Paper Group ANR 551
Label Super Resolution with Inter-Instance Loss. Virtual Adversarial Training on Graph Convolutional Networks in Node Classification. MixModule: Mixed CNN Kernel Module for Medical Image Segmentation. Identifying Malicious Web Domains Using Machine Learning Techniques with Online Credibility and Performance Data. Persuasion for Good: Towards a Pers …
Label Super Resolution with Inter-Instance Loss
| Title | Label Super Resolution with Inter-Instance Loss |
| Authors | Maozheng Zhao, Le Hou, Han Le, Dimitris Samaras, Nebojsa Jojic, Danielle Fassler, Tahsin Kurc, Rajarsi Gupta, Kolya Malkin, Shroyer Kenneth, Joel Saltz |
| Abstract | For the task of semantic segmentation, high-resolution (pixel-level) ground truth is very expensive to collect, especially for high resolution images such as gigapixel pathology images. On the other hand, collecting low resolution labels (labels for a block of pixels) for these high resolution images is much more cost efficient. Conventional methods trained on these low-resolution labels are only capable of giving low-resolution predictions. The existing state-of-the-art label super resolution (LSR) method is capable of predicting high resolution labels, using only low-resolution supervision, given the joint distribution between low resolution and high resolution labels. However, it does not consider the inter-instance variance which is crucial in the ideal mathematical formulation. In this work, we propose a novel loss function modeling the inter-instance variance. We test our method on a real world application: infiltrating breast cancer region segmentation in histopathology slides. Experimental results show the effectiveness of our method. |
| Tasks | Semantic Segmentation, Super-Resolution |
| Published | 2019-04-09 |
| URL | https://arxiv.org/abs/1904.04429v2 |
| https://arxiv.org/pdf/1904.04429v2.pdf | |
| PWC | https://paperswithcode.com/paper/label-super-resolution-with-inter-instance |
| Repo | |
| Framework | |
Virtual Adversarial Training on Graph Convolutional Networks in Node Classification
| Title | Virtual Adversarial Training on Graph Convolutional Networks in Node Classification |
| Authors | Ke Sun, Zhouchen Lin, Hantao Guo, Zhanxing Zhu |
| Abstract | The effectiveness of Graph Convolutional Networks (GCNs) has been demonstrated in a wide range of graph-based machine learning tasks. However, the update of parameters in GCNs is only from labeled nodes, lacking the utilization of unlabeled data. In this paper, we apply Virtual Adversarial Training (VAT), an adversarial regularization method based on both labeled and unlabeled data, on the supervised loss of GCN to enhance its generalization performance. By imposing virtually adversarial smoothness on the posterior distribution in semi-supervised learning, VAT yields improvement on the Symmetrical Laplacian Smoothness of GCNs. In addition, due to the difference of property in features, we perturb virtual adversarial perturbations on sparse and dense features, resulting in GCN Sparse VAT (GCNSVAT) and GCN Dense VAT (GCNDVAT) algorithms, respectively. Extensive experiments verify the effectiveness of our two methods across different training sizes. Our work paves the way towards better understanding the direction of improvement on GCNs in the future. |
| Tasks | Node Classification |
| Published | 2019-02-28 |
| URL | https://arxiv.org/abs/1902.11045v2 |
| https://arxiv.org/pdf/1902.11045v2.pdf | |
| PWC | https://paperswithcode.com/paper/virtual-adversarial-training-on-graph |
| Repo | |
| Framework | |
MixModule: Mixed CNN Kernel Module for Medical Image Segmentation
| Title | MixModule: Mixed CNN Kernel Module for Medical Image Segmentation |
| Authors | Henry H. Yu, Xue Feng, Hao Sun, Ziwen Wang |
| Abstract | Convolutional neural networks (CNNs) have been successfully applied to medical image classification, segmentation, and related tasks. Among the many CNNs architectures, U-Net and its improved versions based are widely used and achieve state-of-the-art performance these years. These improved architectures focus on structural improvements and the size of the convolution kernel is generally fixed. In this paper, we propose a module that combines the benefits of multiple kernel sizes and we apply the proposed module to U-Net and its variants. We test our module on three segmentation benchmark datasets and experimental results show significant improvement. |
| Tasks | Image Classification, Medical Image Segmentation, Semantic Segmentation |
| Published | 2019-10-19 |
| URL | https://arxiv.org/abs/1910.08728v2 |
| https://arxiv.org/pdf/1910.08728v2.pdf | |
| PWC | https://paperswithcode.com/paper/mixmodule-mixed-cnn-kernel-module-for-medical |
| Repo | |
| Framework | |
Identifying Malicious Web Domains Using Machine Learning Techniques with Online Credibility and Performance Data
| Title | Identifying Malicious Web Domains Using Machine Learning Techniques with Online Credibility and Performance Data |
| Authors | Zhongyi Hu, Raymond Chiong, Ilung Pranata, Willy Susilo, Yukun Bao |
| Abstract | Malicious web domains represent a big threat to web users’ privacy and security. With so much freely available data on the Internet about web domains’ popularity and performance, this study investigated the performance of well-known machine learning techniques used in conjunction with this type of online data to identify malicious web domains. Two datasets consisting of malware and phishing domains were collected to build and evaluate the machine learning classifiers. Five single classifiers and four ensemble classifiers were applied to distinguish malicious domains from benign ones. In addition, a binary particle swarm optimisation (BPSO) based feature selection method was used to improve the performance of single classifiers. Experimental results show that, based on the web domains’ popularity and performance data features, the examined machine learning techniques can accurately identify malicious domains in different ways. Furthermore, the BPSO-based feature selection procedure is shown to be an effective way to improve the performance of classifiers. |
| Tasks | Feature Selection |
| Published | 2019-02-23 |
| URL | http://arxiv.org/abs/1902.08792v1 |
| http://arxiv.org/pdf/1902.08792v1.pdf | |
| PWC | https://paperswithcode.com/paper/identifying-malicious-web-domains-using |
| Repo | |
| Framework | |
Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good
| Title | Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good |
| Authors | Xuewei Wang, Weiyan Shi, Richard Kim, Yoojung Oh, Sijia Yang, Jingwen Zhang, Zhou Yu |
| Abstract | Developing intelligent persuasive conversational agents to change people’s opinions and actions for social good is the frontier in advancing the ethical development of automated dialogue systems. To do so, the first step is to understand the intricate organization of strategic disclosures and appeals employed in human persuasion conversations. We designed an online persuasion task where one participant was asked to persuade the other to donate to a specific charity. We collected a large dataset with 1,017 dialogues and annotated emerging persuasion strategies from a subset. Based on the annotation, we built a baseline classifier with context information and sentence-level features to predict the 10 persuasion strategies used in the corpus. Furthermore, to develop an understanding of personalized persuasion processes, we analyzed the relationships between individuals’ demographic and psychological backgrounds including personality, morality, value systems, and their willingness for donation. Then, we analyzed which types of persuasion strategies led to a greater amount of donation depending on the individuals’ personal backgrounds. This work lays the ground for developing a personalized persuasive dialogue system. |
| Tasks | |
| Published | 2019-06-16 |
| URL | https://arxiv.org/abs/1906.06725v2 |
| https://arxiv.org/pdf/1906.06725v2.pdf | |
| PWC | https://paperswithcode.com/paper/persuasion-for-good-towards-a-personalized |
| Repo | |
| Framework | |
Open Issues in Combating Fake News: Interpretability as an Opportunity
| Title | Open Issues in Combating Fake News: Interpretability as an Opportunity |
| Authors | Sina Mohseni, Eric Ragan, Xia Hu |
| Abstract | Combating fake news needs a variety of defense methods. Although rumor detection and various linguistic analysis techniques are common methods to detect false content in social media, there are other feasible mitigation approaches that could be explored in the machine learning community. In this paper, we present open issues and opportunities in fake news research that need further attention. We first review different stages of the news life cycle in social media and discuss core vulnerability issues for news feed algorithms in propagating fake news content with three examples. We then discuss how complexity and unclarity of the fake news problem limit the advancements in this field. Lastly, we present research opportunities from interpretable machine learning to mitigate fake news problems with 1) interpretable fake news detection and 2) transparent news feed algorithms. We propose three dimensions of interpretability consisting of algorithmic interpretability, human interpretability, and the inclusion of supporting evidence that can benefit fake news mitigation methods in different ways. |
| Tasks | Fake News Detection, Interpretable Machine Learning |
| Published | 2019-04-04 |
| URL | http://arxiv.org/abs/1904.03016v1 |
| http://arxiv.org/pdf/1904.03016v1.pdf | |
| PWC | https://paperswithcode.com/paper/open-issues-in-combating-fake-news |
| Repo | |
| Framework | |
Deep Modulation Embedding
| Title | Deep Modulation Embedding |
| Authors | Amin Abbasloo, Alan Salari |
| Abstract | Deep neural network has recently shown very promising applications in different research directions and attracted the industry attention as well. Although the idea was introduced in the past but just recently the main limitation of using this class of algorithms is solved by enabling parallel computing on GPU hardware. Opening the possibility of hardware prototyping with proven superiority of this class of algorithm, trigger several research directions in communication system too. Among them cognitive radio, modulation recognition, learning based receiver and transceiver are already given very interesting result in simulation and real experimental evaluation implemented on software defined radio. Specifically, modulation recognition is mostly approached as a classification problem which is a supervised learning framework. But it is here addressed as an unsupervised problem with introducing new features for training, a new loss function and investigating the robustness of the pipeline against several mismatch conditions. |
| Tasks | |
| Published | 2019-02-17 |
| URL | http://arxiv.org/abs/1902.07316v2 |
| http://arxiv.org/pdf/1902.07316v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-modulation-embedding |
| Repo | |
| Framework | |
Effects of a Social Force Model reward in Robot Navigation based on Deep Reinforcement Learning
| Title | Effects of a Social Force Model reward in Robot Navigation based on Deep Reinforcement Learning |
| Authors | Óscar Gil Viyuela, Alberto Sanfeliu |
| Abstract | In this paper is proposed an inclusion of the Social Force Model (SFM) into a concrete Deep Reinforcement Learning (RL) framework for robot navigation. These types of techniques have demonstrated to be useful to deal with different types of environments to achieve a goal. In Deep RL, a description of the world to describe the states and a reward adapted to the environment are crucial elements to get the desire behaviour and achieve a high performance. For this reason, this work adds a dense reward function based on SFM and uses the forces in the states like an additional description. Furthermore, obstacles are added to improve the behaviour of works that only consider moving agents. This SFM inclusion can offer a better description of the obstacles for the navigation. Several simulations have been done to check the effects of these modifications in the average performance. |
| Tasks | Robot Navigation |
| Published | 2019-12-08 |
| URL | https://arxiv.org/abs/1912.03747v1 |
| https://arxiv.org/pdf/1912.03747v1.pdf | |
| PWC | https://paperswithcode.com/paper/effects-of-a-social-force-model-reward-in |
| Repo | |
| Framework | |
Network Lens: Node Classification in Topologically Heterogeneous Networks
| Title | Network Lens: Node Classification in Topologically Heterogeneous Networks |
| Authors | Kshiteesh Hegde, Malik Magdon-Ismail |
| Abstract | We study the problem of identifying different behaviors occurring in different parts of a large heterogenous network. We zoom in to the network using lenses of different sizes to capture the local structure of the network. These network signatures are then weighted to provide a set of predicted labels for every node. We achieve a peak accuracy of $\sim42%$ (random=$11%$) on two networks with $\sim100,000$ and $\sim1,000,000$ nodes each. Further, we perform better than random even when the given node is connected to up to 5 different types of networks. Finally, we perform this analysis on homogeneous networks and show that highly structured networks have high homogeneity. |
| Tasks | Node Classification |
| Published | 2019-01-15 |
| URL | http://arxiv.org/abs/1901.09681v1 |
| http://arxiv.org/pdf/1901.09681v1.pdf | |
| PWC | https://paperswithcode.com/paper/network-lens-node-classification-in |
| Repo | |
| Framework | |
Convolutional Dictionary Learning in Hierarchical Networks
| Title | Convolutional Dictionary Learning in Hierarchical Networks |
| Authors | Javier Zazo, Bahareh Tolooshams, Demba Ba |
| Abstract | Filter banks are a popular tool for the analysis of piecewise smooth signals such as natural images. Motivated by the empirically observed properties of scale and detail coefficients of images in the wavelet domain, we propose a hierarchical deep generative model of piecewise smooth signals that is a recursion across scales: the low pass scale coefficients at one layer are obtained by filtering the scale coefficients at the next layer, and adding a high pass detail innovation obtained by filtering a sparse vector. This recursion describes a linear dynamic system that is a non-Gaussian Markov process across scales and is closely related to multilayer-convolutional sparse coding (ML-CSC) generative model for deep networks, except that our model allows for deeper architectures, and combines sparse and non-sparse signal representations. We propose an alternating minimization algorithm for learning the filters in this hierarchical model given observations at layer zero, e.g., natural images. The algorithm alternates between a coefficient-estimation step and a filter update step. The coefficient update step performs sparse (detail) and smooth (scale) coding and, when unfolded, leads to a deep neural network. We use MNIST to demonstrate the representation capabilities of the model, and its derived features (coefficients) for classification. |
| Tasks | Dictionary Learning |
| Published | 2019-07-23 |
| URL | https://arxiv.org/abs/1907.09881v1 |
| https://arxiv.org/pdf/1907.09881v1.pdf | |
| PWC | https://paperswithcode.com/paper/convolutional-dictionary-learning-in |
| Repo | |
| Framework | |
Enhancing Model Interpretability and Accuracy for Disease Progression Prediction via Phenotype-Based Patient Similarity Learning
| Title | Enhancing Model Interpretability and Accuracy for Disease Progression Prediction via Phenotype-Based Patient Similarity Learning |
| Authors | Yue Wang, Tong Wu, Yunlong Wang, Gao Wang |
| Abstract | Models have been proposed to extract temporal patterns from longitudinal electronic health records (EHR) for clinical predictive models. However, the common relations among patients (e.g., receiving the same medical treatments) were rarely considered. In this paper, we propose to learn patient similarity features as phenotypes from the aggregated patient-medical service matrix using non-negative matrix factorization. On real-world medical claim data, we show that the learned phenotypes are coherent within each group, and also explanatory and indicative of targeted diseases. We conducted experiments to predict the diagnoses for Chronic Lymphocytic Leukemia (CLL) patients. Results show that the phenotype-based similarity features can improve prediction over multiple baselines, including logistic regression, random forest, convolutional neural network, and more. |
| Tasks | |
| Published | 2019-09-26 |
| URL | https://arxiv.org/abs/1909.11913v1 |
| https://arxiv.org/pdf/1909.11913v1.pdf | |
| PWC | https://paperswithcode.com/paper/enhancing-model-interpretability-and-accuracy |
| Repo | |
| Framework | |
To Populate is To Regulate
| Title | To Populate is To Regulate |
| Authors | Nicole Fitzgerald |
| Abstract | We examine the effects of instantiating Lewis signaling games within a population of speaker and listener agents with the aim of producing a set of general and robust representations of unstructured pixel data. Preliminary experiments suggest that the set of representations associated with languages generated within a population outperform those generated between a single speaker-listener pair on this objective, making a case for the adoption of population-based approaches in emergent communication studies. Furthermore, post-hoc analysis reveals that population-based learning induces a number of novel factors to the conventional emergent communication setup, inviting a wide range of future research questions regarding communication dynamics and the flow of information within them. |
| Tasks | |
| Published | 2019-11-06 |
| URL | https://arxiv.org/abs/1911.04362v1 |
| https://arxiv.org/pdf/1911.04362v1.pdf | |
| PWC | https://paperswithcode.com/paper/to-populate-is-to-regulate |
| Repo | |
| Framework | |
Learning with Good Feature Representations in Bandits and in RL with a Generative Model
| Title | Learning with Good Feature Representations in Bandits and in RL with a Generative Model |
| Authors | Tor Lattimore, Csaba Szepesvari, Gellert Weisz |
| Abstract | The construction by Du et al. (2019) implies that even if a learner is given linear features in $\mathbb R^d$ that approximate the rewards in a bandit with a uniform error of $\epsilon$, then searching for an action that is optimal up to $O(\epsilon)$ requires examining essentially all actions. We use the Kiefer-Wolfowitz theorem to prove a positive result that by checking only a few actions, a learner can always find an action that is suboptimal with an error of at most $O(\epsilon \sqrt{d})$. Thus, features are useful when the approximation error is small relative to the dimensionality of the features. The idea is applied to stochastic bandits and reinforcement learning with a generative model where the learner has access to $d$-dimensional linear features that approximate the action-value functions for all policies to an accuracy of $\epsilon$. For linear bandits, we prove a bound on the regret of order $\sqrt{dn \log(k)} + \epsilon n \sqrt{d} \log(n)$ with $k$ the number of actions and $n$ the horizon. For RL we show that approximate policy iteration can learn a policy that is optimal up to an additive error of order $\epsilon \sqrt{d}/(1 - \gamma)^2$ and using $d/(\epsilon^2(1 - \gamma)^4)$ samples from a generative model. These bounds are independent of the finer details of the features. We also investigate how the structure of the feature set impacts the tradeoff between sample complexity and estimation error. |
| Tasks | |
| Published | 2019-11-18 |
| URL | https://arxiv.org/abs/1911.07676v2 |
| https://arxiv.org/pdf/1911.07676v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-with-good-feature-representations-in |
| Repo | |
| Framework | |
MULEX: Disentangling Exploitation from Exploration in Deep RL
| Title | MULEX: Disentangling Exploitation from Exploration in Deep RL |
| Authors | Lucas Beyer, Damien Vincent, Olivier Teboul, Sylvain Gelly, Matthieu Geist, Olivier Pietquin |
| Abstract | An agent learning through interactions should balance its action selection process between probing the environment to discover new rewards and using the information acquired in the past to adopt useful behaviour. This trade-off is usually obtained by perturbing either the agent’s actions (e.g., e-greedy or Gibbs sampling) or the agent’s parameters (e.g., NoisyNet), or by modifying the reward it receives (e.g., exploration bonus, intrinsic motivation, or hand-shaped rewards). Here, we adopt a disruptive but simple and generic perspective, where we explicitly disentangle exploration and exploitation. Different losses are optimized in parallel, one of them coming from the true objective (maximizing cumulative rewards from the environment) and others being related to exploration. Every loss is used in turn to learn a policy that generates transitions, all shared in a single replay buffer. Off-policy methods are then applied to these transitions to optimize each loss. We showcase our approach on a hard-exploration environment, show its sample-efficiency and robustness, and discuss further implications. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://arxiv.org/abs/1907.00868v1 |
| https://arxiv.org/pdf/1907.00868v1.pdf | |
| PWC | https://paperswithcode.com/paper/mulex-disentangling-exploitation-from |
| Repo | |
| Framework | |
Intent-Aware Probabilistic Trajectory Estimation for Collision Prediction with Uncertainty Quantification
| Title | Intent-Aware Probabilistic Trajectory Estimation for Collision Prediction with Uncertainty Quantification |
| Authors | Andrew Patterson, Arun Lakshmanan, Naira Hovakimyan |
| Abstract | Collision prediction in a dynamic and unknown environment relies on knowledge of how the environment is changing. Many collision prediction methods rely on deterministic knowledge of how obstacles are moving in the environment. However, complete deterministic knowledge of the obstacles’ motion is often unavailable. This work proposes a Gaussian process based prediction method that replaces the assumption of deterministic knowledge of each obstacle’s future behavior with probabilistic knowledge, to allow a larger class of obstacles to be considered. The method solely relies on position and velocity measurements to predict collisions with dynamic obstacles. We show that the uncertainty region for obstacle positions can be expressed in terms of a combination of polynomials generated with Gaussian process regression. To control the growth of uncertainty over arbitrary time horizons, a probabilistic obstacle intention is assumed as a distribution over obstacle positions and velocities, which can be naturally included in the Gaussian process framework. Our approach is demonstrated in two case studies in which (i), an obstacle overtakes the agent and (ii), an obstacle crosses the agent’s path perpendicularly. In these simulations we show that the collision can be predicted despite having limited knowledge of the obstacle’s behavior. |
| Tasks | |
| Published | 2019-04-04 |
| URL | http://arxiv.org/abs/1904.02765v1 |
| http://arxiv.org/pdf/1904.02765v1.pdf | |
| PWC | https://paperswithcode.com/paper/intent-aware-probabilistic-trajectory |
| Repo | |
| Framework | |
