October 16, 2019

3337 words 16 mins read

Paper Group ANR 1015

Deep Meta-Learning: Learning to Learn in the Concept Space. Loss Aversion in Recommender Systems: Utilizing Negative User Preference to Improve Recommendation Quality. On the Effectiveness of System API-Related Information for Android Ransomware Detection. Exploiting Effective Representations for Chinese Sentiment Analysis Using a Multi-Channel Con …

Deep Meta-Learning: Learning to Learn in the Concept Space


Title	Deep Meta-Learning: Learning to Learn in the Concept Space
Authors	Fengwei Zhou, Bin Wu, Zhenguo Li
Abstract	Few-shot learning remains challenging for meta-learning that learns a learning algorithm (meta-learner) from many related tasks. In this work, we argue that this is due to the lack of a good representation for meta-learning, and propose deep meta-learning to integrate the representation power of deep learning into meta-learning. The framework is composed of three modules, a concept generator, a meta-learner, and a concept discriminator, which are learned jointly. The concept generator, e.g. a deep residual net, extracts a representation for each instance that captures its high-level concept, on which the meta-learner performs few-shot learning, and the concept discriminator recognizes the concepts. By learning to learn in the concept space rather than in the complicated instance space, deep meta-learning can substantially improve vanilla meta-learning, which is demonstrated on various few-shot image recognition problems. For example, on 5-way-1-shot image recognition on CIFAR-100 and CUB-200, it improves Matching Nets from 50.53% and 56.53% to 58.18% and 63.47%, improves MAML from 49.28% and 50.45% to 56.65% and 64.63%, and improves Meta-SGD from 53.83% and 53.34% to 61.62% and 66.95%, respectively.
Tasks	Few-Shot Learning, Meta-Learning
Published	2018-02-10
URL	http://arxiv.org/abs/1802.03596v1
PDF	http://arxiv.org/pdf/1802.03596v1.pdf
PWC	https://paperswithcode.com/paper/deep-meta-learning-learning-to-learn-in-the
Repo
Framework

Loss Aversion in Recommender Systems: Utilizing Negative User Preference to Improve Recommendation Quality


Title	Loss Aversion in Recommender Systems: Utilizing Negative User Preference to Improve Recommendation Quality
Authors	Bibek Paudel, Sandro Luck, Abraham Bernstein
Abstract	Negative user preference is an important context that is not sufficiently utilized by many existing recommender systems. This context is especially useful in scenarios where the cost of negative items is high for the users. In this work, we describe a new recommender algorithm that explicitly models negative user preferences in order to recommend more positive items at the top of recommendation-lists. We build upon existing machine-learning model to incorporate the contextual information provided by negative user preference. With experimental evaluations on two openly available datasets, we show that our method is able to improve recommendation quality: by improving accuracy and at the same time reducing the number of negative items at the top of recommendation-lists. Our work demonstrates the value of the contextual information provided by negative feedback, and can also be extended to signed social networks and link prediction in other networks.
Tasks	Link Prediction, Recommendation Systems
Published	2018-12-29
URL	http://arxiv.org/abs/1812.11422v1
PDF	http://arxiv.org/pdf/1812.11422v1.pdf
PWC	https://paperswithcode.com/paper/loss-aversion-in-recommender-systems
Repo
Framework


Title	On the Effectiveness of System API-Related Information for Android Ransomware Detection
Authors	Michele Scalas, Davide Maiorca, Francesco Mercaldo, Corrado Aaron Visaggio, Fabio Martinelli, Giorgio Giacinto
Abstract	Ransomware constitutes a significant threat to the Android operating system. It can either lock or encrypt the target devices, and victims are forced to pay ransoms to restore their data. Hence, the prompt detection of such attacks has a priority in comparison to other malicious threats. Previous works on Android malware detection mainly focused on Machine Learning-oriented approaches that were tailored to identifying malware families, without a clear focus on ransomware. More specifically, such approaches resorted to complex information types such as permissions, user-implemented API calls, and native calls. However, this led to significant drawbacks concerning complexity, resilience against obfuscation, and explainability. To overcome these issues, in this paper, we propose and discuss learning-based detection strategies that rely on System API information. These techniques leverage the fact that ransomware attacks heavily resort to System API to perform their actions, and allow distinguishing between generic malware, ransomware and goodware. We tested three different ways of employing System API information, i.e., through packages, classes, and methods, and we compared their performances to other, more complex state-of-the-art approaches. The attained results showed that systems based on System API could detect ransomware and generic malware with very good accuracy, comparable to systems that employed more complex information. Moreover, the proposed systems could accurately detect novel samples in the wild and showed resilience against static obfuscation attempts. Finally, to guarantee early on-device detection, we developed and released on the Android platform a complete ransomware and malware detector (R-PackDroid) that employed one of the methodologies proposed in this paper.
Tasks	Android Malware Detection, Malware Detection
Published	2018-05-24
URL	https://arxiv.org/abs/1805.09563v4
PDF	https://arxiv.org/pdf/1805.09563v4.pdf
PWC	https://paperswithcode.com/paper/on-the-effectiveness-of-system-api-related
Repo
Framework

Exploiting Effective Representations for Chinese Sentiment Analysis Using a Multi-Channel Convolutional Neural Network


Title	Exploiting Effective Representations for Chinese Sentiment Analysis Using a Multi-Channel Convolutional Neural Network
Authors	Pengfei Liu, Ji Zhang, Cane Wing-Ki Leung, Chao He, Thomas L. Griffiths
Abstract	Effective representation of a text is critical for various natural language processing tasks. For the particular task of Chinese sentiment analysis, it is important to understand and choose an effective representation of a text from different forms of Chinese representations such as word, character and pinyin. This paper presents a systematic study of the effect of these representations for Chinese sentiment analysis by proposing a multi-channel convolutional neural network (MCCNN), where each channel corresponds to a representation. Experimental results show that: (1) Word wins on the dataset of low OOV rate while character wins otherwise; (2) Using these representations in combination generally improves the performance; (3) The representations based on MCCNN outperform conventional ngram features using SVM; (4) The proposed MCCNN model achieves the competitive performance against the state-of-the-art model fastText for Chinese sentiment analysis.
Tasks	Sentiment Analysis
Published	2018-08-08
URL	http://arxiv.org/abs/1808.02961v1
PDF	http://arxiv.org/pdf/1808.02961v1.pdf
PWC	https://paperswithcode.com/paper/exploiting-effective-representations-for
Repo
Framework

Interpretable Graph Convolutional Neural Networks for Inference on Noisy Knowledge Graphs


Title	Interpretable Graph Convolutional Neural Networks for Inference on Noisy Knowledge Graphs
Authors	Daniel Neil, Joss Briody, Alix Lacoste, Aaron Sim, Paidi Creed, Amir Saffari
Abstract	In this work, we provide a new formulation for Graph Convolutional Neural Networks (GCNNs) for link prediction on graph data that addresses common challenges for biomedical knowledge graphs (KGs). We introduce a regularized attention mechanism to GCNNs that not only improves performance on clean datasets, but also favorably accommodates noise in KGs, a pervasive issue in real-world applications. Further, we explore new visualization methods for interpretable modelling and to illustrate how the learned representation can be exploited to automate dataset denoising. The results are demonstrated on a synthetic dataset, the common benchmark dataset FB15k-237, and a large biomedical knowledge graph derived from a combination of noisy and clean data sources. Using these improvements, we visualize a learned model’s representation of the disease cystic fibrosis and demonstrate how to interrogate a neural network to show the potential of PPARG as a candidate therapeutic target for rheumatoid arthritis.
Tasks	Denoising, Knowledge Graphs, Link Prediction
Published	2018-12-01
URL	http://arxiv.org/abs/1812.00279v1
PDF	http://arxiv.org/pdf/1812.00279v1.pdf
PWC	https://paperswithcode.com/paper/interpretable-graph-convolutional-neural
Repo
Framework

Deep-learning Based Modeling of Fault Detachment Stability for Power Grid


Title	Deep-learning Based Modeling of Fault Detachment Stability for Power Grid
Authors	Haotian Cui, Xianggen Liu, Yanhao Huang
Abstract	The project intends to model the stability of power system with a deep learning algorithm to the problem, aiming to delay the removal of the fault. The so-called “fail-delay cut-off” refers to the occurrence of N-1 backup protection action on the backbone network of the system, resulting in longer time for the removal of the fault. In practice, through the analysis and calculation of a large number of online data, we have found that the N-1 failure system of the main protection action will not be unstable, which is also a guarantee of the operation mode arrangement. In the case of the N-1 backup protection action, there is an approximately 2.5% probability that the system will be destabilized. Therefore, research is needed to improve the operating arrangement.
Tasks
Published	2018-05-17
URL	http://arxiv.org/abs/1805.06657v1
PDF	http://arxiv.org/pdf/1805.06657v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-based-modeling-of-fault
Repo
Framework

Calibration Wizard: A Guidance System for Camera Calibration Based on Modelling Geometric and Corner Uncertainty


Title	Calibration Wizard: A Guidance System for Camera Calibration Based on Modelling Geometric and Corner Uncertainty
Authors	Songyou Peng, Peter Sturm
Abstract	It is well known that the accuracy of a calibration depends strongly on the choice of camera poses from which images of a calibration object are acquired. We present a system – Calibration Wizard – that interactively guides a user towards taking optimal calibration images. For each new image to be taken, the system computes, from all previously acquired images, the pose that leads to the globally maximum reduction of expected uncertainty on intrinsic parameters and then guides the user towards that pose. We also show how to incorporate uncertainty in corner point position in a novel principled manner, for both, calibration and computation of the next best pose. Synthetic and real-world experiments are performed to demonstrate the effectiveness of Calibration Wizard.
Tasks	Calibration
Published	2018-11-08
URL	https://arxiv.org/abs/1811.03264v2
PDF	https://arxiv.org/pdf/1811.03264v2.pdf
PWC	https://paperswithcode.com/paper/calibration-wizard-a-guidance-system-for
Repo
Framework

Naive Dictionary On Musical Corpora: From Knowledge Representation To Pattern Recognition


Title	Naive Dictionary On Musical Corpora: From Knowledge Representation To Pattern Recognition
Authors	Qiuyi Wu, Ernest Fokoue
Abstract	In this paper, we propose and develop the novel idea of treating musical sheets as literary documents in the traditional text analytics parlance, to fully benefit from the vast amount of research already existing in statistical text mining and topic modelling. We specifically introduce the idea of representing any given piece of music as a collection of “musical words” that we codenamed “muselets”, which are essentially musical words of various lengths. Given the novelty and therefore the extremely difficulty of properly forming a complete version of a dictionary of muselets, the present paper focuses on a simpler albeit naive version of the ultimate dictionary, which we refer to as a Naive Dictionary because of the fact that all the words are of the same length. We specifically herein construct a naive dictionary featuring a corpus made up of African American, Chinese, Japanese and Arabic music, on which we perform both topic modelling and pattern recognition. Although some of the results based on the Naive Dictionary are reasonably good, we anticipate phenomenal predictive performances once we get around to actually building a full scale complete version of our intended dictionary of muselets.
Tasks
Published	2018-11-29
URL	http://arxiv.org/abs/1811.12802v1
PDF	http://arxiv.org/pdf/1811.12802v1.pdf
PWC	https://paperswithcode.com/paper/naive-dictionary-on-musical-corpora-from
Repo
Framework

Language Guided Fashion Image Manipulation with Feature-wise Transformations


Title	Language Guided Fashion Image Manipulation with Feature-wise Transformations
Authors	Mehmet Günel, Erkut Erdem, Aykut Erdem
Abstract	Developing techniques for editing an outfit image through natural sentences and accordingly generating new outfits has promising applications for art, fashion and design. However, it is considered as a certainly challenging task since image manipulation should be carried out only on the relevant parts of the image while keeping the remaining sections untouched. Moreover, this manipulation process should generate an image that is as realistic as possible. In this work, we propose FiLMedGAN, which leverages feature-wise linear modulation (FiLM) to relate and transform visual features with natural language representations without using extra spatial information. Our experiments demonstrate that this approach, when combined with skip connections and total variation regularization, produces more plausible results than the baseline work, and has a better localization capability when generating new outfits consistent with the target description.
Tasks
Published	2018-08-12
URL	http://arxiv.org/abs/1808.04000v1
PDF	http://arxiv.org/pdf/1808.04000v1.pdf
PWC	https://paperswithcode.com/paper/language-guided-fashion-image-manipulation
Repo
Framework

Three-Stage Speaker Verification Architecture in Emotional Talking Environments


Title	Three-Stage Speaker Verification Architecture in Emotional Talking Environments
Authors	Ismail Shahin, Ali Bou Nassif
Abstract	Speaker verification performance in neutral talking environment is usually high, while it is sharply decreased in emotional talking environments. This performance degradation in emotional environments is due to the problem of mismatch between training in neutral environment while testing in emotional environments. In this work, a three-stage speaker verification architecture has been proposed to enhance speaker verification performance in emotional environments. This architecture is comprised of three cascaded stages: gender identification stage followed by an emotion identification stage followed by a speaker verification stage. The proposed framework has been evaluated on two distinct and independent emotional speech datasets: in-house dataset and Emotional Prosody Speech and Transcripts dataset. Our results show that speaker verification based on both gender information and emotion information is superior to each of speaker verification based on gender information only, emotion information only, and neither gender information nor emotion information. The attained average speaker verification performance based on the proposed framework is very alike to that attained in subjective assessment by human listeners.
Tasks	Speaker Verification
Published	2018-09-03
URL	http://arxiv.org/abs/1809.01721v1
PDF	http://arxiv.org/pdf/1809.01721v1.pdf
PWC	https://paperswithcode.com/paper/three-stage-speaker-verification-architecture
Repo
Framework

Evaluating the Ability of LSTMs to Learn Context-Free Grammars


Title	Evaluating the Ability of LSTMs to Learn Context-Free Grammars
Authors	Luzi Sennhauser, Robert C. Berwick
Abstract	While long short-term memory (LSTM) neural net architectures are designed to capture sequence information, human language is generally composed of hierarchical structures. This raises the question as to whether LSTMs can learn hierarchical structures. We explore this question with a well-formed bracket prediction task using two types of brackets modeled by an LSTM. Demonstrating that such a system is learnable by an LSTM is the first step in demonstrating that the entire class of CFLs is also learnable. We observe that the model requires exponential memory in terms of the number of characters and embedded depth, where a sub-linear memory should suffice. Still, the model does more than memorize the training input. It learns how to distinguish between relevant and irrelevant information. On the other hand, we also observe that the model does not generalize well. We conclude that LSTMs do not learn the relevant underlying context-free rules, suggesting the good overall performance is attained rather by an efficient way of evaluating nuisance variables. LSTMs are a way to quickly reach good results for many natural language tasks, but to understand and generate natural language one has to investigate other concepts that can make more direct use of natural language’s structural nature.
Tasks
Published	2018-11-06
URL	http://arxiv.org/abs/1811.02611v1
PDF	http://arxiv.org/pdf/1811.02611v1.pdf
PWC	https://paperswithcode.com/paper/evaluating-the-ability-of-lstms-to-learn
Repo
Framework

Decentralized Cooperative Planning for Automated Vehicles with Continuous Monte Carlo Tree Search


Title	Decentralized Cooperative Planning for Automated Vehicles with Continuous Monte Carlo Tree Search
Authors	Karl Kurzer, Florian Engelhorn, J. Marius Zöllner
Abstract	Urban traffic scenarios often require a high degree of cooperation between traffic participants to ensure safety and efficiency. Observing the behavior of others, humans infer whether or not others are cooperating. This work aims to extend the capabilities of automated vehicles, enabling them to cooperate implicitly in heterogeneous environments. Continuous actions allow for arbitrary trajectories and hence are applicable to a much wider class of problems than existing cooperative approaches with discrete action spaces. Based on cooperative modeling of other agents, Monte Carlo Tree Search (MCTS) in conjunction with Decoupled-UCT evaluates the action-values of each agent in a cooperative and decentralized way, respecting the interdependence of actions among traffic participants. The extension to continuous action spaces is addressed by incorporating novel MCTS-specific enhancements for efficient search space exploration. The proposed algorithm is evaluated under different scenarios, showing that the algorithm is able to achieve effective cooperative planning and generate solutions egocentric planning fails to identify.
Tasks
Published	2018-09-10
URL	http://arxiv.org/abs/1809.03200v1
PDF	http://arxiv.org/pdf/1809.03200v1.pdf
PWC	https://paperswithcode.com/paper/decentralized-cooperative-planning-for-1
Repo
Framework

Persistence Atlas for Critical Point Variability in Ensembles


Title	Persistence Atlas for Critical Point Variability in Ensembles
Authors	Guillaume Favelier, Noura Faraj, Brian Summa, Julien Tierny
Abstract	This paper presents a new approach for the visualization and analysis of the spatial variability of features of interest represented by critical points in ensemble data. Our framework, called Persistence Atlas, enables the visualization of the dominant spatial patterns of critical points, along with statistics regarding their occurrence in the ensemble. The persistence atlas represents in the geometrical domain each dominant pattern in the form of a confidence map for the appearance of critical points. As a by-product, our method also provides 2-dimensional layouts of the entire ensemble, highlighting the main trends at a global level. Our approach is based on the new notion of Persistence Map, a measure of the geometrical density in critical points which leverages the robustness to noise of topological persistence to better emphasize salient features. We show how to leverage spectral embedding to represent the ensemble members as points in a low-dimensional Euclidean space, where distances between points measure the dissimilarities between critical point layouts and where statistical tasks, such as clustering, can be easily carried out. Further, we show how the notion of mandatory critical point can be leveraged to evaluate for each cluster confidence regions for the appearance of critical points. Most of the steps of this framework can be trivially parallelized and we show how to efficiently implement them. Extensive experiments demonstrate the relevance of our approach. The accuracy of the confidence regions provided by the persistence atlas is quantitatively evaluated and compared to a baseline strategy using an off-the-shelf clustering approach. We illustrate the importance of the persistence atlas in a variety of real-life datasets, where clear trends in feature layouts are identified and analyzed.
Tasks
Published	2018-07-30
URL	http://arxiv.org/abs/1807.11212v1
PDF	http://arxiv.org/pdf/1807.11212v1.pdf
PWC	https://paperswithcode.com/paper/persistence-atlas-for-critical-point
Repo
Framework

The Disparate Effects of Strategic Manipulation


Title	The Disparate Effects of Strategic Manipulation
Authors	Lily Hu, Nicole Immorlica, Jennifer Wortman Vaughan
Abstract	When consequential decisions are informed by algorithmic input, individuals may feel compelled to alter their behavior in order to gain a system’s approval. Models of agent responsiveness, termed “strategic manipulation,” analyze the interaction between a learner and agents in a world where all agents are equally able to manipulate their features in an attempt to “trick” a published classifier. In cases of real world classification, however, an agent’s ability to adapt to an algorithm is not simply a function of her personal interest in receiving a positive classification, but is bound up in a complex web of social factors that affect her ability to pursue certain action responses. In this paper, we adapt models of strategic manipulation to capture dynamics that may arise in a setting of social inequality wherein candidate groups face different costs to manipulation. We find that whenever one group’s costs are higher than the other’s, the learner’s equilibrium strategy exhibits an inequality-reinforcing phenomenon wherein the learner erroneously admits some members of the advantaged group, while erroneously excluding some members of the disadvantaged group. We also consider the effects of interventions in which a learner subsidizes members of the disadvantaged group, lowering their costs in order to improve her own classification performance. Here we encounter a paradoxical result: there exist cases in which providing a subsidy improves only the learner’s utility while actually making both candidate groups worse-off–even the group receiving the subsidy. Our results reveal the potentially adverse social ramifications of deploying tools that attempt to evaluate an individual’s “quality” when agents’ capacities to adaptively respond differ.
Tasks
Published	2018-08-27
URL	https://arxiv.org/abs/1808.08646v4
PDF	https://arxiv.org/pdf/1808.08646v4.pdf
PWC	https://paperswithcode.com/paper/the-disparate-effects-of-strategic
Repo
Framework

Image Anomalies: a Review and Synthesis of Detection Methods


Title	Image Anomalies: a Review and Synthesis of Detection Methods
Authors	Thibaud Ehret, Axel Davy, Jean-Michel Morel, Mauricio Delbracio
Abstract	We review the broad variety of methods that have been proposed for anomaly detection in images. Most methods found in the literature have in mind a particular application. Yet we show that the methods can be classified mainly by the structural assumption they make on the “normal” image. Five different structural assumptions emerge. Our analysis leads us to reformulate the best representative algorithms by attaching to them an a contrario detection that controls the number of false positives and thus derive universal detection thresholds. By combining the most general structural assumptions expressing the background’s normality with the best proposed statistical detection tools, we end up proposing generic algorithms that seem to generalize or reconcile most methods. We compare the six best representatives of our proposed classes of algorithms on anomalous images taken from classic papers on the subject, and on a synthetic database. Our conclusion is that it is possible to perform automatic anomaly detection on a single image.
Tasks	Anomaly Detection
Published	2018-08-07
URL	https://arxiv.org/abs/1808.02564v2
PDF	https://arxiv.org/pdf/1808.02564v2.pdf
PWC	https://paperswithcode.com/paper/image-anomalies-a-review-and-synthesis-of
Repo
Framework