Paper Group ANR 142
Structures of Spurious Local Minima in $k$-means. On Certifying Robustness against Backdoor Attacks via Randomized Smoothing. LAXARY: A Trustworthy Explainable Twitter Analysis Model for Post-Traumatic Stress Disorder Assessment. HotelRec: a Novel Very Large-Scale Hotel Recommendation Dataset. Attentive Item2Vec: Neural Attentive User Representatio …
Structures of Spurious Local Minima in $k$-means
| Title | Structures of Spurious Local Minima in $k$-means |
| Authors | Wei Qian, Yuqian Zhang, Yudong Chen |
| Abstract | $k$-means clustering is a fundamental problem in unsupervised learning. The problem concerns finding a partition of the data points into $k$ clusters such that the within-cluster variation is minimized. Despite its importance and wide applicability, a theoretical understanding of the $k$-means problem has not been completely satisfactory. Existing algorithms with theoretical performance guarantees often rely on sophisticated (sometimes artificial) algorithmic techniques and restricted assumptions on the data. The main challenge lies in the non-convex nature of the problem; in particular, there exist additional local solutions other than the global optimum. Moreover, the simplest and most popular algorithm for $k$-means, namely Lloyd’s algorithm, generally converges to such spurious local solutions both in theory and in practice. In this paper, we approach the $k$-means problem from a new perspective, by investigating the structures of these spurious local solutions under a probabilistic generative model with $k$ ground truth clusters. As soon as $k=3$, spurious local minima provably exist, even for well-separated and balanced clusters. One such local minimum puts two centers at one true cluster, and the third center in the middle of the other two true clusters. For general $k$, one local minimum puts multiple centers at a true cluster, and one center in the middle of multiple true clusters. Perhaps surprisingly, we prove that this is essentially the only type of spurious local minima under a separation condition. Our results pertain to the $k$-means formulation for mixtures of Gaussians or bounded distributions. Our theoretical results corroborate existing empirical observations and provide justification for several improved algorithms for $k$-means clustering. |
| Tasks | |
| Published | 2020-02-16 |
| URL | https://arxiv.org/abs/2002.06694v2 |
| https://arxiv.org/pdf/2002.06694v2.pdf | |
| PWC | https://paperswithcode.com/paper/structures-of-spurious-local-minima-in-k |
| Repo | |
| Framework | |
On Certifying Robustness against Backdoor Attacks via Randomized Smoothing
| Title | On Certifying Robustness against Backdoor Attacks via Randomized Smoothing |
| Authors | Binghui Wang, Xiaoyu Cao, Jinyuan jia, Neil Zhenqiang Gong |
| Abstract | Backdoor attack is a severe security threat to deep neural networks (DNNs). We envision that, like adversarial examples, there will be a cat-and-mouse game for backdoor attacks, i.e., new empirical defenses are developed to defend against backdoor attacks but they are soon broken by strong adaptive backdoor attacks. To prevent such cat-and-mouse game, we take the first step towards certified defenses against backdoor attacks. Specifically, in this work, we study the feasibility and effectiveness of certifying robustness against backdoor attacks using a recent technique called randomized smoothing. Randomized smoothing was originally developed to certify robustness against adversarial examples. We generalize randomized smoothing to defend against backdoor attacks. Our results show the theoretical feasibility of using randomized smoothing to certify robustness against backdoor attacks. However, we also find that existing randomized smoothing methods have limited effectiveness at defending against backdoor attacks, which highlight the needs of new theory and methods to certify robustness against backdoor attacks. |
| Tasks | |
| Published | 2020-02-26 |
| URL | https://arxiv.org/abs/2002.11750v1 |
| https://arxiv.org/pdf/2002.11750v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-certifying-robustness-against-backdoor |
| Repo | |
| Framework | |
LAXARY: A Trustworthy Explainable Twitter Analysis Model for Post-Traumatic Stress Disorder Assessment
| Title | LAXARY: A Trustworthy Explainable Twitter Analysis Model for Post-Traumatic Stress Disorder Assessment |
| Authors | Mohammad Arif Ul Alam, Dhawal Kapadia |
| Abstract | Veteran mental health is a significant national problem as large number of veterans are returning from the recent war in Iraq and continued military presence in Afghanistan. While significant existing works have investigated twitter posts-based Post Traumatic Stress Disorder (PTSD) assessment using blackbox machine learning techniques, these frameworks cannot be trusted by the clinicians due to the lack of clinical explainability. To obtain the trust of clinicians, we explore the big question, can twitter posts provide enough information to fill up clinical PTSD assessment surveys that have been traditionally trusted by clinicians? To answer the above question, we propose, LAXARY (Linguistic Analysis-based Exaplainable Inquiry) model, a novel Explainable Artificial Intelligent (XAI) model to detect and represent PTSD assessment of twitter users using a modified Linguistic Inquiry and Word Count (LIWC) analysis. First, we employ clinically validated survey tools for collecting clinical PTSD assessment data from real twitter users and develop a PTSD Linguistic Dictionary using the PTSD assessment survey results. Then, we use the PTSD Linguistic Dictionary along with machine learning model to fill up the survey tools towards detecting PTSD status and its intensity of corresponding twitter users. Our experimental evaluation on 210 clinically validated veteran twitter users provides promising accuracies of both PTSD classification and its intensity estimation. We also evaluate our developed PTSD Linguistic Dictionary’s reliability and validity. |
| Tasks | |
| Published | 2020-03-16 |
| URL | https://arxiv.org/abs/2003.07433v1 |
| https://arxiv.org/pdf/2003.07433v1.pdf | |
| PWC | https://paperswithcode.com/paper/laxary-a-trustworthy-explainable-twitter |
| Repo | |
| Framework | |
HotelRec: a Novel Very Large-Scale Hotel Recommendation Dataset
| Title | HotelRec: a Novel Very Large-Scale Hotel Recommendation Dataset |
| Authors | Diego Antognini, Boi Faltings |
| Abstract | Today, recommender systems are an inevitable part of everyone’s daily digital routine and are present on most internet platforms. State-of-the-art deep learning-based models require a large number of data to achieve their best performance. Many datasets fulfilling this criterion have been proposed for multiple domains, such as Amazon products, restaurants, or beers. However, works and datasets in the hotel domain are limited: the largest hotel review dataset is below the million samples. Additionally, the hotel domain suffers from a higher data sparsity than traditional recommendation datasets and therefore, traditional collaborative-filtering approaches cannot be applied to such data. In this paper, we propose HotelRec, a very large-scale hotel recommendation dataset, based on TripAdvisor, containing 50 million reviews. To the best of our knowledge, HotelRec is the largest publicly available dataset in the hotel domain (50M versus 0.9M) and additionally, the largest recommendation dataset in a single domain and with textual reviews (50M versus 22M). We release HotelRec for further research: https://github.com/Diego999/HotelRec. |
| Tasks | Recommendation Systems |
| Published | 2020-02-17 |
| URL | https://arxiv.org/abs/2002.06854v1 |
| https://arxiv.org/pdf/2002.06854v1.pdf | |
| PWC | https://paperswithcode.com/paper/hotelrec-a-novel-very-large-scale-hotel |
| Repo | |
| Framework | |
Attentive Item2Vec: Neural Attentive User Representations
| Title | Attentive Item2Vec: Neural Attentive User Representations |
| Authors | Oren Barkan, Avi Caciularu, Ori Katz, Noam Koenigstein |
| Abstract | Factorization methods for recommender systems tend to represent users as a single latent vector. However, user behavior and interests may change in the context of the recommendations that are presented to the user. For example, in the case of movie recommendations, it is usually true that earlier user data is less informative than more recent data. However, it is possible that a certain early movie may become suddenly more relevant in the presence of a popular sequel movie. This is just a single example of a variety of possible dynamically altering user interests in the presence of a potential new recommendation. In this work, we present Attentive Item2vec (AI2V) - a novel attentive version of Item2vec (I2V). AI2V employs a context-target attention mechanism in order to learn and capture different characteristics of user historical behavior (context) with respect to a potential recommended item (target). The attentive context-target mechanism enables a final neural attentive user representation. We demonstrate the effectiveness of AI2V on several datasets, where it is shown to outperform other baselines. |
| Tasks | Recommendation Systems |
| Published | 2020-02-15 |
| URL | https://arxiv.org/abs/2002.06205v1 |
| https://arxiv.org/pdf/2002.06205v1.pdf | |
| PWC | https://paperswithcode.com/paper/attentive-item2vec-neural-attentive-user |
| Repo | |
| Framework | |
Realistic River Image Synthesis using Deep Generative Adversarial Networks
| Title | Realistic River Image Synthesis using Deep Generative Adversarial Networks |
| Authors | Akshat Gautam, Muhammed Sit, Ibrahim Demir |
| Abstract | In this paper, we investigate an application of image generation for river satellite imagery. Specifically, we propose a generative adversarial network (GAN) model capable of generating high-resolution and realistic river images that can be used to support models in surface water estimation, river meandering, wetland loss and other hydrological research studies. First, we summarized an augmented, diverse repository of overhead river images to be used in training. Second, we incorporate the Progressive Growing GAN (PGGAN), a network architecture that iteratively trains smaller-resolution GANs to gradually build up to a very high resolution, to generate 256x256 river satellite imagery. With conventional GAN architectures, difficulties soon arise in terms of exponential increase of training time and vanishing/exploding gradient issues, which the PGGAN implementation seems to significantly reduce. Our preliminary results show great promise in capturing the detail of river flow and green areas present in river satellite images that can be used for supporting hydroinformatics studies. |
| Tasks | Image Generation |
| Published | 2020-02-14 |
| URL | https://arxiv.org/abs/2003.00826v2 |
| https://arxiv.org/pdf/2003.00826v2.pdf | |
| PWC | https://paperswithcode.com/paper/realistic-river-image-synthesis-using-deep |
| Repo | |
| Framework | |
VisMaker: a Question-Oriented Visualization Recommender System for Data Exploration
| Title | VisMaker: a Question-Oriented Visualization Recommender System for Data Exploration |
| Authors | Raul de Araújo Lima, Simone Diniz Junqueira Barbosa |
| Abstract | The increasingly rapid growth of data production and the consequent need to explore data to obtain answers to the most varied questions have promoted the development of tools to facilitate the manipulation and construction of data visualizations. However, building useful data visualizations is not a trivial task: it may involve a large number of subtle decisions that require experience from their designer. In this paper, we present VisMaker, a visualization recommender tool that uses a set of rules to present visualization recommendations organized and described through questions, in order to facilitate the understanding of the recommendations and assisting the visual exploration process. We carried out two studies comparing our tool with Voyager 2 and analyzed some aspects of the use of tools. We collected feedback from participants to identify the advantages and disadvantages of our recommendation approach. As a result, we gathered comments to help improve the development of tools in this domain. |
| Tasks | Recommendation Systems |
| Published | 2020-02-14 |
| URL | https://arxiv.org/abs/2002.06125v1 |
| https://arxiv.org/pdf/2002.06125v1.pdf | |
| PWC | https://paperswithcode.com/paper/vismaker-a-question-oriented-visualization |
| Repo | |
| Framework | |
Performance-Oriented Neural Architecture Search
| Title | Performance-Oriented Neural Architecture Search |
| Authors | Andrew Anderson, Jing Su, Rozenn Dahyot, David Gregg |
| Abstract | Hardware-Software Co-Design is a highly successful strategy for improving performance of domain-specific computing systems. We argue for the application of the same methodology to deep learning; specifically, we propose to extend neural architecture search with information about the hardware to ensure that the model designs produced are highly efficient in addition to the typical criteria around accuracy. Using the task of keyword spotting in audio on edge computing devices, we demonstrate that our approach results in neural architecture that is not only highly accurate, but also efficiently mapped to the computing platform which will perform the inference. Using our modified neural architecture search, we demonstrate $0.88%$ increase in TOP-1 accuracy with $1.85\times$ reduction in latency for keyword spotting in audio on an embedded SoC, and $1.59\times$ on a high-end GPU. |
| Tasks | Keyword Spotting, Neural Architecture Search |
| Published | 2020-01-09 |
| URL | https://arxiv.org/abs/2001.02976v1 |
| https://arxiv.org/pdf/2001.02976v1.pdf | |
| PWC | https://paperswithcode.com/paper/performance-oriented-neural-architecture |
| Repo | |
| Framework | |
EdgeNets:Edge Varying Graph Neural Networks
| Title | EdgeNets:Edge Varying Graph Neural Networks |
| Authors | Elvin Isufi, Fernando Gama, Alejandro Ribeiro |
| Abstract | Recent years have seen a surge of interest in developing neural networks for graphs and data supported on graphs. The graph is leveraged at each layer of the neural network as a parameterization to capture detail at the node level with a reduced number of parameters and computational complexity. Following this rationale, this paper puts forth a general framework that unifies state-of-the-art graph neural networks (GNNs) through the concept of EdgeNet. An EdgeNet is a GNN architecture that allows different nodes to use different parameters to weigh the information of different neighbors. By extrapolating this strategy to more iterations between neighboring nodes, the EdgeNet learns edge- and neighbor-dependent weights to capture local detail. This is the most general linear and local operation that a node can perform and encompasses under one formulation all existing graph convolutional neural networks (GCNNs) as well as graph attention networks (GATs). In writing different GNN architectures with a common language, EdgeNets highlight specific architecture advantages and limitations, while providing guidelines to improve their capacity without compromising their local implementation. For instance, we show that GCNNs have a parameter sharing structure that induces permutation equivariance. This can be an advantage or a limitation, depending on the application. In cases where it is a limitation, we propose hybrid approaches and provide insights to develop several other solutions that promote parameter sharing without enforcing permutation equivariance. Another interesting conclusion is the unification of GCNNs and GATs -approaches that have been so far perceived as separate. In particular, we show that GATs are GCNNs on a graph that is learned from the features. This particularization opens the doors to develop alternative attention mechanisms for improving discriminatory power. |
| Tasks | |
| Published | 2020-01-21 |
| URL | https://arxiv.org/abs/2001.07620v2 |
| https://arxiv.org/pdf/2001.07620v2.pdf | |
| PWC | https://paperswithcode.com/paper/edgenetsedge-varying-graph-neural-networks |
| Repo | |
| Framework | |
From Seeing to Moving: A Survey on Learning for Visual Indoor Navigation (VIN)
| Title | From Seeing to Moving: A Survey on Learning for Visual Indoor Navigation (VIN) |
| Authors | Xin Ye, Yezhou Yang |
| Abstract | Visual Indoor Navigation (VIN) task has drawn increasing attentions from the data-driven machine learning communities especially with the recent reported success from learning-based methods. Due to the innate complexity of this task, researchers have tried approaching the problem from a variety of different angles, the full scope of which has not yet been captured within an overarching report. In this survey, we discuss the representative work of learning-based approaches for visual navigation and its related tasks. Firstly, we summarize the current work in terms of task representations and applied methods along with their properties. We then further identify and discuss lingering issues impeding the performance of VIN tasks and motivate future research in these key areas worth exploring in the future for the community. |
| Tasks | Visual Navigation |
| Published | 2020-02-26 |
| URL | https://arxiv.org/abs/2002.11310v1 |
| https://arxiv.org/pdf/2002.11310v1.pdf | |
| PWC | https://paperswithcode.com/paper/from-seeing-to-moving-a-survey-on-learning |
| Repo | |
| Framework | |
Towards Transparent Robotic Planning via Contrastive Explanations
| Title | Towards Transparent Robotic Planning via Contrastive Explanations |
| Authors | Shenghui Chen, Kayla Boggess, Lu Feng |
| Abstract | Providing explanations of chosen robotic actions can help to increase the transparency of robotic planning and improve users’ trust. Social sciences suggest that the best explanations are contrastive, explaining not just why one action is taken, but why one action is taken instead of another. We formalize the notion of contrastive explanations for robotic planning policies based on Markov decision processes, drawing on insights from the social sciences. We present methods for the automated generation of contrastive explanations with three key factors: selectiveness, constrictiveness, and responsibility. The results of a user study with 100 participants on the Amazon Mechanical Turk platform show that our generated contrastive explanations can help to increase users’ understanding and trust of robotic planning policies while reducing users’ cognitive burden. |
| Tasks | |
| Published | 2020-03-16 |
| URL | https://arxiv.org/abs/2003.07425v1 |
| https://arxiv.org/pdf/2003.07425v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-transparent-robotic-planning-via |
| Repo | |
| Framework | |
Data Warehouse and Decision Support on Integrated Crop Big Data
| Title | Data Warehouse and Decision Support on Integrated Crop Big Data |
| Authors | V. M. Ngo, N. A. Le-Khac, M. T. Kechadi |
| Abstract | In recent years, precision agriculture is becoming very popular. The introduction of modern information and communication technologies for collecting and processing Agricultural data revolutionise the agriculture practises. This has started a while ago (early 20th century) and it is driven by the low cost of collecting data about everything; from information on fields such as seed, soil, fertiliser, pest, to weather data, drones and satellites images. Specially, the agricultural data mining today is considered as Big Data application in terms of volume, variety, velocity and veracity. Hence it leads to challenges in processing vast amounts of complex and diverse information to extract useful knowledge for the farmer, agronomist, and other businesses. It is a key foundation to establishing a crop intelligence platform, which will enable efficient resource management and high quality agronomy decision making and recommendations. In this paper, we designed and implemented a continental level agricultural data warehouse (ADW). ADW is characterised by its (1) flexible schema; (2) data integration from real agricultural multi datasets; (3) data science and business intelligent support; (4) high performance; (5) high storage; (6) security; (7) governance and monitoring; (8) consistency, availability and partition tolerant; (9) cloud compatibility. We also evaluate the performance of ADW and present some complex queries to extract and return necessary knowledge about crop management. |
| Tasks | Decision Making |
| Published | 2020-03-10 |
| URL | https://arxiv.org/abs/2003.04470v1 |
| https://arxiv.org/pdf/2003.04470v1.pdf | |
| PWC | https://paperswithcode.com/paper/data-warehouse-and-decision-support-on |
| Repo | |
| Framework | |
Infrequent adverse event prediction in low carbon energy production using machine learning
| Title | Infrequent adverse event prediction in low carbon energy production using machine learning |
| Authors | Stefano Coniglio, Anthony J. Dunn, Alain B. Zemkoho |
| Abstract | Machine Learning is one of the fastest growing fields in academia. Many industries are aiming to incorporate machine learning tools into their day to day operation. However the keystone of doing so, is recognising when you have a problem which can be solved using machine learning. Adverse event prediction is one such problem. There are a wide range of methods for the production of sustainable energy. In many of which adverse events can occur which can impede energy production and even damage equipment. The two examples of adverse event prediction in sustainable energy production we examine in this paper are foam formation in anaerobic digestion and condenser fouling in steam turbines as used in nuclear power stations. In this paper we will propose a framework for: formalising a classification problem based around adverse event prediction, building predictive maintenance models capable of predicting these events before they occur and testing the reliability of these models. |
| Tasks | |
| Published | 2020-01-19 |
| URL | https://arxiv.org/abs/2001.06916v1 |
| https://arxiv.org/pdf/2001.06916v1.pdf | |
| PWC | https://paperswithcode.com/paper/infrequent-adverse-event-prediction-in-low |
| Repo | |
| Framework | |
Multi-Task Learning by a Top-Down Control Network
| Title | Multi-Task Learning by a Top-Down Control Network |
| Authors | Hila Levi, Shimon Ullman |
| Abstract | A general problem that received considerable recent attention is how to perform multiple tasks in the same network, maximizing both prediction accuracy and efficiency of training. Recent approaches address this problem by branching networks, or by a channel-wise modulation of the feature-maps with task specific vectors. We propose a novel architecture that uses a top-down network to modify the main network according to the task in a channel-wise, as well as spatial-wise, image-dependent computation scheme. We show the effectiveness of our scheme by achieving better results than alternative state-of-the-art approaches to multi-task learning. We also demonstrate our advantages in terms of task selectivity, scaling the number of tasks, learning from fewer examples and interpretability. |
| Tasks | Multi-Task Learning |
| Published | 2020-02-09 |
| URL | https://arxiv.org/abs/2002.03335v2 |
| https://arxiv.org/pdf/2002.03335v2.pdf | |
| PWC | https://paperswithcode.com/paper/multi-task-learning-by-a-top-down-control |
| Repo | |
| Framework | |
Unsupervised K-modal Styled Content Generation
| Title | Unsupervised K-modal Styled Content Generation |
| Authors | Omry Sendik, Dani Lischinski, Daniel Cohen-Or |
| Abstract | The emergence of generative models based on deep neural networks has recently enabled the automatic generation of massive amounts of graphical content, both in 2D and in 3D. Generative Adversarial Networks (GANs) and style control mechanisms, such as Adaptive Instance Normalization (AdaIN), have proved particularly effective in this context, culminating in the state-of-the-art StyleGAN architecture. While such models are able to learn diverse distributions, provided a sufficiently large training set, they are not well-suited for scenarios where the distribution of the training data exhibits a multi-modal behavior. In such cases, reshaping a uniform or normal distribution over the latent space into a complex multi-modal distribution in the data domain is challenging, and the quality of the generated samples may suffer as a result. Furthermore, the different modes are entangled with the other attributes of the data, and thus, mode transitions cannot be well controlled via continuous style parameters. In this paper, we introduce uMM-GAN, a novel architecture designed to better model such multi-modal distributions, in an unsupervised fashion. Building upon the StyleGAN architecture, our network learns multiple modes, in a completely unsupervised manner, and combines them using a set of learned weights. Quite strikingly, we show that this approach is capable of homing onto the natural modes in the training set, and effectively approximates the complex distribution as a superposition of multiple simple ones. We demonstrate that uMM-GAN copes better with multi-modal distributions, while at the same time disentangling between the modes and their style, thereby providing an independent degree of control over the generated content. |
| Tasks | |
| Published | 2020-01-10 |
| URL | https://arxiv.org/abs/2001.03640v1 |
| https://arxiv.org/pdf/2001.03640v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-k-modal-styled-content |
| Repo | |
| Framework | |
