April 2, 2020

3004 words 15 mins read

Paper Group ANR 285

An Assignment Problem Formulation for Dominance Move Indicator. DeepPlume: Very High Resolution Real-Time Air Quality Mapping. Generating Word and Document Embeddings for Sentiment Analysis. Forecasting the Intra-Day Spread Densities of Electricity Prices. A characterization of proportionally representative committees. Memristive Properties of Mush …

An Assignment Problem Formulation for Dominance Move Indicator


Title	An Assignment Problem Formulation for Dominance Move Indicator
Authors	Claudio Lucio do Val Lopes, Flávio Vinícius Cruzeiro Martins, Elizabeth F. Wanner
Abstract	Dominance move (DoM) is a binary quality indicator to compare solution sets in multiobjective optimization. The indicator allows a more natural and intuitive relation when comparing solution sets. It is Pareto compliant and does not demand any parameters or reference sets. In spite of its advantages, the combinatorial calculation nature is a limitation. The original formulation presents an efficient method to calculate it in a biobjective case only. This work presents an assignment formulation to calculate DoM in problems with three objectives or more. Some initial experiments, in the biobjective space, were done to present the model correctness. Next, other experiments, using three dimensions, were also done to show how DoM could be compared with other indicators: inverted generational distance (IGD) and hypervolume (HV). Results show the assignment formulation for DoM is valid for more than three objectives. However, there are some strengths and weaknesses, which are discussed and detailed. Some notes, considerations, and future research paths conclude this work.
Tasks	Multiobjective Optimization
Published	2020-02-25
URL	https://arxiv.org/abs/2002.10842v1
PDF	https://arxiv.org/pdf/2002.10842v1.pdf
PWC	https://paperswithcode.com/paper/an-assignment-problem-formulation-for
Repo
Framework

DeepPlume: Very High Resolution Real-Time Air Quality Mapping


Title	DeepPlume: Very High Resolution Real-Time Air Quality Mapping
Authors	Grégoire Jauvion, Thibaut Cassard, Boris Quennehen, David Lissmyr
Abstract	This paper presents an engine able to predict jointly the real-time concentration of the main pollutants harming people’s health: nitrogen dioxyde (NO2), ozone (O3) and particulate matter (PM2.5 and PM10, which are respectively the particles whose size are below 2.5 um and 10 um). The engine covers a large part of the world and is fed with real-time official stations measures, atmospheric models’ forecasts, land cover data, road networks and traffic estimates to produce predictions with a very high resolution in the range of a few dozens of meters. This resolution makes the engine adapted to very innovative applications like street-level air quality mapping or air quality adjusted routing. Plume Labs has deployed a similar prediction engine to build several products aiming at providing air quality data to individuals and businesses. For the sake of clarity and reproducibility, the engine presented here has been built specifically for this paper and differs quite significantly from the one used in Plume Labs’ products. A major difference is in the data sources feeding the engine: in particular, this prediction engine does not include mobile sensors measurements.
Tasks
Published	2020-02-14
URL	https://arxiv.org/abs/2002.10394v1
PDF	https://arxiv.org/pdf/2002.10394v1.pdf
PWC	https://paperswithcode.com/paper/deepplume-very-high-resolution-real-time-air
Repo
Framework

Generating Word and Document Embeddings for Sentiment Analysis


Title	Generating Word and Document Embeddings for Sentiment Analysis
Authors	Cem Rıfkı Aydın, Tunga Güngör, Ali Erkan
Abstract	Sentiments of words differ from one corpus to another. Inducing general sentiment lexicons for languages and using them cannot, in general, produce meaningful results for different domains. In this paper, we combine contextual and supervised information with the general semantic representations of words occurring in the dictionary. Contexts of words help us capture the domain-specific information and supervised scores of words are indicative of the polarities of those words. When we combine supervised features of words with the features extracted from their dictionary definitions, we observe an increase in the success rates. We try out the combinations of contextual, supervised, and dictionary-based approaches, and generate original vectors. We also combine the word2vec approach with hand-crafted features. We induce domain-specific sentimental vectors for two corpora, which are the movie domain and the Twitter datasets in Turkish. When we thereafter generate document vectors and employ the support vector machines method utilising those vectors, our approaches perform better than the baseline studies for Turkish with a significant margin. We evaluated our models on two English corpora as well and these also outperformed the word2vec approach. It shows that our approaches are cross-lingual and cross-domain.
Tasks	Sentiment Analysis
Published	2020-01-05
URL	https://arxiv.org/abs/2001.01269v1
PDF	https://arxiv.org/pdf/2001.01269v1.pdf
PWC	https://paperswithcode.com/paper/generating-word-and-document-embeddings-for
Repo
Framework

Forecasting the Intra-Day Spread Densities of Electricity Prices


Title	Forecasting the Intra-Day Spread Densities of Electricity Prices
Authors	Ekaterina Abramova, Derek Bunn
Abstract	Intra-day price spreads are of interest to electricity traders, storage and electric vehicle operators. This paper formulates dynamic density functions, based upon skewed-t and similar representations, to model and forecast the German electricity price spreads between different hours of the day, as revealed in the day-ahead auctions. The four specifications of the density functions are dynamic and conditional upon exogenous drivers, thereby permitting the location, scale and shape parameters of the densities to respond hourly to such factors as weather and demand forecasts. The best fitting and forecasting specifications for each spread are selected based on the Pinball Loss function, following the closed-form analytical solutions of the cumulative distribution functions.
Tasks
Published	2020-02-20
URL	https://arxiv.org/abs/2002.10566v1
PDF	https://arxiv.org/pdf/2002.10566v1.pdf
PWC	https://paperswithcode.com/paper/forecasting-the-intra-day-spread-densities-of
Repo
Framework

A characterization of proportionally representative committees


Title	A characterization of proportionally representative committees
Authors	Haris Aziz, Barton E. Lee
Abstract	A well-known axiom for proportional representation is Proportionality of Solid Coalitions (PSC). We characterize committees satisfying PSC as possible outcomes of the Minimal Demand rule, which generalizes an approach pioneered by Michael Dummett.
Tasks
Published	2020-02-22
URL	https://arxiv.org/abs/2002.09598v1
PDF	https://arxiv.org/pdf/2002.09598v1.pdf
PWC	https://paperswithcode.com/paper/a-characterization-of-proportionally
Repo
Framework

Memristive Properties of Mushrooms


Title	Memristive Properties of Mushrooms
Authors	Alexander E. Beasley, Anna L. Powell, Andrew Adamatzky
Abstract	Memristors close the loop for I-V characteristics of the traditional, passive, semi-conductor devices. Originally proposed in 1971, the hunt for the memristor has been going ever since. The key feature of a memristor is that its current resitance is a function of its previous resistance. As such, the behaviour of the device is influenced by changing the way in which potential is applied across it. Ultimately, information can be encoded on memristors. Biological substrates have already been shown to exhibit some memristive properties. However, many memristive devices are yet to be found. Here we show that the fruit bodies of grey oyster fungi Pleurotus ostreatus exhibit memristive behaviours. This paper presents the I-V characteristics of the mushrooms. By examination of the conducted current for a given voltage applied as a function of the previous voltage, it is shown that the mushroom is a memristor. Our results demonstrate that nature continues to provide specimens that hold these unique and valuable electrical characteristics and which have the potential to advance the field of hybrid electronic systems.
Tasks
Published	2020-02-15
URL	https://arxiv.org/abs/2002.06413v1
PDF	https://arxiv.org/pdf/2002.06413v1.pdf
PWC	https://paperswithcode.com/paper/memristive-properties-of-mushrooms
Repo
Framework

Partial Multi-label Learning with Label and Feature Collaboration


Title	Partial Multi-label Learning with Label and Feature Collaboration
Authors	Tingting Yu, Guoxian Yu, Jun Wang, Maozu Guo
Abstract	Partial multi-label learning (PML) models the scenario where each training instance is annotated with a set of candidate labels, and only some of the labels are relevant. The PML problem is practical in real-world scenarios, as it is difficult and even impossible to obtain precisely labeled samples. Several PML solutions have been proposed to combat with the prone misled by the irrelevant labels concealed in the candidate labels, but they generally focus on the smoothness assumption in feature space or low-rank assumption in label space, while ignore the negative information between features and labels. Specifically, if two instances have largely overlapped candidate labels, irrespective of their feature similarity, their ground-truth labels should be similar; while if they are dissimilar in the feature and candidate label space, their ground-truth labels should be dissimilar with each other. To achieve a credible predictor on PML data, we propose a novel approach called PML-LFC (Partial Multi-label Learning with Label and Feature Collaboration). PML-LFC estimates the confidence values of relevant labels for each instance using the similarity from both the label and feature spaces, and trains the desired predictor with the estimated confidence values. PML-LFC achieves the predictor and the latent label matrix in a reciprocal reinforce manner by a unified model, and develops an alternative optimization procedure to optimize them. Extensive empirical study on both synthetic and real-world datasets demonstrates the superiority of PML-LFC.
Tasks	Multi-Label Learning
Published	2020-03-17
URL	https://arxiv.org/abs/2003.07578v1
PDF	https://arxiv.org/pdf/2003.07578v1.pdf
PWC	https://paperswithcode.com/paper/partial-multi-label-learning-with-label-and
Repo
Framework

Automatic Shortcut Removal for Self-Supervised Representation Learning


Title	Automatic Shortcut Removal for Self-Supervised Representation Learning
Authors	Matthias Minderer, Olivier Bachem, Neil Houlsby, Michael Tschannen
Abstract	In self-supervised visual representation learning, a feature extractor is trained on a “pretext task” for which labels can be generated cheaply. A central challenge in this approach is that the feature extractor quickly learns to exploit low-level visual features such as color aberrations or watermarks and then fails to learn useful semantic representations. Much work has gone into identifying such “shortcut” features and hand-designing schemes to reduce their effect. Here, we propose a general framework for removing shortcut features automatically. Our key assumption is that those features which are the first to be exploited for solving the pretext task may also be the most vulnerable to an adversary trained to make the task harder. We show that this assumption holds across common pretext tasks and datasets by training a “lens” network to make small image changes that maximally reduce performance in the pretext task. Representations learned with the modified images outperform those learned without in all tested cases. Additionally, the modifications made by the lens reveal how the choice of pretext task and dataset affects the features learned by self-supervision.
Tasks	Representation Learning
Published	2020-02-20
URL	https://arxiv.org/abs/2002.08822v2
PDF	https://arxiv.org/pdf/2002.08822v2.pdf
PWC	https://paperswithcode.com/paper/automatic-shortcut-removal-for-self
Repo
Framework

Straight to the Point: Fast-forwarding Videos via Reinforcement Learning Using Textual Data


Title	Straight to the Point: Fast-forwarding Videos via Reinforcement Learning Using Textual Data
Authors	Washington Ramos, Michel Silva, Edson Araujo, Leandro Soriano Marcolino, Erickson Nascimento
Abstract	The rapid increase in the amount of published visual data and the limited time of users bring the demand for processing untrimmed videos to produce shorter versions that convey the same information. Despite the remarkable progress that has been made by summarization methods, most of them can only select a few frames or skims, which creates visual gaps and breaks the video context. In this paper, we present a novel methodology based on a reinforcement learning formulation to accelerate instructional videos. Our approach can adaptively select frames that are not relevant to convey the information without creating gaps in the final video. Our agent is textually and visually oriented to select which frames to remove to shrink the input video. Additionally, we propose a novel network, called Visually-guided Document Attention Network (VDAN), able to generate a highly discriminative embedding space to represent both textual and visual data. Our experiments show that our method achieves the best performance in terms of F1 Score and coverage at the video segment level.
Tasks
Published	2020-03-31
URL	https://arxiv.org/abs/2003.14229v1
PDF	https://arxiv.org/pdf/2003.14229v1.pdf
PWC	https://paperswithcode.com/paper/straight-to-the-point-fast-forwarding-videos
Repo
Framework

Hyper-Parameter Optimization: A Review of Algorithms and Applications


Title	Hyper-Parameter Optimization: A Review of Algorithms and Applications
Authors	Tong Yu, Hong Zhu
Abstract	Since deep neural networks were developed, they have made huge contributions to everyday lives. Machine learning provides more rational advice than humans are capable of in almost every aspect of daily life. However, despite this achievement, the design and training of neural networks are still challenging and unpredictable procedures. To lower the technical thresholds for common users, automated hyper-parameter optimization (HPO) has become a popular topic in both academic and industrial areas. This paper provides a review of the most essential topics on HPO. The first section introduces the key hyper-parameters related to model training and structure, and discusses their importance and methods to define the value range. Then, the research focuses on major optimization algorithms and their applicability, covering their efficiency and accuracy especially for deep learning networks. This study next reviews major services and toolkits for HPO, comparing their support for state-of-the-art searching algorithms, feasibility with major deep learning frameworks, and extensibility for new modules designed by users. The paper concludes with problems that exist when HPO is applied to deep learning, a comparison between optimization algorithms, and prominent approaches for model evaluation with limited computational resources.
Tasks
Published	2020-03-12
URL	https://arxiv.org/abs/2003.05689v1
PDF	https://arxiv.org/pdf/2003.05689v1.pdf
PWC	https://paperswithcode.com/paper/hyper-parameter-optimization-a-review-of
Repo
Framework

APTER: Aggregated Prognosis Through Exponential Reweighting


Title	APTER: Aggregated Prognosis Through Exponential Reweighting
Authors	Kristiaan Pelckmans, Liu Yang
Abstract	This paper considers the task of learning how to make a prognosis of a patient based on his/her micro-array expression levels. The method is an application of the aggregation method as recently proposed in the literature on theoretical machine learning, and excels in its computational convenience and capability to deal with high-dimensional data. A formal analysis of the method is given, yielding rates of convergence similar to what traditional techniques obtain, while it is shown to cope well with an exponentially large set of features. Those results are supported by numerical simulations on a range of publicly available survival-micro-array datasets. It is empirically found that the proposed technique combined with a recently proposed preprocessing technique gives excellent performances.
Tasks
Published	2020-02-20
URL	https://arxiv.org/abs/2002.08731v1
PDF	https://arxiv.org/pdf/2002.08731v1.pdf
PWC	https://paperswithcode.com/paper/apter-aggregated-prognosis-through
Repo
Framework

Thermodynamic Cost of Edge Detection in Artificial Neural Network(ANN)-Based Processors


Title	Thermodynamic Cost of Edge Detection in Artificial Neural Network(ANN)-Based Processors
Authors	Seçkin Barışık, İlke Ercan
Abstract	Architecture-based heat dissipation analyses allows us to reveal fundamental sources of inefficiency in a given processor and thereby provide us with roadmaps to design less dissipative computing schemes independent of technology-bases used to implement the processor. In this work, we study architectural-level contributions to energy dissipation in Artificial Neural Network (ANN)-based processors that are trained to perform edge detection task. We compare the training and information processing cost ofANNs to that of conventional architectures and algorithms using 64-pixel binary image. Our results reveal the inherent efficiency advantages of ANN networks trained for specific tasks over general purpose processors based on von Neumann architecture.We also compare the proposed performance improvements to that of CAPs and show the reduction in dissipation for special purpose processors. Lastly, we calculate the change in dissipation as a result of change in input data structure and show the effect of randomness on energetic cost of information processing. The results we obtain provide a basis for comparison for task-based fundamental energy efficiency analyses for a range of processors and therefore contribute to the study of architecture-level descriptions of processors and thermodynamic cost calculations based on physics of computation.
Tasks	Edge Detection
Published	2020-03-18
URL	https://arxiv.org/abs/2003.08196v1
PDF	https://arxiv.org/pdf/2003.08196v1.pdf
PWC	https://paperswithcode.com/paper/thermodynamic-cost-of-edge-detection-in
Repo
Framework

Dam Burst: A region-merging-based image segmentation method


Title	Dam Burst: A region-merging-based image segmentation method
Authors	Rui Tang, Wenlong Song, Xiaoping Guan, Huibin Ge, Deke Kong
Abstract	Until now, all single level segmentation algorithms except CNN-based ones lead to over segmentation. And CNN-based segmentation algorithms have their own problems. To avoid over segmentation, multiple thresholds of criteria are adopted in region merging process to produce hierarchical segmentation results. However, there still has extreme over segmentation in the low level of the hierarchy, and outstanding tiny objects are merged to their large adjacencies in the high level of the hierarchy. This paper proposes a region-merging-based image segmentation method that we call it Dam Burst. As a single level segmentation algorithm, this method avoids over segmentation and retains details by the same time. It is named because of that it simulates a flooding from underground destroys dams between water-pools. We treat edge detection results as strengthening structure of a dam if it is on the dam. To simulate a flooding from underground, regions are merged by ascending order of the average gra-dient inside the region.
Tasks	Edge Detection, Semantic Segmentation
Published	2020-02-26
URL	https://arxiv.org/abs/2003.04797v1
PDF	https://arxiv.org/pdf/2003.04797v1.pdf
PWC	https://paperswithcode.com/paper/dam-burst-a-region-merging-based-image
Repo
Framework

Relational Neural Machines


Title	Relational Neural Machines
Authors	Giuseppe Marra, Michelangelo Diligenti, Francesco Giannini, Marco Gori, Marco Maggini
Abstract	Deep learning has been shown to achieve impressive results in several tasks where a large amount of training data is available. However, deep learning solely focuses on the accuracy of the predictions, neglecting the reasoning process leading to a decision, which is a major issue in life-critical applications. Probabilistic logic reasoning allows to exploit both statistical regularities and specific domain expertise to perform reasoning under uncertainty, but its scalability and brittle integration with the layers processing the sensory data have greatly limited its applications. For these reasons, combining deep architectures and probabilistic logic reasoning is a fundamental goal towards the development of intelligent agents operating in complex environments. This paper presents Relational Neural Machines, a novel framework allowing to jointly train the parameters of the learners and of a First–Order Logic based reasoner. A Relational Neural Machine is able to recover both classical learning from supervised data in case of pure sub-symbolic learning, and Markov Logic Networks in case of pure symbolic reasoning, while allowing to jointly train and perform inference in hybrid learning tasks. Proper algorithmic solutions are devised to make learning and inference tractable in large-scale problems. The experiments show promising results in different relational tasks.
Tasks
Published	2020-02-06
URL	https://arxiv.org/abs/2002.02193v1
PDF	https://arxiv.org/pdf/2002.02193v1.pdf
PWC	https://paperswithcode.com/paper/relational-neural-machines
Repo
Framework

FlowFusion: Dynamic Dense RGB-D SLAM Based on Optical Flow


Title	FlowFusion: Dynamic Dense RGB-D SLAM Based on Optical Flow
Authors	Tianwei Zhang, Huayan Zhang, Yang Li, Yoshihiko Nakamura, Lei Zhang
Abstract	Dynamic environments are challenging for visual SLAM since the moving objects occlude the static environment features and lead to wrong camera motion estimation. In this paper, we present a novel dense RGB-D SLAM solution that simultaneously accomplishes the dynamic/static segmentation and camera ego-motion estimation as well as the static background reconstructions. Our novelty is using optical flow residuals to highlight the dynamic semantics in the RGB-D point clouds and provide more accurate and efficient dynamic/static segmentation for camera tracking and background reconstruction. The dense reconstruction results on public datasets and real dynamic scenes indicate that the proposed approach achieved accurate and efficient performances in both dynamic and static environments compared to state-of-the-art approaches.
Tasks	Motion Estimation, Optical Flow Estimation
Published	2020-03-11
URL	https://arxiv.org/abs/2003.05102v1
PDF	https://arxiv.org/pdf/2003.05102v1.pdf
PWC	https://paperswithcode.com/paper/flowfusion-dynamic-dense-rgb-d-slam-based-on
Repo
Framework