Paper Group ANR 1467
Meta-GNN: On Few-shot Node Classification in Graph Meta-learning. Beyond the EM Algorithm: Constrained Optimization Methods for Latent Class Model. Optimal Nonparametric Inference under Quantization. Improved Safe Real-time Heuristic Search. Depthwise Convolution is All You Need for Learning Multiple Visual Domains. Monitoring Achilles tendon heali …
Meta-GNN: On Few-shot Node Classification in Graph Meta-learning
| Title | Meta-GNN: On Few-shot Node Classification in Graph Meta-learning |
| Authors | Fan Zhou, Chengtai Cao, Kunpeng Zhang, Goce Trajcevski, Ting Zhong, Ji Geng |
| Abstract | Meta-learning has received a tremendous recent attention as a possible approach for mimicking human intelligence, i.e., acquiring new knowledge and skills with little or even no demonstration. Most of the existing meta-learning methods are proposed to tackle few-shot learning problems such as image and text, in rather Euclidean domain. However, there are very few works applying meta-learning to non-Euclidean domains, and the recently proposed graph neural networks (GNNs) models do not perform effectively on graph few-shot learning problems. Towards this, we propose a novel graph meta-learning framework – Meta-GNN – to tackle the few-shot node classification problem in graph meta-learning settings. It obtains the prior knowledge of classifiers by training on many similar few-shot learning tasks and then classifies the nodes from new classes with only few labeled samples. Additionally, Meta-GNN is a general model that can be straightforwardly incorporated into any existing state-of-the-art GNN. Our experiments conducted on three benchmark datasets demonstrate that our proposed approach not only improves the node classification performance by a large margin on few-shot learning problems in meta-learning paradigm, but also learns a more general and flexible model for task adaption. |
| Tasks | Few-Shot Learning, Meta-Learning, Node Classification |
| Published | 2019-05-23 |
| URL | https://arxiv.org/abs/1905.09718v1 |
| https://arxiv.org/pdf/1905.09718v1.pdf | |
| PWC | https://paperswithcode.com/paper/meta-gnn-on-few-shot-node-classification-in |
| Repo | |
| Framework | |
Beyond the EM Algorithm: Constrained Optimization Methods for Latent Class Model
| Title | Beyond the EM Algorithm: Constrained Optimization Methods for Latent Class Model |
| Authors | Hao Chen, Lanshan Han, Alvin Lim |
| Abstract | Latent class model (LCM), which is a finite mixture of different categorical distributions, is one of the most widely used models in statistics and machine learning fields. Because of its non-continuous nature and the flexibility in shape, researchers in practice areas such as marketing and social sciences also frequently use LCM to gain insights from their data. One likelihood-based method, the Expectation-Maximization (EM) algorithm, is often used to obtain the model estimators. However, the EM algorithm is well-known for its notoriously slow convergence. In this research, we explore alternative likelihood-based methods that can potential remedy the slow convergence of the EM algorithm. More specifically, we regard likelihood-based approach as a constrained nonlinear optimization problem, and apply quasi-Newton type methods to solve them. We examine two different constrained optimization methods to maximize the log likelihood function. We present simulation study results to show that the proposed methods not only converge in less iterations than the EM algorithm but also produce more accurate model estimators. |
| Tasks | |
| Published | 2019-01-09 |
| URL | https://arxiv.org/abs/1901.02928v3 |
| https://arxiv.org/pdf/1901.02928v3.pdf | |
| PWC | https://paperswithcode.com/paper/beyond-the-em-algorithm-constrained |
| Repo | |
| Framework | |
Optimal Nonparametric Inference under Quantization
| Title | Optimal Nonparametric Inference under Quantization |
| Authors | Ruiqi Liu, Ganggang Xu, Zuofeng Shang |
| Abstract | Statistical inference based on lossy or incomplete samples is of fundamental importance in research areas such as signal/image processing, medical image storage, remote sensing, signal transmission. In this paper, we propose a nonparametric testing procedure based on quantized samples. In contrast to the classic nonparametric approach, our method lives on a coarse grid of sample information and are simple-to-use. Under mild technical conditions, we establish the asymptotic properties of the proposed procedures including asymptotic null distribution of the quantization test statistic as well as its minimax power optimality. Concrete quantizers are constructed for achieving the minimax optimality in practical use. Simulation results and a real data analysis are provided to demonstrate the validity and effectiveness of the proposed test. Our work bridges the classical nonparametric inference to modern lossy data setting. |
| Tasks | Quantization |
| Published | 2019-01-24 |
| URL | http://arxiv.org/abs/1901.08571v2 |
| http://arxiv.org/pdf/1901.08571v2.pdf | |
| PWC | https://paperswithcode.com/paper/optimal-nonparametric-inference-under |
| Repo | |
| Framework | |
Improved Safe Real-time Heuristic Search
| Title | Improved Safe Real-time Heuristic Search |
| Authors | Bence Cserna, Kevin C. Gall, Wheeler Ruml |
| Abstract | A fundamental concern in real-time planning is the presence of dead-ends in the state space, from which no goal is reachable. Recently, the SafeRTS algorithm was proposed for searching in such spaces. SafeRTS exploits a user-provided predicate to identify safe states, from which a goal is likely reachable, and attempts to maintain a backup plan for reaching a safe state at all times. In this paper, we study the SafeRTS approach, identify certain properties of its behavior, and design an improved framework for safe real-time search. We prove that the new approach performs at least as well as SafeRTS and present experimental results showing that its promise is fulfilled in practice. |
| Tasks | |
| Published | 2019-05-15 |
| URL | https://arxiv.org/abs/1905.06402v1 |
| https://arxiv.org/pdf/1905.06402v1.pdf | |
| PWC | https://paperswithcode.com/paper/improved-safe-real-time-heuristic-search |
| Repo | |
| Framework | |
Depthwise Convolution is All You Need for Learning Multiple Visual Domains
| Title | Depthwise Convolution is All You Need for Learning Multiple Visual Domains |
| Authors | Yunhui Guo, Yandong Li, Rogerio Feris, Liqiang Wang, Tajana Rosing |
| Abstract | There is a growing interest in designing models that can deal with images from different visual domains. If there exists a universal structure in different visual domains that can be captured via a common parameterization, then we can use a single model for all domains rather than one model per domain. A model aware of the relationships between different domains can also be trained to work on new domains with less resources. However, to identify the reusable structure in a model is not easy. In this paper, we propose a multi-domain learning architecture based on depthwise separable convolution. The proposed approach is based on the assumption that images from different domains share cross-channel correlations but have domain-specific spatial correlations. The proposed model is compact and has minimal overhead when being applied to new domains. Additionally, we introduce a gating mechanism to promote soft sharing between different domains. We evaluate our approach on Visual Decathlon Challenge, a benchmark for testing the ability of multi-domain models. The experiments show that our approach can achieve the highest score while only requiring 50% of the parameters compared with the state-of-the-art approaches. |
| Tasks | |
| Published | 2019-02-03 |
| URL | http://arxiv.org/abs/1902.00927v2 |
| http://arxiv.org/pdf/1902.00927v2.pdf | |
| PWC | https://paperswithcode.com/paper/depthwise-convolution-is-all-you-need-for |
| Repo | |
| Framework | |
Monitoring Achilles tendon healing progress in ultrasound imaging with convolutional neural networks
| Title | Monitoring Achilles tendon healing progress in ultrasound imaging with convolutional neural networks |
| Authors | Piotr Woznicki, Przemyslaw Przybyszewski, Norbert Kapinski, Jakub Zielinski, Beata Ciszkowska-Lyson, Bartosz A. Borucki, Tomasz Trzcinski, Krzysztof S. Nowinski |
| Abstract | Achilles tendon rupture is a debilitating injury, which is typically treated with surgical repair and long-term rehabilitation. The recovery, however, is protracted and often incomplete. Diagnosis, as well as healing progress assessment, are largely based on ultrasound and magnetic resonance imaging. In this paper, we propose an automatic method based on deep learning for analysis of Achilles tendon condition and estimation of its healing progress on ultrasound images. We develop custom convolutional neural networks for classification and regression on healing score and feature extraction. Our models are trained and validated on an acquired dataset of over 250.000 sagittal and over 450.000 axial ultrasound slices. The obtained estimates show a high correlation with the assessment of expert radiologists, with respect to all key parameters describing healing progress. We also observe that parameters associated with i.a. intratendinous healing processes are better modeled with sagittal slices. We prove that ultrasound imaging is quantitatively useful for clinical assessment of Achilles tendon healing process and should be viewed as complementary to magnetic resonance imaging. |
| Tasks | |
| Published | 2019-09-11 |
| URL | https://arxiv.org/abs/1909.04973v1 |
| https://arxiv.org/pdf/1909.04973v1.pdf | |
| PWC | https://paperswithcode.com/paper/monitoring-achilles-tendon-healing-progress |
| Repo | |
| Framework | |
Face X-ray for More General Face Forgery Detection
| Title | Face X-ray for More General Face Forgery Detection |
| Authors | Lingzhi Li, Jianmin Bao, Ting Zhang, Hao Yang, Dong Chen, Fang Wen, Baining Guo |
| Abstract | In this paper we propose a novel image representation called face X-ray for detecting forgery in face images. The face X-ray of an input face image is a greyscale image that reveals whether the input image can be decomposed into the blending of two images from different sources. It does so by showing the blending boundary for a forged image and the absence of blending for a real image. We observe that most existing face manipulation methods share a common step: blending the altered face into an existing background image. For this reason, face X-ray provides an effective way for detecting forgery generated by most existing face manipulation algorithms. Face X-ray is general in the sense that it only assumes the existence of a blending step and does not rely on any knowledge of the artifacts associated with a specific face manipulation technique. Indeed, the algorithm for computing face X-ray can be trained without fake images generated by any of the state-of-the-art face manipulation methods. Extensive experiments show that face X-ray remains effective when applied to forgery generated by unseen face manipulation techniques, while most existing face forgery detection algorithms experience a significant performance drop. |
| Tasks | |
| Published | 2019-12-31 |
| URL | https://arxiv.org/abs/1912.13458v1 |
| https://arxiv.org/pdf/1912.13458v1.pdf | |
| PWC | https://paperswithcode.com/paper/face-x-ray-for-more-general-face-forgery |
| Repo | |
| Framework | |
Cultural Endowment as Collective Improvisation: subjectivity and digital infinity
| Title | Cultural Endowment as Collective Improvisation: subjectivity and digital infinity |
| Authors | Victor Peterson II |
| Abstract | Philosophically, a repertoire of signifying practices as constitutive of a cultural endowment was said to be ambiguous or unworthy of pursuit. Currently, a unique capacity of the mind is considered to be its ability to produce a digital infinity. The infinity produced, here an operation expressing subjectivity, follows a simple principle according to which a limited set of means, here functions, are utilized to produce an infinite range of potentially meaningful expressions. It is from this concept that I propose a theory of subjectivity and the endowment from which it expresses a self in the world(s) it participates. In particular, I make a case for the subjectivity of blackness. I treat subjectivity as an operation in order to address problems with Identity theory, Afro-Pessimism, and to formalize an analysis of blackness despite the onto-epistemological commitments of racialized systems of categorization. In sum, subjectivity will be characterized as poetic computation. |
| Tasks | |
| Published | 2019-07-19 |
| URL | https://arxiv.org/abs/1907.08643v1 |
| https://arxiv.org/pdf/1907.08643v1.pdf | |
| PWC | https://paperswithcode.com/paper/cultural-endowment-as-collective |
| Repo | |
| Framework | |
Stochastic Optimal Control as Approximate Input Inference
| Title | Stochastic Optimal Control as Approximate Input Inference |
| Authors | Joe Watson, Hany Abdulsamad, Jan Peters |
| Abstract | Optimal control of stochastic nonlinear dynamical systems is a major challenge in the domain of robot learning. Given the intractability of the global control problem, state-of-the-art algorithms focus on approximate sequential optimization techniques, that heavily rely on heuristics for regularization in order to achieve stable convergence. By building upon the duality between inference and control, we develop the view of Optimal Control as Input Estimation, devising a probabilistic stochastic optimal control formulation that iteratively infers the optimal input distributions by minimizing an upper bound of the control cost. Inference is performed through Expectation Maximization and message passing on a probabilistic graphical model of the dynamical system, and time-varying linear Gaussian feedback controllers are extracted from the joint state-action distribution. This perspective incorporates uncertainty quantification, effective initialization through priors, and the principled regularization inherent to the Bayesian treatment. Moreover, it can be shown that for deterministic linearized systems, our framework derives the maximum entropy linear quadratic optimal control law. We provide a complete and detailed derivation of our probabilistic approach and highlight its advantages in comparison to other deterministic and probabilistic solvers. |
| Tasks | |
| Published | 2019-10-07 |
| URL | https://arxiv.org/abs/1910.03003v1 |
| https://arxiv.org/pdf/1910.03003v1.pdf | |
| PWC | https://paperswithcode.com/paper/stochastic-optimal-control-as-approximate |
| Repo | |
| Framework | |
Phase mapping for cardiac unipolar electrograms with neural network instead of phase transformation
| Title | Phase mapping for cardiac unipolar electrograms with neural network instead of phase transformation |
| Authors | Konstantin Ushenin, Tatyana Nesterova, Dmitry Shmarko, Vladimir Sholokhov |
| Abstract | A phase mapping is an approach to processing signals of electrograms recorded from the surface of cardiac tissue. The main concept of phase mapping is the application of the phase transformation with the aim to obtain signals with useful properties. In our study, we propose to use a simple sawtooth signal instead of a phase signal for processing of electrogram data and building of the phase maps. We denote transformation that can provide this signal as a phase-like transformation (PLT). PLT defined via a convolutional neural network that is trained on a dataset from computer models of cardiac tissue electrophysiology. The proposed approaches were validated on data from the detailed personalized model of the human torso electrophysiology. This paper includes visualization of the phase map based on PLT and shows the robustness of the proposed approaches in the analysis of the complex non-stationary periodic activity of the excitable cardiac tissue. |
| Tasks | |
| Published | 2019-11-21 |
| URL | https://arxiv.org/abs/1911.09731v2 |
| https://arxiv.org/pdf/1911.09731v2.pdf | |
| PWC | https://paperswithcode.com/paper/phase-mapping-for-cardiac-unipolar |
| Repo | |
| Framework | |
A Dynamically Controlled Recurrent Neural Network for Modeling Dynamical Systems
| Title | A Dynamically Controlled Recurrent Neural Network for Modeling Dynamical Systems |
| Authors | Yiwei Fu, Samer Saab Jr, Asok Ray, Michael Hauser |
| Abstract | This work proposes a novel neural network architecture, called the Dynamically Controlled Recurrent Neural Network (DCRNN), specifically designed to model dynamical systems that are governed by ordinary differential equations (ODEs). The current state vectors of these types of dynamical systems only depend on their state-space models, along with the respective inputs and initial conditions. Long Short-Term Memory (LSTM) networks, which have proven to be very effective for memory-based tasks, may fail to model physical processes as they tend to memorize, rather than learn how to capture the information on the underlying dynamics. The proposed DCRNN includes learnable skip-connections across previously hidden states, and introduces a regularization term in the loss function by relying on Lyapunov stability theory. The regularizer enables the placement of eigenvalues of the transfer function induced by the DCRNN to desired values, thereby acting as an internal controller for the hidden state trajectory. The results show that, for forecasting a chaotic dynamical system, the DCRNN outperforms the LSTM in $100$ out of $100$ randomized experiments by reducing the mean squared error of the LSTM’s forecasting by $80.0% \pm 3.0%$. |
| Tasks | |
| Published | 2019-10-31 |
| URL | https://arxiv.org/abs/1911.00089v1 |
| https://arxiv.org/pdf/1911.00089v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-dynamically-controlled-recurrent-neural |
| Repo | |
| Framework | |
Allowing for equal opportunities for artists in music recommendation
| Title | Allowing for equal opportunities for artists in music recommendation |
| Authors | Christine Bauer |
| Abstract | Promoting diversity in the music sector is widely discussed on the media. While the major problem may lie deep in our society, music information retrieval contributes to promoting diversity or may create unequal opportunities for artists. For example, considering the known problem of popularity bias in music recommendation, it is important to investigate whether the short head of popular music artists and the long tail of less popular ones show similar patterns of diversity—in terms of, for example, age, gender, or ethnic origin—or the popularity bias amplifies a positive or negative effect. I advocate for reasonable opportunities for artists—for (currently) popular artists and artists in the long-tail alike—in music recommender systems. In this work, I represent the position that we need to develop a deep understanding of the biases and inequalities because it is the essential basis to design approaches for music recommendation that provide reasonable opportunities. Thus, research needs to investigate the various reasons that hinder equal opportunity and diversity in music recommendation. |
| Tasks | Information Retrieval, Music Information Retrieval, Recommendation Systems |
| Published | 2019-11-13 |
| URL | https://arxiv.org/abs/1911.05395v1 |
| https://arxiv.org/pdf/1911.05395v1.pdf | |
| PWC | https://paperswithcode.com/paper/allowing-for-equal-opportunities-for-artists |
| Repo | |
| Framework | |
A quantum active learning algorithm for sampling against adversarial attacks
| Title | A quantum active learning algorithm for sampling against adversarial attacks |
| Authors | P. A. M. Casares, M. A. Martin-Delgado |
| Abstract | Adversarial attacks represent a serious menace for learning algorithms and may compromise the security of future autonomous systems. A theorem by Khoury and Hadfield-Menell (KH), provides sufficient conditions to guarantee the robustness of active learning algorithms, but comes with a caveat: it is crucial to know the smallest distance among the classes of the corresponding classification problem. We propose a theoretical framework that allows us to think of active learning as sampling the most promising new points to be classified, so that the minimum distance between classes can be found and the theorem KH used. The complexity of the quantum active learning algorithm is polynomial in the variables used, like the dimension of the space $m$ and the size of the initial training data $n$. On the other hand, if one replicates this approach with a classical computer, we expect that it would take exponential time in $m$, an example of the so-called `curse of dimensionality’. | |
| Tasks | Active Learning |
| Published | 2019-12-06 |
| URL | https://arxiv.org/abs/1912.03283v1 |
| https://arxiv.org/pdf/1912.03283v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-quantum-active-learning-algorithm-for |
| Repo | |
| Framework | |
A unified framework of epidemic spreading prediction by empirical mode decomposition based ensemble learning techniques
| Title | A unified framework of epidemic spreading prediction by empirical mode decomposition based ensemble learning techniques |
| Authors | Yun Feng, Bing-Chuan Wang |
| Abstract | In this paper, a unified susceptible-exposed-infected-susceptible-aware (SEIS-A) framework is proposed to combine epidemic spreading with individuals’ on-line self-consultation behaviors. An epidemic spreading prediction model is established based on the SEIS-A framework. The prediction process contains two phases. In phase I, the time series data of disease density are decomposed through the empirical mode decomposition (EMD) method to obtain the intrinsic mode functions (IMFs). In phase II, the ensemble learning techniques which use the on-line query data as an additional input are applied to these IMFs. Finally, experiments for prediction of weekly consultation rates of Hand-foot-and-mouth disease (HFMD) in Hong Kong are conducted to validate the effectiveness of the proposed method. The main advantage of this method is that it outperforms other methods on fluctuating complex data. |
| Tasks | Time Series |
| Published | 2019-01-03 |
| URL | http://arxiv.org/abs/1901.01144v2 |
| http://arxiv.org/pdf/1901.01144v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-unified-framework-of-epidemic-spreading |
| Repo | |
| Framework | |
Compact Autoregressive Network
| Title | Compact Autoregressive Network |
| Authors | Di Wang, Feiqing Huang, Jingyu Zhao, Guodong Li, Guangjian Tian |
| Abstract | Autoregressive networks can achieve promising performance in many sequence modeling tasks with short-range dependence. However, when handling high-dimensional inputs and outputs, the huge amount of parameters in the network lead to expensive computational cost and low learning efficiency. The problem can be alleviated slightly by introducing one more narrow hidden layer to the network, but the sample size required to achieve a certain training error is still large. To address this challenge, we rearrange the weight matrices of a linear autoregressive network into a tensor form, and then make use of Tucker decomposition to represent low-rank structures. This leads to a novel compact autoregressive network, called Tucker AutoRegressive (TAR) net. Interestingly, the TAR net can be applied to sequences with long-range dependence since the dimension along the sequential order is reduced. Theoretical studies show that the TAR net improves the learning efficiency, and requires much fewer samples for model training. Experiments on synthetic and real-world datasets demonstrate the promising performance of the proposed compact network. |
| Tasks | |
| Published | 2019-09-06 |
| URL | https://arxiv.org/abs/1909.03830v1 |
| https://arxiv.org/pdf/1909.03830v1.pdf | |
| PWC | https://paperswithcode.com/paper/compact-autoregressive-network |
| Repo | |
| Framework | |
