January 29, 2020

2906 words 14 mins read

Paper Group ANR 646

A Deep Reinforcement Learning based Approach to Learning Transferable Proof Guidance Strategies. Speeding Up Distributed Pseudo-tree Optimization Procedure with Cross Edge Consistency to Solve DCOPs. Graph Resistance and Learning from Pairwise Comparisons. No Peeking through My Windows: Conserving Privacy in Personal Drones. DEVDAN: Deep Evolving D …

A Deep Reinforcement Learning based Approach to Learning Transferable Proof Guidance Strategies


Title	A Deep Reinforcement Learning based Approach to Learning Transferable Proof Guidance Strategies
Authors	Maxwell Crouse, Ibrahim Abdelaziz, Bassem Makni, Spencer Whitehead, Cristina Cornelio, Pavan Kapanipathi, Edwin Pell, Kavitha Srinivas, Veronika Thost, Michael Witbrock, Achille Fokoue
Abstract	Traditional first-order logic (FOL) reasoning systems usually rely on manual heuristics for proof guidance. We propose TRAIL: a system that learns to perform proof guidance using reinforcement learning. A key design principle of our system is that it is general enough to allow transfer to problems in different domains that do not share the same vocabulary of the training set. To do so, we developed a novel representation of the internal state of a prover in terms of clauses and inference actions. We also propose a novel neural-based attention mechanism to learn interactions between clauses. We demonstrate that this approach enables the system to generalize from training to test data across domains with different vocabularies, suggesting that the neural architecture in TRAIL is well suited for representing and processing of logical formalisms. We also show that TRAIL’s learned strategies provide a comparable performance to an established heuristics-based theorem prover.
Tasks
Published	2019-11-05
URL	https://arxiv.org/abs/1911.02065v2
PDF	https://arxiv.org/pdf/1911.02065v2.pdf
PWC	https://paperswithcode.com/paper/a-deep-reinforcement-learning-based-approach
Repo
Framework

Speeding Up Distributed Pseudo-tree Optimization Procedure with Cross Edge Consistency to Solve DCOPs


Title	Speeding Up Distributed Pseudo-tree Optimization Procedure with Cross Edge Consistency to Solve DCOPs
Authors	Mashrur Rashik, Md. Musfiqur Rahman, Md. Mamun-or-Rashid, Md. Mosaddek Khan
Abstract	Distributed Pseudo-tree Optimization Procedure (DPOP) is a well-known message passing algorithm that has been used to provide optimal solutions of Distributed Constraint Optimization Problems (DCOPs) – a framework that is designed to optimize constraints in cooperative multi-agent systems. The traditional DCOP formulation does not consider those constraints that must be satisfied (also known as hard constraints), rather it concentrates only on soft constraints. However, the presence of both types of constraints are observed in a number of applications, such as Distributed Radio Link Frequency Assignment and Distributed Event Scheduling, etc. Although the combination of these types of constraints is recently incorporated in DPOP to solve DCOPs, scalability remains an issue for them as finding an optimal solution is NP-hard. Additionally, in DPOP, the agents are arranged as a DFS pseudo-tree. Recently it has been observed that the constructed pseudo-trees in this way often come to be chain-like and greatly impair the algorithm’s performance. To address these issues, we develop an algorithm that speeds up the DPOP algorithm by reducing the size of the messages exchanged and increasing parallelism in the pseudo tree. Our empirical evidence suggests that our approach outperforms the state-of-the-art algorithms by a significant margin.
Tasks
Published	2019-09-14
URL	https://arxiv.org/abs/1909.06537v1
PDF	https://arxiv.org/pdf/1909.06537v1.pdf
PWC	https://paperswithcode.com/paper/speeding-up-distributed-pseudo-tree
Repo
Framework

Graph Resistance and Learning from Pairwise Comparisons


Title	Graph Resistance and Learning from Pairwise Comparisons
Authors	Julien M. Hendrickx, Alex Olshevsky, Venkatesh Saligrama
Abstract	We consider the problem of learning the qualities of a collection of items by performing noisy comparisons among them. Following the standard paradigm, we assume there is a fixed “comparison graph” and every neighboring pair of items in this graph is compared $k$ times according to the Bradley-Terry-Luce model (where the probability than an item wins a comparison is proportional the item quality). We are interested in how the relative error in quality estimation scales with the comparison graph in the regime where $k$ is large. We prove that, after a known transition period, the relevant graph-theoretic quantity is the square root of the resistance of the comparison graph. Specifically, we provide an algorithm that is minimax optimal. The algorithm has a relative error decay that scales with the square root of the graph resistance, and provide a matching lower bound (up to log factors). The performance guarantee of our algorithm, both in terms of the graph and the skewness of the item quality distribution, outperforms earlier results.
Tasks
Published	2019-02-01
URL	https://arxiv.org/abs/1902.00141v2
PDF	https://arxiv.org/pdf/1902.00141v2.pdf
PWC	https://paperswithcode.com/paper/graph-resistance-and-learning-from-pairwise
Repo
Framework

No Peeking through My Windows: Conserving Privacy in Personal Drones


Title	No Peeking through My Windows: Conserving Privacy in Personal Drones
Authors	Alem Fitwi, Yu Chen, Sencun Zhu
Abstract	The drone technology has been increasingly used by many tech-savvy consumers, a number of defense companies, hobbyists and enthusiasts during the last ten years. Drones often come in various sizes and are designed for a multitude of purposes. Nowadays many people have small-sized personal drones for entertainment, filming, or transporting items from one place to another. However, personal drones lack a privacy-preserving mechanism. While in mission, drones often trespass into the personal territories of other people and capture photos or videos through windows without their knowledge and consent. They may also capture video or pictures of people walking, sitting, or doing private things within the drones’ reach in clear form without their go permission. This could potentially invade people’s personal privacy. This paper, therefore, proposes a lightweight privacy-preserving-by-design method that prevents drones from peeking through windows of houses and capturing people doing private things at home. It is a fast window object detection and scrambling technology built based on image-enhancing, morphological transformation, segmentation and contouring processes (MASP). Besides, a chaotic scrambling technique is incorporated into it for privacy purpose. Hence, this mechanism detects window objects in every image or frame of a real-time video and masks them chaotically to protect the privacy of people. The experimental results validated that the proposed MASP method is lightweight and suitable to be employed in drones, considered as edge devices.
Tasks	Object Detection
Published	2019-08-26
URL	https://arxiv.org/abs/1908.09935v1
PDF	https://arxiv.org/pdf/1908.09935v1.pdf
PWC	https://paperswithcode.com/paper/no-peeking-through-my-windows-conserving
Repo
Framework

DEVDAN: Deep Evolving Denoising Autoencoder


Title	DEVDAN: Deep Evolving Denoising Autoencoder
Authors	Andri Ashfahani, Mahardhika Pratama, Edwin Lughofer, Yew Soon Ong
Abstract	The Denoising Autoencoder (DAE) enhances the flexibility of the data stream method in exploiting unlabeled samples. Nonetheless, the feasibility of DAE for data stream analytic deserves an in-depth study because it characterizes a fixed network capacity that cannot adapt to rapidly changing environments. Deep evolving denoising autoencoder (DEVDAN), is proposed in this paper. It features an open structure in the generative phase and the discriminative phase where the hidden units can be automatically added and discarded on the fly. The generative phase refines the predictive performance of the discriminative model exploiting unlabeled data. Furthermore, DEVDAN is free of the problem-specific threshold and works fully in the single-pass learning fashion. We show that DEVDAN can find competitive network architecture compared with state-of-the-art methods on the classification task using ten prominent datasets simulated under the prequential test-then-train protocol.
Tasks	Denoising
Published	2019-10-08
URL	https://arxiv.org/abs/1910.04062v2
PDF	https://arxiv.org/pdf/1910.04062v2.pdf
PWC	https://paperswithcode.com/paper/devdan-deep-evolving-denoising-autoencoder
Repo
Framework

IsMo-GAN: Adversarial Learning for Monocular Non-Rigid 3D Reconstruction


Title	IsMo-GAN: Adversarial Learning for Monocular Non-Rigid 3D Reconstruction
Authors	Soshi Shimada, Vladislav Golyanik, Christian Theobalt, Didier Stricker
Abstract	The majority of the existing methods for non-rigid 3D surface regression from monocular 2D images require an object template or point tracks over multiple frames as an input, and are still far from real-time processing rates. In this work, we present the Isometry-Aware Monocular Generative Adversarial Network (IsMo-GAN) - an approach for direct 3D reconstruction from a single image, trained for the deformation model in an adversarial manner on a light-weight synthetic dataset. IsMo-GAN reconstructs surfaces from real images under varying illumination, camera poses, textures and shading at over 250 Hz. In multiple experiments, it consistently outperforms several approaches in the reconstruction accuracy, runtime, generalisation to unknown surfaces and robustness to occlusions. In comparison to the state-of-the-art, we reduce the reconstruction error by 10-30% including the textureless case and our surfaces evince fewer artefacts qualitatively.
Tasks	3D Reconstruction
Published	2019-04-27
URL	http://arxiv.org/abs/1904.12144v1
PDF	http://arxiv.org/pdf/1904.12144v1.pdf
PWC	https://paperswithcode.com/paper/ismo-gan-adversarial-learning-for-monocular
Repo
Framework

Beyond the Grounding Bottleneck: Datalog Techniques for Inference in Probabilistic Logic Programs (Technical Report)


Title	Beyond the Grounding Bottleneck: Datalog Techniques for Inference in Probabilistic Logic Programs (Technical Report)
Authors	Efthymia Tsamoura, Victor Gutierrez-Basulto, Angelika Kimmig
Abstract	State-of-the-art inference approaches in probabilistic logic programming typically start by computing the relevant ground program with respect to the queries of interest, and then use this program for probabilistic inference using knowledge compilation and weighted model counting. We propose an alternative approach that uses efficient Datalog techniques to integrate knowledge compilation with forward reasoning with a non-ground program. This effectively eliminates the grounding bottleneck that so far has prohibited the application of probabilistic logic programming in query answering scenarios over knowledge graphs, while also providing fast approximations on classical benchmarks in the field.
Tasks	Knowledge Graphs
Published	2019-11-18
URL	https://arxiv.org/abs/1911.07750v1
PDF	https://arxiv.org/pdf/1911.07750v1.pdf
PWC	https://paperswithcode.com/paper/beyond-the-grounding-bottleneck-datalog
Repo
Framework

On the Fairness of Disentangled Representations


Title	On the Fairness of Disentangled Representations
Authors	Francesco Locatello, Gabriele Abbati, Tom Rainforth, Stefan Bauer, Bernhard Schölkopf, Olivier Bachem
Abstract	Recently there has been a significant interest in learning disentangled representations, as they promise increased interpretability, generalization to unseen scenarios and faster learning on downstream tasks. In this paper, we investigate the usefulness of different notions of disentanglement for improving the fairness of downstream prediction tasks based on representations. We consider the setting where the goal is to predict a target variable based on the learned representation of high-dimensional observations (such as images) that depend on both the target variable and an \emph{unobserved} sensitive variable. We show that in this setting both the optimal and empirical predictions can be unfair, even if the target variable and the sensitive variable are independent. Analyzing the representations of more than \num{12600} trained state-of-the-art disentangled models, we observe that several disentanglement scores are consistently correlated with increased fairness, suggesting that disentanglement may be a useful property to encourage fairness when sensitive variables are not observed.
Tasks
Published	2019-05-31
URL	https://arxiv.org/abs/1905.13662v2
PDF	https://arxiv.org/pdf/1905.13662v2.pdf
PWC	https://paperswithcode.com/paper/on-the-fairness-of-disentangled
Repo
Framework

Making Efficient Use of Demonstrations to Solve Hard Exploration Problems


Title	Making Efficient Use of Demonstrations to Solve Hard Exploration Problems
Authors	Tom Le Paine, Caglar Gulcehre, Bobak Shahriari, Misha Denil, Matt Hoffman, Hubert Soyer, Richard Tanburn, Steven Kapturowski, Neil Rabinowitz, Duncan Williams, Gabriel Barth-Maron, Ziyu Wang, Nando de Freitas, Worlds Team
Abstract	This paper introduces R2D3, an agent that makes efficient use of demonstrations to solve hard exploration problems in partially observable environments with highly variable initial conditions. We also introduce a suite of eight tasks that combine these three properties, and show that R2D3 can solve several of the tasks where other state of the art methods (both with and without demonstrations) fail to see even a single successful trajectory after tens of billions of steps of exploration.
Tasks
Published	2019-09-03
URL	https://arxiv.org/abs/1909.01387v1
PDF	https://arxiv.org/pdf/1909.01387v1.pdf
PWC	https://paperswithcode.com/paper/making-efficient-use-of-demonstrations-to
Repo
Framework

Re-ranking Based Diversification: A Unifying View


Title	Re-ranking Based Diversification: A Unifying View
Authors	Shameem A Puthiya Parambath
Abstract	We analyze different re-ranking algorithms for diversification and show that majority of them are based on maximizing submodular/modular functions from the class of parameterized concave/linear over modular functions. We study the optimality of such algorithms in terms of the `total curvature'. We also show that by adjusting the hyperparameter of the concave/linear composition to trade-off relevance and diversity, if any, one is in fact tuning the` total curvature’ of the function for relevance-diversity trade-off.
Tasks
Published	2019-06-26
URL	https://arxiv.org/abs/1906.11285v1
PDF	https://arxiv.org/pdf/1906.11285v1.pdf
PWC	https://paperswithcode.com/paper/re-ranking-based-diversification-a-unifying
Repo
Framework

Moral Dilemmas for Artificial Intelligence: a position paper on an application of Compositional Quantum Cognition


Title	Moral Dilemmas for Artificial Intelligence: a position paper on an application of Compositional Quantum Cognition
Authors	Camilo M. Signorelli, Xerxes D. Arsiwalla
Abstract	Traditionally, the way one evaluates the performance of an Artificial Intelligence (AI) system is via a comparison to human performance in specific tasks, treating humans as a reference for high-level cognition. However, these comparisons leave out important features of human intelligence: the capability to transfer knowledge and make complex decisions based on emotional and rational reasoning. These decisions are influenced by current inferences as well as prior experiences, making the decision process strongly subjective and apparently biased. In this context, a definition of compositional intelligence is necessary to incorporate these features in future AI tests. Here, a concrete implementation of this will be suggested, using recent developments in quantum cognition, natural language and compositional meaning of sentences, thanks to categorical compositional models of meaning.
Tasks
Published	2019-11-22
URL	https://arxiv.org/abs/1911.10154v1
PDF	https://arxiv.org/pdf/1911.10154v1.pdf
PWC	https://paperswithcode.com/paper/moral-dilemmas-for-artificial-intelligence-a
Repo
Framework

On an Optimal Solution to the Film Scheduling and Showtime Staggering Problem


Title	On an Optimal Solution to the Film Scheduling and Showtime Staggering Problem
Authors	Ikjyot Singh Kohli, Katherine Goff Inglis
Abstract	The scheduling of films is a major problem for the movie theatre exhibition business. The problem is two-fold: movie exhibitors ideally would like to schedule films to screens in their various locations to maximize attendance and revenue, but would also like to schedule these films such that neighbouring theatre locations play the same films at different times thus giving guests a multitude of showtime options. We refer to this latter problem as the showtime \emph{staggering} problem. We give an exact formulation of this scheduling problem using binary integer linear optimization, and provide a solved example as well. This work further shows that the optimal scheduling of films cannot be done across all theatre locations at once, but rather, must be done for each cluster of neighbouring locations.
Tasks
Published	2019-11-22
URL	https://arxiv.org/abs/1911.10153v1
PDF	https://arxiv.org/pdf/1911.10153v1.pdf
PWC	https://paperswithcode.com/paper/on-an-optimal-solution-to-the-film-scheduling
Repo
Framework

Cross-Modality Attention with Semantic Graph Embedding for Multi-Label Classification


Title	Cross-Modality Attention with Semantic Graph Embedding for Multi-Label Classification
Authors	Renchun You, Zhiyao Guo, Lei Cui, Xiang Long, Yingze Bao, Shilei Wen
Abstract	Multi-label image and video classification are fundamental yet challenging tasks in computer vision. The main challenges lie in capturing spatial or temporal dependencies between labels and discovering the locations of discriminative features for each class. In order to overcome these challenges, we propose to use cross-modality attention with semantic graph embedding for multi label classification. Based on the constructed label graph, we propose an adjacency-based similarity graph embedding method to learn semantic label embeddings, which explicitly exploit label relationships. Then our novel cross-modality attention maps are generated with the guidance of learned label embeddings. Experiments on two multi-label image classification datasets (MS-COCO and NUS-WIDE) show our method outperforms other existing state-of-the-arts. In addition, we validate our method on a large multi-label video classification dataset (YouTube-8M Segments) and the evaluation results demonstrate the generalization capability of our method.
Tasks	Graph Embedding, Image Classification, Multi-Label Classification, Video Classification
Published	2019-12-17
URL	https://arxiv.org/abs/1912.07872v2
PDF	https://arxiv.org/pdf/1912.07872v2.pdf
PWC	https://paperswithcode.com/paper/cross-modality-attention-with-semantic-graph
Repo
Framework

Adversarial Learning of Privacy-Preserving and Task-Oriented Representations


Title	Adversarial Learning of Privacy-Preserving and Task-Oriented Representations
Authors	Taihong Xiao, Yi-Hsuan Tsai, Kihyuk Sohn, Manmohan Chandraker, Ming-Hsuan Yang
Abstract	Data privacy has emerged as an important issue as data-driven deep learning has been an essential component of modern machine learning systems. For instance, there could be a potential privacy risk of machine learning systems via the model inversion attack, whose goal is to reconstruct the input data from the latent representation of deep networks. Our work aims at learning a privacy-preserving and task-oriented representation to defend against such model inversion attacks. Specifically, we propose an adversarial reconstruction learning framework that prevents the latent representations decoded into original input data. By simulating the expected behavior of adversary, our framework is realized by minimizing the negative pixel reconstruction loss or the negative feature reconstruction (i.e., perceptual distance) loss. We validate the proposed method on face attribute prediction, showing that our method allows protecting visual privacy with a small decrease in utility performance. In addition, we show the utility-privacy trade-off with different choices of hyperparameter for negative perceptual distance loss at training, allowing service providers to determine the right level of privacy-protection with a certain utility performance. Moreover, we provide an extensive study with different selections of features, tasks, and the data to further analyze their influence on privacy protection.
Tasks
Published	2019-11-22
URL	https://arxiv.org/abs/1911.10143v1
PDF	https://arxiv.org/pdf/1911.10143v1.pdf
PWC	https://paperswithcode.com/paper/adversarial-learning-of-privacy-preserving-2
Repo
Framework

A laboratory-created dataset with ground-truth for hyperspectral unmixing evaluation


Title	A laboratory-created dataset with ground-truth for hyperspectral unmixing evaluation
Authors	Min Zhao, Jie Chen, Zhe He
Abstract	Spectral unmixing is an important and challenging problem in hyperspectral data processing. This topic has been extensively studied and a variety of unmixing algorithms have been proposed in the literature. However, the lack of publicly available dataset with ground-truth makes it difficult to evaluate and compare the performance of unmixing algorithms in a quantitative and objective manner. Most of the existing works rely on the use of numerical synthetic data and an intuitive inspection of the results of real data. To alleviate this dilemma, in this study, we design several experimental scenes in our laboratory, including printed checkerboards, mixed quartz sands, and reflection with a vertical board. A dataset is then created by imaging these scenes with the hyperspectral camera in our laboratory, providing 36 mixtures with more than 130, 000 pixels with 256 wavelength bands ranging from 400nm to 1000nm. The experimental settings are strictly controlled so that pure material spectral signatures and material compositions are known. To the best of our knowledge, this dataset is the first publicly available dataset created in a systematic manner with ground-truth for spectral unmixing. Some typical linear and nonlinear unmixing algorithms are also tested with this dataset and lead to meaningful results.
Tasks	Hyperspectral Unmixing
Published	2019-02-22
URL	http://arxiv.org/abs/1902.08347v1
PDF	http://arxiv.org/pdf/1902.08347v1.pdf
PWC	https://paperswithcode.com/paper/a-laboratory-created-dataset-with-ground
Repo
Framework