Paper Group ANR 525
Resilient Load Restoration in Microgrids Considering Mobile Energy Storage Fleets: A Deep Reinforcement Learning Approach. Validation of Approximate Likelihood and Emulator Models for Computationally Intensive Simulations. A spiking neural algorithm for the Network Flow problem. Resource Allocation in Mobility-Aware Federated Learning Networks: A D …
Resilient Load Restoration in Microgrids Considering Mobile Energy Storage Fleets: A Deep Reinforcement Learning Approach
| Title | Resilient Load Restoration in Microgrids Considering Mobile Energy Storage Fleets: A Deep Reinforcement Learning Approach |
| Authors | Shuhan Yao, Jiuxiang Gu, Peng Wang, Tianyang Zhao, Huajun Zhang, Xiaochuan Liu |
| Abstract | Mobile energy storage systems (MESSs) provide mobility and flexibility to enhance distribution system resilience. The paper proposes a Markov decision process (MDP) formulation for an integrated service restoration strategy that coordinates the scheduling of MESSs and resource dispatching of microgrids. The uncertainties in load consumption are taken into account. The deep reinforcement learning (DRL) algorithm is utilized to solve the MDP for optimal scheduling. Specifically, the twin delayed deep deterministic policy gradient (TD3) is applied to train the deep Q-network and policy network, then the well trained policy can be deployed in on-line manner to perform multiple actions simultaneously. The proposed model is demonstrated on an integrated test system with three microgrids connected by Sioux Falls transportation network. The simulation results indicate that mobile and stationary energy resources can be well coordinated to improve system resilience. |
| Tasks | |
| Published | 2019-11-06 |
| URL | https://arxiv.org/abs/1911.02206v2 |
| https://arxiv.org/pdf/1911.02206v2.pdf | |
| PWC | https://paperswithcode.com/paper/resilient-load-restoration-in-microgrids |
| Repo | |
| Framework | |
Validation of Approximate Likelihood and Emulator Models for Computationally Intensive Simulations
| Title | Validation of Approximate Likelihood and Emulator Models for Computationally Intensive Simulations |
| Authors | Niccolò Dalmasso, Ann B. Lee, Rafael Izbicki, Taylor Pospisil, Ilmun Kim, Chieh-An Lin |
| Abstract | Complex phenomena in engineering and the sciences are often modeled with computationally intensive feed-forward simulations for which a tractable analytic likelihood does not exist. In these cases, it is sometimes necessary to estimate an approximate likelihood or fit a fast emulator model for efficient statistical inference; such surrogate models include Gaussian synthetic likelihoods and more recently neural density estimators such as autoregressive models and normalizing flows. To date, however, there is no consistent way of quantifying the quality of such a fit. Here we propose a statistical framework that can distinguish any arbitrary misspecified model from the target likelihood, and that in addition can identify with statistical confidence the regions of parameter as well as feature space where the fit is inadequate. Our validation method applies to settings where simulations are extremely costly and generated in batches or “ensembles” at fixed locations in parameter space. At the heart of our approach is a two-sample test that quantifies the quality of the fit at fixed parameter values, and a global test that assesses goodness-of-fit across simulation parameters. While our general framework can incorporate any test statistic or distance metric, we specifically argue for a new two-sample test that can leverage any regression method to attain high power and provide diagnostics in complex data settings. |
| Tasks | |
| Published | 2019-05-27 |
| URL | https://arxiv.org/abs/1905.11505v2 |
| https://arxiv.org/pdf/1905.11505v2.pdf | |
| PWC | https://paperswithcode.com/paper/validation-of-approximate-likelihood-and |
| Repo | |
| Framework | |
A spiking neural algorithm for the Network Flow problem
| Title | A spiking neural algorithm for the Network Flow problem |
| Authors | Abdullahi Ali, Johan Kwisthout |
| Abstract | It is currently not clear what the potential is of neuromorphic hardware beyond machine learning and neuroscience. In this project, a problem is investigated that is inherently difficult to fully implement in neuromorphic hardware by introducing a new machine model in which a conventional Turing machine and neuromorphic oracle work together to solve such types of problems. We show that the P-complete Max Network Flow problem is intractable in models where the oracle may be consulted only once (create-and-run' model) but becomes tractable using an interactive (neuromorphic co-processor’) model of computation. More in specific we show that a logspace-constrained Turing machine with access to an interactive neuromorphic oracle with linear space, time, and energy constraints can solve Max Network Flow. A modified variant of this algorithm is implemented on the Intel Loihi chip; a neuromorphic manycore processor developed by Intel Labs. We show that by off-loading the search for augmenting paths to the neuromorphic processor we can get energy efficiency gains, while not sacrificing runtime resources. This result demonstrates how P-complete problems can be mapped on neuromorphic architectures in a theoretically and potentially practically efficient manner. |
| Tasks | |
| Published | 2019-11-29 |
| URL | https://arxiv.org/abs/1911.13097v1 |
| https://arxiv.org/pdf/1911.13097v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-spiking-neural-algorithm-for-the-network |
| Repo | |
| Framework | |
Resource Allocation in Mobility-Aware Federated Learning Networks: A Deep Reinforcement Learning Approach
| Title | Resource Allocation in Mobility-Aware Federated Learning Networks: A Deep Reinforcement Learning Approach |
| Authors | Huy T. Nguyen, Nguyen Cong Luong, Jun Zhao, Chau Yuen, Dusit Niyato |
| Abstract | Federated learning allows mobile devices, i.e., workers, to use their local data to collaboratively train a global model required by the model owner. Federated learning thus addresses the privacy issues of traditional machine learning. However, federated learning faces the energy constraints of the workers and the high network resource cost due to the fact that a number of global model transmissions may be required to achieve the target accuracy. To address the energy constraint, a power beacon can be used that recharges energy to the workers. However, the model owner may need to pay an energy cost to the power beacon for the energy recharge. To address the high network resource cost, the model owner can use a WiFi channel, called default channel, for the global model transmissions. However, communication interruptions may occur due to the instability of the default channel quality. For this, special channels such as LTE channels can be used, but this incurs channel cost. As such, the problem of the model owner is to decide amounts of energy recharged to the workers and to choose channels used to transmit its global model to the workers to maximize the number of global model transmissions while minimizing the energy and channel costs. This is challenging for the model owner under the uncertainty of the channel, energy and mobility states of the workers. In this paper, we thus propose to employ the Deep Q-Network (DQN) that enables the model owner to find the optimal decisions on the energy and the channels without any a priori network knowledge. Simulation results show that the proposed DQN always achieves better performance compared to the conventional algorithms. |
| Tasks | |
| Published | 2019-10-21 |
| URL | https://arxiv.org/abs/1910.09172v1 |
| https://arxiv.org/pdf/1910.09172v1.pdf | |
| PWC | https://paperswithcode.com/paper/resource-allocation-in-mobility-aware |
| Repo | |
| Framework | |
Few-Shot Viewpoint Estimation
| Title | Few-Shot Viewpoint Estimation |
| Authors | Hung-Yu Tseng, Shalini De Mello, Jonathan Tremblay, Sifei Liu, Stan Birchfield, Ming-Hsuan Yang, Jan Kautz |
| Abstract | Viewpoint estimation for known categories of objects has been improved significantly thanks to deep networks and large datasets, but generalization to unknown categories is still very challenging. With an aim towards improving performance on unknown categories, we introduce the problem of category-level few-shot viewpoint estimation. We design a novel framework to successfully train viewpoint networks for new categories with few examples (10 or less). We formulate the problem as one of learning to estimate category-specific 3D canonical shapes, their associated depth estimates, and semantic 2D keypoints. We apply meta-learning to learn weights for our network that are amenable to category-specific few-shot fine-tuning. Furthermore, we design a flexible meta-Siamese network that maximizes information sharing during meta-learning. Through extensive experimentation on the ObjectNet3D and Pascal3D+ benchmark datasets, we demonstrate that our framework, which we call MetaView, significantly outperforms fine-tuning the state-of-the-art models with few examples, and that the specific architectural innovations of our method are crucial to achieving good performance. |
| Tasks | Meta-Learning, Viewpoint Estimation |
| Published | 2019-05-13 |
| URL | https://arxiv.org/abs/1905.04957v2 |
| https://arxiv.org/pdf/1905.04957v2.pdf | |
| PWC | https://paperswithcode.com/paper/few-shot-viewpoint-estimation |
| Repo | |
| Framework | |
Understanding the Curse of Horizon in Off-Policy Evaluation via Conditional Importance Sampling
| Title | Understanding the Curse of Horizon in Off-Policy Evaluation via Conditional Importance Sampling |
| Authors | Yao Liu, Pierre-Luc Bacon, Emma Brunskill |
| Abstract | We establish a connection between the importance sampling estimators typically used for off-policy policy evaluation in reinforcement learning and the extended conditional Monte Carlo method. We show with some examples that in the finite horizon case there is no strict ordering in general between the variance of such conditional importance sampling estimators: the variance of the per-decision or stationary variants may, in fact, be higher than that of the crude importance sampling estimator. We also provide sufficient conditions for the finite horizon case under which the per-decision or stationary estimators can reduce the variance. We then develop an asymptotic analysis and derive sufficient conditions under which there exists an exponential v.s. polynomial gap (in terms of horizon $T$) between the variance of importance sampling and that of the per-decision or stationary estimators. |
| Tasks | |
| Published | 2019-10-15 |
| URL | https://arxiv.org/abs/1910.06508v1 |
| https://arxiv.org/pdf/1910.06508v1.pdf | |
| PWC | https://paperswithcode.com/paper/understanding-the-curse-of-horizon-in-off |
| Repo | |
| Framework | |
Influence maximization in unknown social networks: Learning Policies for Effective Graph Sampling
| Title | Influence maximization in unknown social networks: Learning Policies for Effective Graph Sampling |
| Authors | Harshavardhan Kamarthi, Priyesh Vijayan, Bryan Wilder, Balaraman Ravindran, Milind Tambe |
| Abstract | A serious challenge when finding influential actors in real-world social networks is the lack of knowledge about the structure of the underlying network. Current state-of-the-art methods rely on hand-crafted sampling algorithms; these methods sample nodes and their neighbours in a carefully constructed order and choose opinion leaders from this discovered network to maximize influence spread in the (unknown) complete network. In this work, we propose a reinforcement learning framework for network discovery that automatically learns useful node and graph representations that encode important structural properties of the network. At training time, the method identifies portions of the network such that the nodes selected from this sampled subgraph can effectively influence nodes in the complete network. The realization of such transferable network structure based adaptable policies is attributed to the meticulous design of the framework that encodes relevant node and graph signatures driven by an appropriate reward scheme. We experiment with real-world social networks from four different domains and show that the policies learned by our RL agent provide a 10-36% improvement over the current state-of-the-art method. |
| Tasks | |
| Published | 2019-07-08 |
| URL | https://arxiv.org/abs/1907.11625v5 |
| https://arxiv.org/pdf/1907.11625v5.pdf | |
| PWC | https://paperswithcode.com/paper/learning-policies-for-social-network |
| Repo | |
| Framework | |
Evaluating Explanation Methods for Deep Learning in Security
| Title | Evaluating Explanation Methods for Deep Learning in Security |
| Authors | Alexander Warnecke, Daniel Arp, Christian Wressnegger, Konrad Rieck |
| Abstract | Deep learning is increasingly used as a building block of security systems. Unfortunately, neural networks are hard to interpret and typically opaque to the practitioner. The machine learning community has started to address this problem by developing methods for explaining the predictions of neural networks. While several of these approaches have been successfully applied in the area of computer vision, their application in security has received little attention so far. It is an open question which explanation methods are appropriate for computer security and what requirements they need to satisfy. In this paper, we introduce criteria for comparing and evaluating explanation methods in the context of computer security. These cover general properties, such as the accuracy of explanations, as well as security-focused aspects, such as the completeness, efficiency, and robustness. Based on our criteria, we investigate six popular explanation methods and assess their utility in security systems for malware detection and vulnerability discovery. We observe significant differences between the methods and build on these to derive general recommendations for selecting and applying explanation methods in computer security. |
| Tasks | Malware Detection |
| Published | 2019-06-05 |
| URL | https://arxiv.org/abs/1906.02108v3 |
| https://arxiv.org/pdf/1906.02108v3.pdf | |
| PWC | https://paperswithcode.com/paper/dont-paint-it-black-white-box-explanations |
| Repo | |
| Framework | |
Incremental Few-Shot Learning for Pedestrian Attribute Recognition
| Title | Incremental Few-Shot Learning for Pedestrian Attribute Recognition |
| Authors | Liuyu Xiang, Xiaoming Jin, Guiguang Ding, Jungong Han, Leida Li |
| Abstract | Pedestrian attribute recognition has received increasing attention due to its important role in video surveillance applications. However, most existing methods are designed for a fixed set of attributes. They are unable to handle the incremental few-shot learning scenario, i.e. adapting a well-trained model to newly added attributes with scarce data, which commonly exists in the real world. In this work, we present a meta learning based method to address this issue. The core of our framework is a meta architecture capable of disentangling multiple attribute information and generalizing rapidly to new coming attributes. By conducting extensive experiments on the benchmark dataset PETA and RAP under the incremental few-shot setting, we show that our method is able to perform the task with competitive performances and low resource requirements. |
| Tasks | Few-Shot Learning, Meta-Learning, Pedestrian Attribute Recognition |
| Published | 2019-06-02 |
| URL | https://arxiv.org/abs/1906.00330v2 |
| https://arxiv.org/pdf/1906.00330v2.pdf | |
| PWC | https://paperswithcode.com/paper/190600330 |
| Repo | |
| Framework | |
ASPIRE: Automated Security Policy Implementation Using Reinforcement Learning
| Title | ASPIRE: Automated Security Policy Implementation Using Reinforcement Learning |
| Authors | Yoni Birman, Shaked Hindi, Gilad Katz, Asaf Shabtai |
| Abstract | Malware detection is an ever-present challenge for all organizational gatekeepers. Organizations often deploy numerous different malware detection tools, and then combine their output to produce a final classification for an inspected file. This approach has two significant drawbacks. First, it requires large amounts of computing resources and time since every incoming file needs to be analyzed by all detectors. Secondly, it is difficult to accurately and dynamically enforce a predefined security policy that comports with the needs of each organization (e.g., how tolerant is the organization to false negatives and false positives). In this study we propose ASPIRE, a reinforcement learning (RL)-based method for malware detection. Our approach receives the organizational policy – defined solely by the perceived costs of correct/incorrect classifications and of computing resources – and then dynamically assigns detection tools and sets the detection threshold for each inspected file. We demonstrate the effectiveness and robustness of our approach by conducting an extensive evaluation on multiple organizational policies. ASPIRE performed well in all scenarios, even achieving near-optimal accuracy of 96.21% (compared to an optimum of 96.86%) at approximately 20% of the running time of this baseline. |
| Tasks | Malware Detection |
| Published | 2019-05-25 |
| URL | https://arxiv.org/abs/1905.10517v1 |
| https://arxiv.org/pdf/1905.10517v1.pdf | |
| PWC | https://paperswithcode.com/paper/aspire-automated-security-policy |
| Repo | |
| Framework | |
New Tricks for Estimating Gradients of Expectations
| Title | New Tricks for Estimating Gradients of Expectations |
| Authors | Christian J. Walder, Paul Roussel, Richard Nock, Cheng Soon Ong, Masashi Sugiyama |
| Abstract | We derive a family of Monte Carlo estimators for gradients of expectations which is related to the log-derivative trick, but involves pairwise interactions between samples. The first of these comes from either a) introducing and approximating an integral representation based on the fundamental theorem of calculus, or b) applying the reparameterisation trick to an implicit parameterisation under infinitesimal perturbation of the parameters. From the former perspective we generalise to a reproducing kernel Hilbert space representation, giving rise to locality parameter in the pairwise interactions mentioned above. The resulting estimators are unbiased and shown to offer an independent component of useful information in comparison with the log-derivative estimator. Promising analytical and numerical examples confirm the intuitions behind the new estimators. |
| Tasks | |
| Published | 2019-01-31 |
| URL | https://arxiv.org/abs/1901.11311v2 |
| https://arxiv.org/pdf/1901.11311v2.pdf | |
| PWC | https://paperswithcode.com/paper/new-tricks-for-estimating-gradients-of |
| Repo | |
| Framework | |
The Blockchain Game: Synthesis of Byzantine Systems and Nash Equilibria
| Title | The Blockchain Game: Synthesis of Byzantine Systems and Nash Equilibria |
| Authors | Dongfang Zhao |
| Abstract | This position paper presents a synthesis viewpoint of blockchains from two orthogonal perspectives: fault-tolerant distributed systems and game theory. Specifically, we formulate a new game-theoretical problem in the context of blockchains and sketch a closed-form Nash equilibrium to the problem. |
| Tasks | |
| Published | 2019-12-20 |
| URL | https://arxiv.org/abs/1912.09644v1 |
| https://arxiv.org/pdf/1912.09644v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-blockchain-game-synthesis-of-byzantine |
| Repo | |
| Framework | |
Deep Graph-Convolutional Image Denoising
| Title | Deep Graph-Convolutional Image Denoising |
| Authors | Diego Valsesia, Giulia Fracastoro, Enrico Magli |
| Abstract | Non-local self-similarity is well-known to be an effective prior for the image denoising problem. However, little work has been done to incorporate it in convolutional neural networks, which surpass non-local model-based methods despite only exploiting local information. In this paper, we propose a novel end-to-end trainable neural network architecture employing layers based on graph convolution operations, thereby creating neurons with non-local receptive fields. The graph convolution operation generalizes the classic convolution to arbitrary graphs. In this work, the graph is dynamically computed from similarities among the hidden features of the network, so that the powerful representation learning capabilities of the network are exploited to uncover self-similar patterns. We introduce a lightweight Edge-Conditioned Convolution which addresses vanishing gradient and over-parameterization issues of this particular graph convolution. Extensive experiments show state-of-the-art performance with improved qualitative and quantitative results on both synthetic Gaussian noise and real noise. |
| Tasks | Denoising, Image Denoising, Representation Learning |
| Published | 2019-07-19 |
| URL | https://arxiv.org/abs/1907.08448v1 |
| https://arxiv.org/pdf/1907.08448v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-graph-convolutional-image-denoising |
| Repo | |
| Framework | |
Unaligned Sequence Similarity Search Using Deep Learning
| Title | Unaligned Sequence Similarity Search Using Deep Learning |
| Authors | James K. Senter, Taylor M. Royalty, Andrew D. Steen, Amir Sadovnik |
| Abstract | Gene annotation has traditionally required direct comparison of DNA sequences between an unknown gene and a database of known ones using string comparison methods. However, these methods do not provide useful information when a gene does not have a close match in the database. In addition, each comparison can be costly when the database is large since it requires alignments and a series of string comparisons. In this work we propose a novel approach: using recurrent neural networks to embed DNA or amino-acid sequences in a low-dimensional space in which distances correlate with functional similarity. This embedding space overcomes both shortcomings of the method of aligning sequences and comparing homology. First, it allows us to obtain information about genes which do not have exact matches by measuring their similarity to other ones in the database. If our database is labeled this can provide labels for a query gene as is done in traditional methods. However, even if the database is unlabeled it allows us to find clusters and infer some characteristics of the gene population. In addition, each comparison is much faster than traditional methods since the distance metric is reduced to the Euclidean distance, and thus efficient approximate nearest neighbor algorithms can be used to find the best match. We present results showing the advantage of our algorithm. More specifically we show how our embedding can be useful for both classification tasks when our labels are known, and clustering tasks where our sequences belong to classes which have not been seen before. |
| Tasks | |
| Published | 2019-09-16 |
| URL | https://arxiv.org/abs/1909.06929v1 |
| https://arxiv.org/pdf/1909.06929v1.pdf | |
| PWC | https://paperswithcode.com/paper/unaligned-sequence-similarity-search-using |
| Repo | |
| Framework | |
Dim the Lights! – Low-Rank Prior Temporal Data for Specular-Free Video Recovery
| Title | Dim the Lights! – Low-Rank Prior Temporal Data for Specular-Free Video Recovery |
| Authors | Samar M. Alsaleh, Angelica I. Aviles-Rivero, Noemie Debroux, James K. Hahn |
| Abstract | The appearance of an object is significantly affected by the illumination conditions in the environment. This is more evident with strong reflective objects as they suffer from more dominant specular reflections, causing information loss and discontinuity in the image domain. In this paper, we present a novel framework for specular-free video recovery with special emphasis on dealing with complex motions coming from objects or camera. Our solution is a twostep approach that allows for both detection and restoration of the damaged regions on video data. We first propose a spatially adaptive detection term that searches for the damage areas. We then introduce a variational solution for specular-free video recovery that allows exploiting spatio-temporal correlations by representing prior data in a low-rank form. We demonstrate that our solution prevents major drawbacks of existing approaches while improving the performance in both detection accuracy and inpainting quality. Finally, we show that our approach can be applied to other problems such as object removal. |
| Tasks | |
| Published | 2019-12-17 |
| URL | https://arxiv.org/abs/1912.07764v1 |
| https://arxiv.org/pdf/1912.07764v1.pdf | |
| PWC | https://paperswithcode.com/paper/dim-the-lights-low-rank-prior-temporal-data |
| Repo | |
| Framework | |
