Paper Group ANR 1456
Joint Label Prediction based Semi-Supervised Adaptive Concept Factorization for Robust Data Representation. Provably Efficient Imitation Learning from Observation Alone. Optimal Passenger-Seeking Policies on E-hailing Platforms Using Markov Decision Process and Imitation Learning. General Supervision via Probabilistic Transformations. Efficiently u …
Joint Label Prediction based Semi-Supervised Adaptive Concept Factorization for Robust Data Representation
| Title | Joint Label Prediction based Semi-Supervised Adaptive Concept Factorization for Robust Data Representation |
| Authors | Zhao Zhang, Yan Zhang, Guangcan Liu, Jinhui Tang, Shuicheng Yan, Meng Wang |
| Abstract | Constrained Concept Factorization (CCF) yields the enhanced representation ability over CF by incorporating label information as additional constraints, but it cannot classify and group unlabeled data appropriately. Minimizing the difference between the original data and its reconstruction directly can enable CCF to model a small noisy perturbation, but is not robust to gross sparse errors. Besides, CCF cannot preserve the manifold structures in new representation space explicitly, especially in an adaptive manner. In this paper, we propose a joint label prediction based Robust Semi-Supervised Adaptive Concept Factorization (RS2ACF) framework. To obtain robust representation, RS2ACF relaxes the factorization to make it simultaneously stable to small entrywise noise and robust to sparse errors. To enrich prior knowledge to enhance the discrimination, RS2ACF clearly uses class information of labeled data and more importantly propagates it to unlabeled data by jointly learning an explicit label indicator for unlabeled data. By the label indicator, RS2ACF can ensure the unlabeled data of the same predicted label to be mapped into the same class in feature space. Besides, RS2ACF incorporates the joint neighborhood reconstruction error over the new representations and predicted labels of both labeled and unlabeled data, so the manifold structures can be preserved explicitly and adaptively in the representation space and label space at the same time. Owing to the adaptive manner, the tricky process of determining the neighborhood size or kernel width can be avoided. Extensive results on public databases verify that our RS2ACF can deliver state-of-the-art data representation, compared with other related methods. |
| Tasks | |
| Published | 2019-05-25 |
| URL | https://arxiv.org/abs/1905.10572v1 |
| https://arxiv.org/pdf/1905.10572v1.pdf | |
| PWC | https://paperswithcode.com/paper/joint-label-prediction-based-semi-supervised |
| Repo | |
| Framework | |
Provably Efficient Imitation Learning from Observation Alone
| Title | Provably Efficient Imitation Learning from Observation Alone |
| Authors | Wen Sun, Anirudh Vemula, Byron Boots, J. Andrew Bagnell |
| Abstract | We study Imitation Learning (IL) from Observations alone (ILFO) in large-scale MDPs. While most IL algorithms rely on an expert to directly provide actions to the learner, in this setting the expert only supplies sequences of observations. We design a new model-free algorithm for ILFO, Forward Adversarial Imitation Learning (FAIL), which learns a sequence of time-dependent policies by minimizing an Integral Probability Metric between the observation distributions of the expert policy and the learner. FAIL is the first provably efficient algorithm in ILFO setting, which learns a near-optimal policy with a number of samples that is polynomial in all relevant parameters but independent of the number of unique observations. The resulting theory extends the domain of provably sample efficient learning algorithms beyond existing results, which typically only consider tabular reinforcement learning settings or settings that require access to a near-optimal reset distribution. We also investigate the extension of FAIL in a model-based setting. Finally we demonstrate the efficacy of FAIL on multiple OpenAI Gym control tasks. |
| Tasks | Imitation Learning |
| Published | 2019-05-27 |
| URL | https://arxiv.org/abs/1905.10948v2 |
| https://arxiv.org/pdf/1905.10948v2.pdf | |
| PWC | https://paperswithcode.com/paper/provably-efficient-imitation-learning-from |
| Repo | |
| Framework | |
Optimal Passenger-Seeking Policies on E-hailing Platforms Using Markov Decision Process and Imitation Learning
| Title | Optimal Passenger-Seeking Policies on E-hailing Platforms Using Markov Decision Process and Imitation Learning |
| Authors | Zhenyu Shou, Xuan Di, Jieping Ye, Hongtu Zhu, Hua Zhang, Robert Hampshire |
| Abstract | Vacant taxi drivers’ passenger seeking process in a road network generates additional vehicle miles traveled, adding congestion and pollution into the road network and the environment. This paper aims to employ a Markov Decision Process (MDP) to model idle e-hailing drivers’ optimal sequential decisions in passenger-seeking. Transportation network companies (TNC) or e-hailing (e.g., Didi, Uber) drivers exhibit different behaviors from traditional taxi drivers because e-hailing drivers do not need to actually search for passengers. Instead, they reposition themselves so that the matching platform can match a passenger. Accordingly, we incorporate e-hailing drivers’ new features into our MDP model. The reward function used in the MDP model is uncovered by leveraging an inverse reinforcement learning technique. We then use 44,160 Didi drivers’ 3-day trajectories to train the model. To validate the effectiveness of the model, a Monte Carlo simulation is conducted to simulate the performance of drivers under the guidance of the optimal policy, which is then compared with the performance of drivers following one baseline heuristic, namely, the local hotspot strategy. The results show that our model is able to achieve a 17.5% improvement over the local hotspot strategy in terms of the rate of return. The proposed MDP model captures the supply-demand ratio considering the fact that the number of drivers in this study is sufficiently large and thus the number of unmatched orders is assumed to be negligible. To better incorporate the competition among multiple drivers into the model, we have also devised and calibrated a dynamic adjustment strategy of the order matching probability. |
| Tasks | Imitation Learning |
| Published | 2019-05-23 |
| URL | https://arxiv.org/abs/1905.09906v3 |
| https://arxiv.org/pdf/1905.09906v3.pdf | |
| PWC | https://paperswithcode.com/paper/where-to-find-next-passengers-on-e-hailing |
| Repo | |
| Framework | |
General Supervision via Probabilistic Transformations
| Title | General Supervision via Probabilistic Transformations |
| Authors | Santiago Mazuelas, Aritz Perez |
| Abstract | Different types of training data have led to numerous schemes for supervised classification. Current learning techniques are tailored to one specific scheme and cannot handle general ensembles of training data. This paper presents a unifying framework for supervised classification with general ensembles of training data, and proposes the learning methodology of generalized robust risk minimization (GRRM). The paper shows how current and novel supervision schemes can be addressed under the proposed framework by representing the relationship between examples at test and training via probabilistic transformations. The results show that GRRM can handle different types of training data in a unified manner, and enable new supervision schemes that aggregate general ensembles of training data. |
| Tasks | |
| Published | 2019-01-24 |
| URL | http://arxiv.org/abs/1901.08552v1 |
| http://arxiv.org/pdf/1901.08552v1.pdf | |
| PWC | https://paperswithcode.com/paper/general-supervision-via-probabilistic |
| Repo | |
| Framework | |
Efficiently utilizing complex-valued PolSAR image data via a multi-task deep learning framework
| Title | Efficiently utilizing complex-valued PolSAR image data via a multi-task deep learning framework |
| Authors | Lamei Zhang, Hongwei Dong, Bin Zou |
| Abstract | Convolutional neural networks (CNNs) have been widely used to improve the accuracy of polarimetric synthetic aperture radar (PolSAR) image classification. However, in most studies, the difference between PolSAR images and optical images is rarely considered. Most of the existing CNNs are not tailored for the task of PolSAR image classification, in which complex-valued PolSAR data have been simply equated to real-valued data to fit the optical image processing architectures and avoid complex-valued operations. This is one of the reasons CNNs unable to perform their full capabilities in PolSAR classification. To solve the above problem, the objective of this paper is to develop a tailored CNN framework for PolSAR image classification, which can be implemented from two aspects: Seeking a better form of PolSAR data as the input of CNNs and building matched CNN architectures based on the proposed input form. In this paper, considering the properties of complex-valued numbers, amplitude and phase of complex-valued PolSAR data are extracted as the input for the first time to maintain the integrity of original information while avoiding immature complex-valued operations. Then, a multi-task CNN (MCNN) architecture is proposed to match the improved input form and achieve better classification results. Furthermore, depthwise separable convolution is introduced to the proposed architecture in order to better extract information from the phase information. Experiments on three PolSAR benchmark datasets not only prove that using amplitude and phase as the input do contribute to the improvement of PolSAR classification, but also verify the adaptability between the improved input form and the well-designed architectures. |
| Tasks | Image Classification, Representation Learning |
| Published | 2019-03-24 |
| URL | https://arxiv.org/abs/1903.09917v2 |
| https://arxiv.org/pdf/1903.09917v2.pdf | |
| PWC | https://paperswithcode.com/paper/efficiently-utilizing-complex-valued-polsar |
| Repo | |
| Framework | |
Near-Term Quantum-Classical Associative Adversarial Networks
| Title | Near-Term Quantum-Classical Associative Adversarial Networks |
| Authors | Eric R. Anschuetz, Cristian Zanoci |
| Abstract | We introduce a new hybrid quantum-classical adversarial machine learning architecture called a quantum-classical associative adversarial network (QAAN). This architecture consists of a classical generative adversarial network with a small auxiliary quantum Boltzmann machine that is simultaneously trained on an intermediate layer of the discriminator of the generative network. We numerically study the performance of QAANs compared to their classical counterparts on the MNIST and CIFAR-10 data sets, and show that QAANs attain a higher quality of learning when evaluated using the Inception score and the Fr'{e}chet Inception distance. As the QAAN architecture only relies on sampling simple local observables of a small quantum Boltzmann machine, this model is particularly amenable for implementation on the current and next generations of quantum devices. |
| Tasks | |
| Published | 2019-05-30 |
| URL | https://arxiv.org/abs/1905.13205v1 |
| https://arxiv.org/pdf/1905.13205v1.pdf | |
| PWC | https://paperswithcode.com/paper/near-term-quantum-classical-associative |
| Repo | |
| Framework | |
Graph Neural Processes: Towards Bayesian Graph Neural Networks
| Title | Graph Neural Processes: Towards Bayesian Graph Neural Networks |
| Authors | Andrew Carr, David Wingate |
| Abstract | We introduce Graph Neural Processes (GNP), inspired by the recent work in conditional and latent neural processes. A Graph Neural Process is defined as a Conditional Neural Process that operates on arbitrary graph data. It takes features of sparsely observed context points as input, and outputs a distribution over target points. We demonstrate graph neural processes in edge imputation and discuss benefits and drawbacks of the method for other application areas. One major benefit of GNPs is the ability to quantify uncertainty in deep learning on graph structures. An additional benefit of this method is the ability to extend graph neural networks to inputs of dynamic sized graphs. |
| Tasks | Imputation |
| Published | 2019-02-26 |
| URL | https://arxiv.org/abs/1902.10042v2 |
| https://arxiv.org/pdf/1902.10042v2.pdf | |
| PWC | https://paperswithcode.com/paper/graph-neural-processes-towards-bayesian-graph |
| Repo | |
| Framework | |
Interpretable Deep Neural Networks for Facial Expression and Dimensional Emotion Recognition in-the-wild
| Title | Interpretable Deep Neural Networks for Facial Expression and Dimensional Emotion Recognition in-the-wild |
| Authors | Valentin Richer, Dimitrios Kollias |
| Abstract | In this project, we created a database with two types of annotations used in the emotion recognition domain : Action Units and Valence Arousal to try to achieve better results than with only one model. The originality of the approach is also based on the type of architecture used to perform the prediction of the emotions : a categorical Generative Adversarial Network. This kind of dual network can generate images based on the pictures from the new dataset thanks to its generative network and decide if an image is fake or real thanks to its discriminative network as well as help to predict the annotations for Action Units and Valence Arousal due to its categorical nature. GANs were trained on the Action Units model only, then the Valence Arousal model only and then on both the Action Units model and Valence Arousal model in order to test different parameters and understand their influence. The generative and discriminative aspects of the GANs have performed interesting results. |
| Tasks | Emotion Recognition |
| Published | 2019-10-14 |
| URL | https://arxiv.org/abs/1910.05877v2 |
| https://arxiv.org/pdf/1910.05877v2.pdf | |
| PWC | https://paperswithcode.com/paper/interpretable-deep-neural-networks-for-facial |
| Repo | |
| Framework | |
Interpretable Deep Neural Networks for Dimensional and Categorical Emotion Recognition in-the-wild
| Title | Interpretable Deep Neural Networks for Dimensional and Categorical Emotion Recognition in-the-wild |
| Authors | Xia Yicheng, Dimitrios Kollias |
| Abstract | Emotions play an important role in people’s life. Understanding and recognising is not only important for interpersonal communication, but also has promising applications in Human-Computer Interaction, automobile safety and medical research. This project focuses on extending the emotion recognition database, and training the CNN + RNN emotion recognition neural networks with emotion category representation and valence & arousal representation. The combined models are constructed by training the two representations simultaneously. The comparison and analysis between the three types of model are discussed. The inner-relationship between two emotion representations and the interpretability of the neural networks are investigated. The findings suggest that categorical emotion recognition performance can benefit from training with a combined model. And the mapping of emotion category and valence & arousal values can explain this phenomenon. |
| Tasks | Emotion Recognition |
| Published | 2019-10-13 |
| URL | https://arxiv.org/abs/1910.05784v2 |
| https://arxiv.org/pdf/1910.05784v2.pdf | |
| PWC | https://paperswithcode.com/paper/interpretable-deep-neural-networks-for-1 |
| Repo | |
| Framework | |
Automatic end-to-end De-identification: Is high accuracy the only metric?
| Title | Automatic end-to-end De-identification: Is high accuracy the only metric? |
| Authors | Vithya Yogarajan, Bernhard Pfahringer, Michael Mayo |
| Abstract | De-identification of electronic health records (EHR) is a vital step towards advancing health informatics research and maximising the use of available data. It is a two-step process where step one is the identification of protected health information (PHI), and step two is replacing such PHI with surrogates. Despite the recent advances in automatic de-identification of EHR, significant obstacles remain if the abundant health data available are to be used to the full potential. Accuracy in de-identification could be considered a necessary, but not sufficient condition for the use of EHR without individual patient consent. We present here a comprehensive review of the progress to date, both the impressive successes in achieving high accuracy and the significant risks and challenges that remain. To best of our knowledge, this is the first paper to present a complete picture of end-to-end automatic de-identification. We review 18 recently published automatic de-identification systems -designed to de-identify EHR in the form of free text- to show the advancements made in improving the overall accuracy of the system, and in identifying individual PHI. We argue that despite the improvements in accuracy there remain challenges in surrogate generation and replacements of identified PHIs, and the risks posed to patient protection and privacy. |
| Tasks | |
| Published | 2019-01-27 |
| URL | http://arxiv.org/abs/1901.10583v1 |
| http://arxiv.org/pdf/1901.10583v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-end-to-end-de-identification-is |
| Repo | |
| Framework | |
How we do things with words: Analyzing text as social and cultural data
| Title | How we do things with words: Analyzing text as social and cultural data |
| Authors | Dong Nguyen, Maria Liakata, Simon DeDeo, Jacob Eisenstein, David Mimno, Rebekah Tromble, Jane Winters |
| Abstract | In this article we describe our experiences with computational text analysis. We hope to achieve three primary goals. First, we aim to shed light on thorny issues not always at the forefront of discussions about computational text analysis methods. Second, we hope to provide a set of best practices for working with thick social and cultural concepts. Our guidance is based on our own experiences and is therefore inherently imperfect. Still, given our diversity of disciplinary backgrounds and research practices, we hope to capture a range of ideas and identify commonalities that will resonate for many. And this leads to our final goal: to help promote interdisciplinary collaborations. Interdisciplinary insights and partnerships are essential for realizing the full potential of any computational text analysis that involves social and cultural concepts, and the more we are able to bridge these divides, the more fruitful we believe our work will be. |
| Tasks | |
| Published | 2019-07-02 |
| URL | https://arxiv.org/abs/1907.01468v1 |
| https://arxiv.org/pdf/1907.01468v1.pdf | |
| PWC | https://paperswithcode.com/paper/how-we-do-things-with-words-analyzing-text-as |
| Repo | |
| Framework | |
Cephalometric Landmark Detection by AttentiveFeature Pyramid Fusion and Regression-Voting
| Title | Cephalometric Landmark Detection by AttentiveFeature Pyramid Fusion and Regression-Voting |
| Authors | Runnan Chen, Yuexin Ma, Nenglun Chen, Daniel Lee, Wenping Wang |
| Abstract | Marking anatomical landmarks in cephalometric radiography is a critical operation in cephalometric analysis. Automatically and accurately locating these landmarks is a challenging issue because different landmarks require different levels of resolution and semantics. Based on this observation, we propose a novel attentive feature pyramid fusion module (AFPF) to explicitly shape high-resolution and semantically enhanced fusion features to achieve significantly higher accuracy than existing deep learning-based methods. We also combine heat maps and offset maps to perform pixel-wise regression-voting to improve detection accuracy. By incorporating the AFPF and regression-voting, we develop an end-to-end deep learning framework that improves detection accuracy by 7%~11% for all the evaluation metrics over the state-of-the-art method. We present ablation studies to give more insights into different components of our method and demonstrate its generalization capability and stability for unseen data from diverse devices. |
| Tasks | |
| Published | 2019-08-23 |
| URL | https://arxiv.org/abs/1908.08841v1 |
| https://arxiv.org/pdf/1908.08841v1.pdf | |
| PWC | https://paperswithcode.com/paper/cephalometric-landmark-detection-by |
| Repo | |
| Framework | |
Blind identification of stochastic block models from dynamical observations
| Title | Blind identification of stochastic block models from dynamical observations |
| Authors | Michael T. Schaub, Santiago Segarra, John N. Tsitsiklis |
| Abstract | We consider a blind identification problem in which we aim to recover a statistical model of a network without knowledge of the network’s edges, but based solely on nodal observations of a certain process. More concretely, we focus on observations that consist of single snapshots taken from multiple trajectories of a diffusive process that evolves over the unknown network. We model the network as generated from an independent draw from a latent stochastic block model (SBM), and our goal is to infer both the partition of the nodes into blocks, as well as the parameters of this SBM. We discuss some non-identifiability issues related to this problem and present simple spectral algorithms that provably solve the partition recovery and parameter estimation problems with high accuracy. Our analysis relies on recent results in random matrix theory and covariance estimation, and associated concentration inequalities. We illustrate our results with several numerical experiments. |
| Tasks | |
| Published | 2019-05-22 |
| URL | https://arxiv.org/abs/1905.09107v2 |
| https://arxiv.org/pdf/1905.09107v2.pdf | |
| PWC | https://paperswithcode.com/paper/blind-identification-of-stochastic-block |
| Repo | |
| Framework | |
Unified Optimal Analysis of the (Stochastic) Gradient Method
| Title | Unified Optimal Analysis of the (Stochastic) Gradient Method |
| Authors | Sebastian U. Stich |
| Abstract | In this note we give a simple proof for the convergence of stochastic gradient (SGD) methods on $\mu$-convex functions under a (milder than standard) $L$-smoothness assumption. We show that for carefully chosen stepsizes SGD converges after $T$ iterations as $O\left( LR^2 \exp \bigl[-\frac{\mu}{4L}T\bigr] + \frac{\sigma^2}{\mu T} \right)$ where $\sigma^2$ measures the variance in the stochastic noise. For deterministic gradient descent (GD) and SGD in the interpolation setting we have $\sigma^2 =0$ and we recover the exponential convergence rate. The bound matches with the best known iteration complexity of GD and SGD, up to constants. |
| Tasks | |
| Published | 2019-07-09 |
| URL | https://arxiv.org/abs/1907.04232v2 |
| https://arxiv.org/pdf/1907.04232v2.pdf | |
| PWC | https://paperswithcode.com/paper/unified-optimal-analysis-of-the-stochastic |
| Repo | |
| Framework | |
Conjugate Gradients for Kernel Machines
| Title | Conjugate Gradients for Kernel Machines |
| Authors | Simon Bartels, Philipp Hennig |
| Abstract | Regularized least-squares (kernel-ridge / Gaussian process) regression is a fundamental algorithm of statistics and machine learning. Because generic algorithms for the exact solution have cubic complexity in the number of datapoints, large datasets require to resort to approximations. In this work, the computation of the least-squares prediction is itself treated as a probabilistic inference problem. We propose a structured Gaussian regression model on the kernel function that uses projections of the kernel matrix to obtain a low-rank approximation of the kernel and the matrix. A central result is an enhanced way to use the method of conjugate gradients for the specific setting of least-squares regression as encountered in machine learning. Our method improves the approximation of the kernel ridge regressor / Gaussian process posterior mean over vanilla conjugate gradients and, allows computation of the posterior variance and the log marginal likelihood (evidence) without further overhead. |
| Tasks | |
| Published | 2019-11-14 |
| URL | https://arxiv.org/abs/1911.06048v1 |
| https://arxiv.org/pdf/1911.06048v1.pdf | |
| PWC | https://paperswithcode.com/paper/conjugate-gradients-for-kernel-machines |
| Repo | |
| Framework | |
