October 19, 2019

2816 words 14 mins read

Paper Group ANR 274

Enhancement of land-use change modeling using convolutional neural networks and convolutional denoising autoencoders. Low-Rank Phase Retrieval via Variational Bayesian Learning. Specifying and Verbalising Answer Set Programs in Controlled Natural Language. Training convolutional neural networks with megapixel images. Neural Network-Based Approach t …

Enhancement of land-use change modeling using convolutional neural networks and convolutional denoising autoencoders


Title	Enhancement of land-use change modeling using convolutional neural networks and convolutional denoising autoencoders
Authors	Guodong Du, Liang Yuan, Kong Joo Shin, Shunsuke Managi
Abstract	The neighborhood effect is a key driving factor for the land-use change (LUC) process. This study applies convolutional neural networks (CNN) to capture neighborhood characteristics from satellite images and to enhance the performance of LUC modeling. We develop a hybrid CNN model (conv-net) to predict the LU transition probability by combining satellite images and geographical features. A spatial weight layer is designed to incorporate the distance-decay characteristics of neighborhood effect into conv-net. As an alternative model, we also develop a hybrid convolutional denoising autoencoder and multi-layer perceptron model (CDAE-net), which specifically learns latent representations from satellite images and denoises the image data. Finally, a DINAMICA-based cellular automata (CA) model simulates the LU pattern. The results show that the convolutional-based models improve the modeling performances compared with a model that accepts only the geographical features. Overall, conv-net outperforms CDAE-net in terms of LUC predictive performance. Nonetheless, CDAE-net performs better when the data are noisy.
Tasks	Denoising
Published	2018-03-03
URL	http://arxiv.org/abs/1803.01159v1
PDF	http://arxiv.org/pdf/1803.01159v1.pdf
PWC	https://paperswithcode.com/paper/enhancement-of-land-use-change-modeling-using
Repo
Framework

Low-Rank Phase Retrieval via Variational Bayesian Learning


Title	Low-Rank Phase Retrieval via Variational Bayesian Learning
Authors	Kaihui Liu, Jiayi Wang, Zhengli Xing, Linxiao Yang, Jun Fang
Abstract	In this paper, we consider the problem of low-rank phase retrieval whose objective is to estimate a complex low-rank matrix from magnitude-only measurements. We propose a hierarchical prior model for low-rank phase retrieval, in which a Gaussian-Wishart hierarchical prior is placed on the underlying low-rank matrix to promote the low-rankness of the matrix. Based on the proposed hierarchical model, a variational expectation-maximization (EM) algorithm is developed. The proposed method is less sensitive to the choice of the initialization point and works well with random initialization. Simulation results are provided to illustrate the effectiveness of the proposed algorithm.
Tasks
Published	2018-11-05
URL	http://arxiv.org/abs/1811.01574v1
PDF	http://arxiv.org/pdf/1811.01574v1.pdf
PWC	https://paperswithcode.com/paper/low-rank-phase-retrieval-via-variational
Repo
Framework

Specifying and Verbalising Answer Set Programs in Controlled Natural Language


Title	Specifying and Verbalising Answer Set Programs in Controlled Natural Language
Authors	Rolf Schwitter
Abstract	We show how a bi-directional grammar can be used to specify and verbalise answer set programs in controlled natural language. We start from a program specification in controlled natural language and translate this specification automatically into an executable answer set program. The resulting answer set program can be modified following certain naming conventions and the revised version of the program can then be verbalised in the same subset of natural language that was used as specification language. The bi-directional grammar is parametrised for processing and generation, deals with referring expressions, and exploits symmetries in the data structure of the grammar rules whenever these grammar rules need to be duplicated. We demonstrate that verbalisation requires sentence planning in order to aggregate similar structures with the aim to improve the readability of the generated specification. Without modifications, the generated specification is always semantically equivalent to the original one; our bi-directional grammar is the first one that allows for semantic round-tripping in the context of controlled natural language processing. This paper is under consideration for acceptance in TPLP.
Tasks
Published	2018-04-28
URL	http://arxiv.org/abs/1804.10765v1
PDF	http://arxiv.org/pdf/1804.10765v1.pdf
PWC	https://paperswithcode.com/paper/specifying-and-verbalising-answer-set
Repo
Framework

Training convolutional neural networks with megapixel images


Title	Training convolutional neural networks with megapixel images
Authors	Hans Pinckaers, Geert Litjens
Abstract	To train deep convolutional neural networks, the input data and the intermediate activations need to be kept in memory to calculate the gradient descent step. Given the limited memory available in the current generation accelerator cards, this limits the maximum dimensions of the input data. We demonstrate a method to train convolutional neural networks holding only parts of the image in memory while giving equivalent results. We quantitatively compare this new way of training convolutional neural networks with conventional training. In addition, as a proof of concept, we train a convolutional neural network with 64 megapixel images, which requires 97% less memory than the conventional approach.
Tasks
Published	2018-04-16
URL	http://arxiv.org/abs/1804.05712v1
PDF	http://arxiv.org/pdf/1804.05712v1.pdf
PWC	https://paperswithcode.com/paper/training-convolutional-neural-networks-with
Repo
Framework

Neural Network-Based Approach to Phase Space Integration


Title	Neural Network-Based Approach to Phase Space Integration
Authors	Matthew D. Klimek, Maxim Perelstein
Abstract	Monte Carlo methods are widely used in particle physics to integrate and sample probability distributions (differential cross sections or decay rates) on multi-dimensional phase spaces. We present a Neural Network (NN) algorithm optimized to perform this task. The algorithm has been applied to several examples of direct relevance for particle physics, including situations with non-trivial features such as sharp resonances and soft/collinear enhancements. Excellent performance has been demonstrated in all examples, with the properly trained NN achieving unweighting efficiencies of between 30% and 75%. In contrast to traditional Monte Carlo algorithms such as VEGAS, the NN-based approach does not require that the phase space coordinates be aligned with resonant or other features in the cross section.
Tasks
Published	2018-10-26
URL	http://arxiv.org/abs/1810.11509v1
PDF	http://arxiv.org/pdf/1810.11509v1.pdf
PWC	https://paperswithcode.com/paper/neural-network-based-approach-to-phase-space
Repo
Framework

Reinforcement and Imitation Learning for Diverse Visuomotor Skills


Title	Reinforcement and Imitation Learning for Diverse Visuomotor Skills
Authors	Yuke Zhu, Ziyu Wang, Josh Merel, Andrei Rusu, Tom Erez, Serkan Cabi, Saran Tunyasuvunakool, János Kramár, Raia Hadsell, Nando de Freitas, Nicolas Heess
Abstract	We propose a model-free deep reinforcement learning method that leverages a small amount of demonstration data to assist a reinforcement learning agent. We apply this approach to robotic manipulation tasks and train end-to-end visuomotor policies that map directly from RGB camera inputs to joint velocities. We demonstrate that our approach can solve a wide variety of visuomotor tasks, for which engineering a scripted controller would be laborious. In experiments, our reinforcement and imitation agent achieves significantly better performances than agents trained with reinforcement learning or imitation learning alone. We also illustrate that these policies, trained with large visual and dynamics variations, can achieve preliminary successes in zero-shot sim2real transfer. A brief visual description of this work can be viewed in https://youtu.be/EDl8SQUNjj0
Tasks	Imitation Learning
Published	2018-02-26
URL	http://arxiv.org/abs/1802.09564v2
PDF	http://arxiv.org/pdf/1802.09564v2.pdf
PWC	https://paperswithcode.com/paper/reinforcement-and-imitation-learning-for
Repo
Framework

When can $l_p$-norm objective functions be minimized via graph cuts?


Title	When can $l_p$-norm objective functions be minimized via graph cuts?
Authors	Filip Malmberg, Robin Strand
Abstract	Techniques based on minimal graph cuts have become a standard tool for solving combinatorial optimization problems arising in image processing and computer vision applications. These techniques can be used to minimize objective functions written as the sum of a set of unary and pairwise terms, provided that the objective function is submodular. This can be interpreted as minimizing the $l_1$-norm of the vector containing all pairwise and unary terms. By raising each term to a power $p$, the same technique can also be used to minimize the $l_p$-norm of the vector. Unfortunately, the submodularity of an $l_1$-norm objective function does not guarantee the submodularity of the corresponding $l_p$-norm objective function. The contribution of this paper is to provide useful conditions under which an $l_p$-norm objective function is submodular for all $p\geq 1$, thereby identifying a large class of $l_p$-norm objective functions that can be minimized via minimal graph cuts.
Tasks	Combinatorial Optimization
Published	2018-02-02
URL	https://arxiv.org/abs/1802.00624v2
PDF	https://arxiv.org/pdf/1802.00624v2.pdf
PWC	https://paperswithcode.com/paper/when-can-l_p-norm-objective-functions-be
Repo
Framework

Subgoal Discovery for Hierarchical Dialogue Policy Learning


Title	Subgoal Discovery for Hierarchical Dialogue Policy Learning
Authors	Da Tang, Xiujun Li, Jianfeng Gao, Chong Wang, Lihong Li, Tony Jebara
Abstract	Developing agents to engage in complex goal-oriented dialogues is challenging partly because the main learning signals are very sparse in long conversations. In this paper, we propose a divide-and-conquer approach that discovers and exploits the hidden structure of the task to enable efficient policy learning. First, given successful example dialogues, we propose the Subgoal Discovery Network (SDN) to divide a complex goal-oriented task into a set of simpler subgoals in an unsupervised fashion. We then use these subgoals to learn a multi-level policy by hierarchical reinforcement learning. We demonstrate our method by building a dialogue agent for the composite task of travel planning. Experiments with simulated and real users show that our approach performs competitively against a state-of-the-art method that requires human-defined subgoals. Moreover, we show that the learned subgoals are often human comprehensible.
Tasks	Hierarchical Reinforcement Learning
Published	2018-04-20
URL	http://arxiv.org/abs/1804.07855v3
PDF	http://arxiv.org/pdf/1804.07855v3.pdf
PWC	https://paperswithcode.com/paper/subgoal-discovery-for-hierarchical-dialogue
Repo
Framework

Instance-Dependent PU Learning by Bayesian Optimal Relabeling


Title	Instance-Dependent PU Learning by Bayesian Optimal Relabeling
Authors	Fengxiang He, Tongliang Liu, Geoffrey I Webb, Dacheng Tao
Abstract	When learning from positive and unlabelled data, it is a strong assumption that the positive observations are randomly sampled from the distribution of $X$ conditional on $Y = 1$, where X stands for the feature and Y the label. Most existing algorithms are optimally designed under the assumption. However, for many real-world applications, the observed positive examples are dependent on the conditional probability $P(Y = 1X)$ and should be sampled biasedly. In this paper, we assume that a positive example with a higher $P(Y = 1X)$ is more likely to be labelled and propose a probabilistic-gap based PU learning algorithms. Specifically, by treating the unlabelled data as noisy negative examples, we could automatically label a group positive and negative examples whose labels are identical to the ones assigned by a Bayesian optimal classifier with a consistency guarantee. The relabelled examples have a biased domain, which is remedied by the kernel mean matching technique. The proposed algorithm is model-free and thus do not have any parameters to tune. Experimental results demonstrate that our method works well on both generated and real-world datasets.
Tasks
Published	2018-08-07
URL	https://arxiv.org/abs/1808.02180v2
PDF	https://arxiv.org/pdf/1808.02180v2.pdf
PWC	https://paperswithcode.com/paper/instance-dependent-pu-learning-by-bayesian
Repo
Framework

Decoupling Strategy and Generation in Negotiation Dialogues


Title	Decoupling Strategy and Generation in Negotiation Dialogues
Authors	He He, Derek Chen, Anusha Balakrishnan, Percy Liang
Abstract	We consider negotiation settings in which two agents use natural language to bargain on goods. Agents need to decide on both high-level strategy (e.g., proposing $50) and the execution of that strategy (e.g., generating “The bike is brand new. Selling for just $50."). Recent work on negotiation trains neural models, but their end-to-end nature makes it hard to control their strategy, and reinforcement learning tends to lead to degenerate solutions. In this paper, we propose a modular approach based on coarse di- alogue acts (e.g., propose(price=50)) that decouples strategy and generation. We show that we can flexibly set the strategy using supervised learning, reinforcement learning, or domain-specific knowledge without degeneracy, while our retrieval-based generation can maintain context-awareness and produce diverse utterances. We test our approach on the recently proposed DEALORNODEAL game, and we also collect a richer dataset based on real items on Craigslist. Human evaluation shows that our systems achieve higher task success rate and more human-like negotiation behavior than previous approaches.
Tasks
Published	2018-08-29
URL	http://arxiv.org/abs/1808.09637v1
PDF	http://arxiv.org/pdf/1808.09637v1.pdf
PWC	https://paperswithcode.com/paper/decoupling-strategy-and-generation-in
Repo
Framework

Inorganic Materials Synthesis Planning with Literature-Trained Neural Networks


Title	Inorganic Materials Synthesis Planning with Literature-Trained Neural Networks
Authors	Edward Kim, Zach Jensen, Alexander van Grootel, Kevin Huang, Matthew Staib, Sheshera Mysore, Haw-Shiuan Chang, Emma Strubell, Andrew McCallum, Stefanie Jegelka, Elsa Olivetti
Abstract	Leveraging new data sources is a key step in accelerating the pace of materials design and discovery. To complement the strides in synthesis planning driven by historical, experimental, and computed data, we present an automated method for connecting scientific literature to synthesis insights. Starting from natural language text, we apply word embeddings from language models, which are fed into a named entity recognition model, upon which a conditional variational autoencoder is trained to generate syntheses for arbitrary materials. We show the potential of this technique by predicting precursors for two perovskite materials, using only training data published over a decade prior to their first reported syntheses. We demonstrate that the model learns representations of materials corresponding to synthesis-related properties, and that the model’s behavior complements existing thermodynamic knowledge. Finally, we apply the model to perform synthesizability screening for proposed novel perovskite compounds.
Tasks	Named Entity Recognition, Word Embeddings
Published	2018-12-31
URL	http://arxiv.org/abs/1901.00032v2
PDF	http://arxiv.org/pdf/1901.00032v2.pdf
PWC	https://paperswithcode.com/paper/inorganic-materials-synthesis-planning-with
Repo
Framework

Activity-conditioned continuous human pose estimation for performance analysis of athletes using the example of swimming


Title	Activity-conditioned continuous human pose estimation for performance analysis of athletes using the example of swimming
Authors	Moritz Einfalt, Dan Zecha, Rainer Lienhart
Abstract	In this paper we consider the problem of human pose estimation in real-world videos of swimmers. Swimming channels allow filming swimmers simultaneously above and below the water surface with a single stationary camera. These recordings can be used to quantitatively assess the athletes’ performance. The quantitative evaluation, so far, requires manual annotations of body parts in each video frame. We therefore apply the concept of CNNs in order to automatically infer the required pose information. Starting with an off-the-shelf architecture, we develop extensions to leverage activity information - in our case the swimming style of an athlete - and the continuous nature of the video recordings. Our main contributions are threefold: (a) We apply and evaluate a fine-tuned Convolutional Pose Machine architecture as a baseline in our very challenging aquatic environment and discuss its error modes, (b) we propose an extension to input swimming style information into the fully convolutional architecture and (c) modify the architecture for continuous pose estimation in videos. With these additions we achieve reliable pose estimates with up to +16% more correct body joint detections compared to the baseline architecture.
Tasks	Pose Estimation
Published	2018-02-02
URL	http://arxiv.org/abs/1802.00634v1
PDF	http://arxiv.org/pdf/1802.00634v1.pdf
PWC	https://paperswithcode.com/paper/activity-conditioned-continuous-human-pose
Repo
Framework

Lecture Notes on Fair Division


Title	Lecture Notes on Fair Division
Authors	Ulle Endriss
Abstract	Fair division is the problem of dividing one or several goods amongst two or more agents in a way that satisfies a suitable fairness criterion. These Notes provide a succinct introduction to the field. We cover three main topics. First, we need to define what is to be understood by a “fair” allocation of goods to individuals. We present an overview of the most important fairness criteria (as well as the closely related criteria for economic efficiency) developed in the literature, together with a short discussion of their axiomatic foundations. Second, we give an introduction to cake-cutting procedures as an example of methods for fairly dividing a single divisible resource amongst a group of individuals. Third, we discuss the combinatorial optimisation problem of fairly allocating a set of indivisible goods to a group of agents, covering both centralised algorithms (similar to auctions) and a distributed approach based on negotiation. While the classical literature on fair division has largely developed within Economics, these Notes are specifically written for readers with a background in Computer Science or similar, and who may be (or may wish to be) engaged in research in Artificial Intelligence, Multiagent Systems, or Computational Social Choice. References for further reading, as well as a small number of exercises, are included. Notes prepared for a tutorial at the 11th European Agent Systems Summer School (EASSS-2009), Torino, Italy, 31 August and 1 September 2009. Updated for a tutorial at the COST-ADT Doctoral School on Computational Social Choice, Estoril, Portugal, 9–14 April 2010.
Tasks
Published	2018-06-11
URL	http://arxiv.org/abs/1806.04234v1
PDF	http://arxiv.org/pdf/1806.04234v1.pdf
PWC	https://paperswithcode.com/paper/lecture-notes-on-fair-division
Repo
Framework

Anomaly Detection for Network Connection Logs


Title	Anomaly Detection for Network Connection Logs
Authors	Swapneel Mehta, Prasanth Kothuri, Daniel Lanza Garcia
Abstract	We leverage a streaming architecture based on ELK, Spark and Hadoop in order to collect, store, and analyse database connection logs in near real-time. The proposed system investigates outliers using unsupervised learning; widely adopted clustering and classification algorithms for log data, highlighting the subtle variances in each model by visualisation of outliers. Arriving at a novel solution to evaluate untagged, unfiltered connection logs, we propose an approach that can be extrapolated to a generalised system of analysing connection logs across a large infrastructure comprising thousands of individual nodes and generating hundreds of lines in logs per second.
Tasks	Anomaly Detection
Published	2018-12-01
URL	http://arxiv.org/abs/1812.01941v1
PDF	http://arxiv.org/pdf/1812.01941v1.pdf
PWC	https://paperswithcode.com/paper/anomaly-detection-for-network-connection-logs
Repo
Framework

Deep Factors with Gaussian Processes for Forecasting


Title	Deep Factors with Gaussian Processes for Forecasting
Authors	Danielle C. Maddix, Yuyang Wang, Alex Smola
Abstract	A large collection of time series poses significant challenges for classical and neural forecasting approaches. Classical time series models fail to fit data well and to scale to large problems, but succeed at providing uncertainty estimates. The converse is true for deep neural networks. In this paper, we propose a hybrid model that incorporates the benefits of both approaches. Our new method is data-driven and scalable via a latent, global, deep component. It also handles uncertainty through a local classical Gaussian Process model. Our experiments demonstrate that our method obtains higher accuracy than state-of-the-art methods.
Tasks	Gaussian Processes, Time Series
Published	2018-11-30
URL	http://arxiv.org/abs/1812.00098v1
PDF	http://arxiv.org/pdf/1812.00098v1.pdf
PWC	https://paperswithcode.com/paper/deep-factors-with-gaussian-processes-for
Repo
Framework