution via explicit exploitation and exploration controls
| Title | Adaptive strategy in differential evolution via explicit exploitation and exploration controls |
| Authors | Sheng Xin Zhang, Wing Shing Chan, Kit Sang Tang, Shao Yong Zheng |
| Abstract | When introducing new strategies to the existing one, two key issues should be addressed. One is to efficiently distribute computational resources so that the appropriate strategy dominates. The other is to remedy or even eliminate the drawback of inappropriate strategies. Adaptation is a popular and efficient method for strategy adjustments and has been widely studied in the literature. Existing methods commonly involve the trials of multiple strategies and then reward better-performing one with more resources based on their previous performance. As a result, it may not efficiently address those two key issues. On the one hand, they are based on trial-and-error with inappropriate strategies consuming resources. On the other hand, since multiple strategies are involved in the trial, the inappropriate strategies could mislead the search. In this paper, we propose an adaptive differential evolution (DE) with explicit exploitation and exploration controls (Explicit adaptation DE, EaDE), which is the first attempt using offline knowledge to separate multiple strategies to exempt the optimization from trial-and-error. EaDE divides the evolution process into several SCSS (Selective-candidate with similarity selection) generations and adaptive generations. Exploitation and exploration needs are learned in the SCSS generations by a relatively balanced strategy. While in the adaptive generations, to meet these needs, two other alternative strategies, an exploitative one or an explorative one is employed. Experimental studies on 28 benchmark functions confirm the effectiveness of the proposed method. |
| Tasks | |
| Published | 2020-02-03 |
| URL | https://arxiv.org/abs/2002.00612v1 |
| https://arxiv.org/pdf/2002.00612v1.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-strategy-in-differential-evolution |
| Repo | |
| Framework | |
Fast, Compact and Highly Scalable Visual Place Recognition through Sequence-based Matching of Overloaded Representations
| Title | Fast, Compact and Highly Scalable Visual Place Recognition through Sequence-based Matching of Overloaded Representations |
| Authors | Sourav Garg, Michael Milford |
| Abstract | Visual place recognition algorithms trade off three key characteristics: their storage footprint, their computational requirements, and their resultant performance, often expressed in terms of recall rate. Significant prior work has investigated highly compact place representations, sub-linear computational scaling and sub-linear storage scaling techniques, but have always involved a significant compromise in one or more of these regards, and have only been demonstrated on relatively small datasets. In this paper we present a novel place recognition system which enables for the first time the combination of ultra-compact place representations, near sub-linear storage scaling and extremely lightweight compute requirements. Our approach exploits the inherently sequential nature of much spatial data in the robotics domain and inverts the typical target criteria, through intentionally coarse scalar quantization-based hashing that leads to more collisions but is resolved by sequence-based matching. For the first time, we show how effective place recognition rates can be achieved on a new very large 10 million place dataset, requiring only 8 bytes of storage per place and 37K unitary operations to achieve over 50% recall for matching a sequence of 100 frames, where a conventional state-of-the-art approach both consumes 1300 times more compute and fails catastrophically. We present analysis investigating the effectiveness of our hashing overload approach under varying sizes of quantized vector length, comparison of near miss matches with the actual match selections and characterise the effect of variance re-scaling of data on quantization. |
| Tasks | Quantization, Visual Place Recognition |
| Published | 2020-01-23 |
| URL | https://arxiv.org/abs/2001.08434v2 |
| https://arxiv.org/pdf/2001.08434v2.pdf | |
| PWC | https://paperswithcode.com/paper/fast-compact-and-highly-scalable-visual-place |
| Repo | |
| Framework | |
On Reinforcement Learning for Turn-based Zero-sum Markov Games
| Title | On Reinforcement Learning for Turn-based Zero-sum Markov Games |
| Authors | Devavrat Shah, Varun Somani, Qiaomin Xie, Zhi Xu |
| Abstract | We consider the problem of finding Nash equilibrium for two-player turn-based zero-sum games. Inspired by the AlphaGo Zero (AGZ) algorithm, we develop a Reinforcement Learning based approach. Specifically, we propose Explore-Improve-Supervise (EIS) method that combines “exploration”, “policy improvement”’ and “supervised learning” to find the value function and policy associated with Nash equilibrium. We identify sufficient conditions for convergence and correctness for such an approach. For a concrete instance of EIS where random policy is used for “exploration”, Monte-Carlo Tree Search is used for “policy improvement” and Nearest Neighbors is used for “supervised learning”, we establish that this method finds an $\varepsilon$-approximate value function of Nash equilibrium in $\widetilde{O}(\varepsilon^{-(d+4)})$ steps when the underlying state-space of the game is continuous and $d$-dimensional. This is nearly optimal as we establish a lower bound of $\widetilde{\Omega}(\varepsilon^{-(d+2)})$ for any policy. |
| Tasks | |
| Published | 2020-02-25 |
| URL | https://arxiv.org/abs/2002.10620v1 |
| https://arxiv.org/pdf/2002.10620v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-reinforcement-learning-for-turn-based-zero |
| Repo | |
| Framework | |
FedCoin: A Peer-to-Peer Payment System for Federated Learning
| Title | FedCoin: A Peer-to-Peer Payment System for Federated Learning |
| Authors | Yuan Liu, Shuai Sun, Zhengpeng Ai, Shuangfeng Zhang, Zelei Liu, Han Yu |
| Abstract | Federated learning (FL) is an emerging collaborative machine learning method to train models on distributed datasets with privacy concerns. To properly incentivize data owners to contribute their efforts, Shapley Value (SV) is often adopted to fairly assess their contribution. However, the calculation of SV is time-consuming and computationally costly. In this paper, we propose FedCoin, a blockchain-based peer-to-peer payment system for FL to enable a feasible SV based profit distribution. In FedCoin, blockchain consensus entities calculate SVs and a new block is created based on the proof of Shapley (PoSap) protocol. It is in contrast to the popular BitCoin network where consensus entities “mine” new blocks by solving meaningless puzzles. Based on the computed SVs, a scheme for dividing the incentive payoffs among FL clients with nonrepudiation and tamper-resistance properties is proposed. Experimental results based on real-world data show that FedCoin can promote high-quality data from FL clients through accurately computing SVs with an upper bound on the computational resources required for reaching consensus. It opens opportunities for non-data owners to play a role in FL. |
| Tasks | |
| Published | 2020-02-26 |
| URL | https://arxiv.org/abs/2002.11711v1 |
| https://arxiv.org/pdf/2002.11711v1.pdf | |
| PWC | https://paperswithcode.com/paper/fedcoin-a-peer-to-peer-payment-system-for |
| Repo | |
| Framework | |
Expecting the Unexpected: Developing Autonomous-System Design Principles for Reacting to Unpredicted Events and Conditions
| Title | Expecting the Unexpected: Developing Autonomous-System Design Principles for Reacting to Unpredicted Events and Conditions |
| Authors | Assaf Marron, Lior Limonad, Sarah Pollack, David Harel |
| Abstract | When developing autonomous systems, engineers and other stakeholders make great effort to prepare the system for all foreseeable events and conditions. However, these systems are still bound to encounter events and conditions that were not considered at design time. For reasons like safety, cost, or ethics, it is often highly desired that these new situations be handled correctly upon first encounter. In this paper we first justify our position that there will always exist unpredicted events and conditions, driven among others by: new inventions in the real world; the diversity of world-wide system deployments and uses; and, the non-negligible probability that multiple seemingly unlikely events, which may be neglected at design time, will not only occur, but occur together. We then argue that despite this unpredictability property, handling these events and conditions is indeed possible. Hence, we offer and exemplify design principles that when applied in advance, can enable systems to deal, in the future, with unpredicted circumstances. We conclude with a discussion of how this work and a broader theoretical study of the unexpected can contribute toward a foundation of engineering principles for developing trustworthy next-generation autonomous systems. |
| Tasks | |
| Published | 2020-01-16 |
| URL | https://arxiv.org/abs/2001.06047v3 |
| https://arxiv.org/pdf/2001.06047v3.pdf | |
| PWC | https://paperswithcode.com/paper/expecting-the-unexpected-developing |
| Repo | |
| Framework | |
Explaining the Punishment Gap of AI and Robots
| Title | Explaining the Punishment Gap of AI and Robots |
| Authors | Gabriel Lima, Meeyoung Cha, Chihyung Jeon, Kyungsin Park |
| Abstract | The European Parliament’s proposal to create a new legal status for artificial intelligence (AI) and robots brought into focus the idea of electronic legal personhood. This discussion, however, is hugely controversial. While some scholars argue that the proposed status could contribute to the coherence of the legal system, others say that it is neither beneficial nor desirable. Notwithstanding this prospect, we conducted a survey (N=3315) to understand online users’ perceptions of the legal personhood of AI and robots. We observed how the participants assigned responsibility, awareness, and punishment to AI, robots, humans, and various entities that could be held liable under existing doctrines. We also asked whether the participants thought that punishing electronic agents fulfills the same legal and social functions as human punishment. The results suggest that even though people do not assign any mental state to electronic agents and are not willing to grant AI and robots physical independence or assets, which are the prerequisites of criminal or civil liability, they do consider them responsible for their actions and worthy of punishment. The participants also did not think that punishment or liability of these entities would achieve the primary functions of punishment, leading to what we define as the punishment gap. Therefore, before we recognize electronic legal personhood, we must first discuss proper methods of satisfying the general population’s demand for punishment. |
| Tasks | |
| Published | 2020-03-13 |
| URL | https://arxiv.org/abs/2003.06507v1 |
| https://arxiv.org/pdf/2003.06507v1.pdf | |
| PWC | https://paperswithcode.com/paper/explaining-the-punishment-gap-of-ai-and |
| Repo | |
| Framework | |
Transformation-based Adversarial Video Prediction on Large-Scale Data
| Title | Transformation-based Adversarial Video Prediction on Large-Scale Data |
| Authors | Pauline Luc, Aidan Clark, Sander Dieleman, Diego de Las Casas, Yotam Doron, Albin Cassirer, Karen Simonyan |
| Abstract | Recent breakthroughs in adversarial generative modeling have led to models capable of producing video samples of high quality, even on large and complex datasets of real-world video. In this work, we focus on the task of video prediction, where given a sequence of frames extracted from a video, the goal is to generate a plausible future sequence. We first improve the state of the art by performing a systematic empirical study of discriminator decompositions and proposing an architecture that yields faster convergence and higher performance than previous approaches. We then analyze recurrent units in the generator, and propose a novel recurrent unit which transforms its past hidden state according to predicted motion-like features, and refines it to to handle dis-occlusions, scene changes and other complex behavior. We show that this recurrent unit consistently outperforms previous designs. Our final model leads to a leap in the state-of-the-art performance, obtaining a test set Frechet Video Distance of 25.7, down from 69.2, on the large-scale Kinetics-600 dataset. |
| Tasks | Video Prediction |
| Published | 2020-03-09 |
| URL | https://arxiv.org/abs/2003.04035v1 |
| https://arxiv.org/pdf/2003.04035v1.pdf | |
| PWC | https://paperswithcode.com/paper/transformation-based-adversarial-video |
| Repo | |
| Framework | |
Wine quality rapid detection using a compact electronic nose system: application focused on spoilage thresholds by acetic acid
| Title | Wine quality rapid detection using a compact electronic nose system: application focused on spoilage thresholds by acetic acid |
| Authors | Juan C. Rodriguez Gamboa, Eva Susana Albarracin E., Adenilton J. da Silva, Luciana Leite, Tiago A. E. Ferreira |
| Abstract | It is crucial for the wine industry to have methods like electronic nose systems (E-Noses) for real-time monitoring thresholds of acetic acid in wines, preventing its spoilage or determining its quality. In this paper, we prove that the portable and compact self-developed E-Nose, based on thin film semiconductor (SnO2) sensors and trained with an approach that uses deep Multilayer Perceptron (MLP) neural network, can perform early detection of wine spoilage thresholds in routine tasks of wine quality control. To obtain rapid and online detection, we propose a method of rising-window focused on raw data processing to find an early portion of the sensor signals with the best recognition performance. Our approach was compared with the conventional approach employed in E-Noses for gas recognition that involves feature extraction and selection techniques for preprocessing data, succeeded by a Support Vector Machine (SVM) classifier. The results evidence that is possible to classify three wine spoilage levels in 2.7 seconds after the gas injection point, implying in a methodology 63 times faster than the results obtained with the conventional approach in our experimental setup. |
| Tasks | |
| Published | 2020-01-16 |
| URL | https://arxiv.org/abs/2001.06323v1 |
| https://arxiv.org/pdf/2001.06323v1.pdf | |
| PWC | https://paperswithcode.com/paper/wine-quality-rapid-detection-using-a-compact |
| Repo | |
| Framework | |
DYNOTEARS: Structure Learning from Time-Series Data
| Title | DYNOTEARS: Structure Learning from Time-Series Data |
| Authors | Roxana Pamfil, Nisara Sriwattanaworachai, Shaan Desai, Philip Pilgerstorfer, Paul Beaumont, Konstantinos Georgatzis, Bryon Aragam |
| Abstract | In this paper, we revisit the structure learning problem for dynamic Bayesian networks and propose a method that simultaneously estimates contemporaneous (intra-slice) and time-lagged (inter-slice) relationships between variables in a time-series. Our approach is score-based, and revolves around minimizing a penalized loss subject to an acyclicity constraint. To solve this problem, we leverage a recent algebraic result characterizing the acyclicity constraint as a smooth equality constraint. The resulting algorithm, which we call DYNOTEARS, outperforms other methods on simulated data, especially in high-dimensions as the number of variables increases. We also apply this algorithm on real datasets from two different domains, finance and molecular biology, and analyze the resulting output. Compared to state-of-the-art methods for learning dynamic Bayesian networks, our method is both scalable and accurate on real data. The simple formulation, and competitive performance of our method make it suitable for a variety of problems where one seeks to learn connections between variables across time. |
| Tasks | Time Series |
| Published | 2020-02-02 |
| URL | https://arxiv.org/abs/2002.00498v1 |
| https://arxiv.org/pdf/2002.00498v1.pdf | |
| PWC | https://paperswithcode.com/paper/dynotears-structure-learning-from-time-series |
| Repo | |
| Framework | |
On Sufficient and Necessary Conditions in Bounded CTL
| Title | On Sufficient and Necessary Conditions in Bounded CTL |
| Authors | Renyan Feng, Erman Acar, Stefan Schlobach, Yisong Wang, Wanwei Liu |
| Abstract | Computation Tree Logic (CTL) is one of the central formalisms in formal verification. As a specification language, it is used to express a property that the system at hand is expected to satisfy. From both the verification and the system design points of view, some information content of such property might become irrelevant for the system due to various reasons e.g., it might become obsolete by time, or perhaps infeasible due to practical difficulties. Then, the problem arises on how to subtract such piece of information without altering the relevant system behaviour or violating the existing specifications. Moreover, in such a scenario, two crucial notions are informative: the strongest necessary condition (SNC) and the weakest sufficient condition (WSC) of a given property. To address such a scenario in a principled way, we introduce a forgetting-based approach in CTL and show that it can be used to compute SNC and WSC of a property under a given model. We study its theoretical properties and also show that our notion of forgetting satisfies existing essential postulates. Furthermore, we analyse the computational complexity of basic tasks, including various results for the relevant fragment CTLAF. |
| Tasks | |
| Published | 2020-03-13 |
| URL | https://arxiv.org/abs/2003.06492v1 |
| https://arxiv.org/pdf/2003.06492v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-sufficient-and-necessary-conditions-in |
| Repo | |
| Framework | |
Recurrent convolutional neural networks for mandible segmentation from computed tomography
| Title | Recurrent convolutional neural networks for mandible segmentation from computed tomography |
| Authors | Bingjiang Qiu, Jiapan Guo, Joep Kraeima, Haye H. Glas, Ronald J. H. Borra, Max J. H. Witjes, Peter M. A. van Ooijen |
| Abstract | Recently, accurate mandible segmentation in CT scans based on deep learning methods has attracted much attention. However, there still exist two major challenges, namely, metal artifacts among mandibles and large variations in shape or size among individuals. To address these two challenges, we propose a recurrent segmentation convolutional neural network (RSegCNN) that embeds segmentation convolutional neural network (SegCNN) into the recurrent neural network (RNN) for robust and accurate segmentation of the mandible. Such a design of the system takes into account the similarity and continuity of the mandible shapes captured in adjacent image slices in CT scans. The RSegCNN infers the mandible information based on the recurrent structure with the embedded encoder-decoder segmentation (SegCNN) components. The recurrent structure guides the system to exploit relevant and important information from adjacent slices, while the SegCNN component focuses on the mandible shapes from a single CT slice. We conducted extensive experiments to evaluate the proposed RSegCNN on two head and neck CT datasets. The experimental results show that the RSegCNN is significantly better than the state-of-the-art models for accurate mandible segmentation. |
| Tasks | |
| Published | 2020-03-13 |
| URL | https://arxiv.org/abs/2003.06486v1 |
| https://arxiv.org/pdf/2003.06486v1.pdf | |
| PWC | https://paperswithcode.com/paper/recurrent-convolutional-neural-networks-for-4 |
| Repo | |
| Framework | |
Semantic Discord: Finding Unusual Local Patterns for Time Series
| Title | Semantic Discord: Finding Unusual Local Patterns for Time Series |
| Authors | Li Zhang, Yifeng Gao, Jessica Lin |
| Abstract | Finding anomalous subsequence in a long time series is a very important but difficult problem. Existing state-of-the-art methods have been focusing on searching for the subsequence that is the most dissimilar to the rest of the subsequences; however, they do not take into account the background patterns that contain the anomalous candidates. As a result, such approaches are likely to miss local anomalies. We introduce a new definition named \textit{semantic discord}, which incorporates the context information from larger subsequences containing the anomaly candidates. We propose an efficient algorithm with a derived lower bound that is up to 3 orders of magnitude faster than the brute force algorithm in real world data. We demonstrate that our method significantly outperforms the state-of-the-art methods in locating anomalies by extensive experiments. We further explain the interpretability of semantic discord. |
| Tasks | Time Series |
| Published | 2020-01-30 |
| URL | https://arxiv.org/abs/2001.11842v2 |
| https://arxiv.org/pdf/2001.11842v2.pdf | |
| PWC | https://paperswithcode.com/paper/semantic-discord-finding-unusual-local |
| Repo | |
| Framework | |
Valid distribution-free inferential models for prediction
| Title | Valid distribution-free inferential models for prediction |
| Authors | Leonardo Cella, Ryan Martin |
| Abstract | A fundamental problem in statistics and machine learning is that of using observed data to predict future observations. This is particularly challenging for model-based approaches because often the goal is to carry out this prediction with no or minimal model assumptions. For example, the inferential model (IM) approach is attractive because it has certain validity guarantees, but requires specification of a parametric model. Here we show that a new perspective on a recently developed generalized IM approach can be applied to construct an IM for prediction that satisfies the desirable validity guarantees without specification of a model. One important special case of this approach corresponds to the powerful conformal prediction framework and, consequently, the desirable properties of conformal prediction follow immediately from the general IM validity theory. Several numerical examples are presented to illustrate the theory and highlight the method’s performance and flexibility. |
| Tasks | |
| Published | 2020-01-24 |
| URL | https://arxiv.org/abs/2001.09225v1 |
| https://arxiv.org/pdf/2001.09225v1.pdf | |
| PWC | https://paperswithcode.com/paper/valid-distribution-free-inferential-models |
| Repo | |
| Framework | |
Joint Encoding of Appearance and Motion Features with Self-supervision for First Person Action Recognition
| Title | Joint Encoding of Appearance and Motion Features with Self-supervision for First Person Action Recognition |
| Authors | Mirco Planamente, Andrea Bottino, Barbara Caputo |
| Abstract | Wearable cameras are becoming more and more popular in several applications, increasing the interest of the research community in developing approaches for recognizing actions from a first-person point of view. An open challenge is how to cope with the limited amount of motion information available about the action itself, as opposed to the more investigated third-person action recognition scenario. When focusing on manipulation tasks, videos tend to record only parts of the movement, making crucial the understanding of the objects being manipulated and of their context. Previous works addressed this issue with two-stream architectures, one dedicated to modeling the appearance of objects involved in the action, another dedicated to extracting motion features from optical flow. In this paper, we argue that features from these two information channels should be learned jointly to capture the spatio-temporal correlations between the two in a better way. To this end, we propose a single stream architecture able to do so, thanks to the addition of a self-supervised block that uses a pretext motion segmentation task to intertwine motion and appearance knowledge. Experiments on several publicly available databases show the power of our approach. |
| Tasks | Motion Segmentation, Optical Flow Estimation |
| Published | 2020-02-10 |
| URL | https://arxiv.org/abs/2002.03982v1 |
| https://arxiv.org/pdf/2002.03982v1.pdf | |
| PWC | https://paperswithcode.com/paper/joint-encoding-of-appearance-and-motion |
| Repo | |
| Framework | |
