Paper Group AWR 82
RLgraph: Modular Computation Graphs for Deep Reinforcement Learning. Deep Learning for Classical Japanese Literature. Fast Online Object Tracking and Segmentation: A Unifying Approach. Reinforcement Learning for Automatic Test Case Prioritization and Selection in Continuous Integration. NetGAN: Generating Graphs via Random Walks. Pre-training with …
RLgraph: Modular Computation Graphs for Deep Reinforcement Learning
| Title | RLgraph: Modular Computation Graphs for Deep Reinforcement Learning |
| Authors | Michael Schaarschmidt, Sven Mika, Kai Fricke, Eiko Yoneki |
| Abstract | Reinforcement learning (RL) tasks are challenging to implement, execute and test due to algorithmic instability, hyper-parameter sensitivity, and heterogeneous distributed communication patterns. We argue for the separation of logical component composition, backend graph definition, and distributed execution. To this end, we introduce RLgraph, a library for designing and executing reinforcement learning tasks in both static graph and define-by-run paradigms. The resulting implementations are robust, incrementally testable, and yield high performance across different deep learning frameworks and distributed backends. |
| Tasks | |
| Published | 2018-10-21 |
| URL | http://arxiv.org/abs/1810.09028v2 |
| http://arxiv.org/pdf/1810.09028v2.pdf | |
| PWC | https://paperswithcode.com/paper/rlgraph-modular-computation-graphs-for-deep |
| Repo | https://github.com/rlgraph/rlgraph |
| Framework | tf |
Deep Learning for Classical Japanese Literature
| Title | Deep Learning for Classical Japanese Literature |
| Authors | Tarin Clanuwat, Mikel Bober-Irizar, Asanobu Kitamoto, Alex Lamb, Kazuaki Yamamoto, David Ha |
| Abstract | Much of machine learning research focuses on producing models which perform well on benchmark tasks, in turn improving our understanding of the challenges associated with those tasks. From the perspective of ML researchers, the content of the task itself is largely irrelevant, and thus there have increasingly been calls for benchmark tasks to more heavily focus on problems which are of social or cultural relevance. In this work, we introduce Kuzushiji-MNIST, a dataset which focuses on Kuzushiji (cursive Japanese), as well as two larger, more challenging datasets, Kuzushiji-49 and Kuzushiji-Kanji. Through these datasets, we wish to engage the machine learning community into the world of classical Japanese literature. Dataset available at https://github.com/rois-codh/kmnist |
| Tasks | |
| Published | 2018-12-03 |
| URL | http://arxiv.org/abs/1812.01718v1 |
| http://arxiv.org/pdf/1812.01718v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-for-classical-japanese |
| Repo | https://github.com/rois-codh/kmnist |
| Framework | none |
Fast Online Object Tracking and Segmentation: A Unifying Approach
| Title | Fast Online Object Tracking and Segmentation: A Unifying Approach |
| Authors | Qiang Wang, Li Zhang, Luca Bertinetto, Weiming Hu, Philip H. S. Torr |
| Abstract | In this paper we illustrate how to perform both visual object tracking and semi-supervised video object segmentation, in real-time, with a single simple approach. Our method, dubbed SiamMask, improves the offline training procedure of popular fully-convolutional Siamese approaches for object tracking by augmenting their loss with a binary segmentation task. Once trained, SiamMask solely relies on a single bounding box initialisation and operates online, producing class-agnostic object segmentation masks and rotated bounding boxes at 55 frames per second. Despite its simplicity, versatility and fast speed, our strategy allows us to establish a new state of the art among real-time trackers on VOT-2018, while at the same time demonstrating competitive performance and the best speed for the semi-supervised video object segmentation task on DAVIS-2016 and DAVIS-2017. The project website is http://www.robots.ox.ac.uk/~qwang/SiamMask. |
| Tasks | Object Tracking, Real-Time Visual Tracking, Semi-Supervised Semantic Segmentation, Semi-supervised Video Object Segmentation, Video Object Segmentation, Visual Object Tracking, Visual Tracking |
| Published | 2018-12-12 |
| URL | https://arxiv.org/abs/1812.05050v2 |
| https://arxiv.org/pdf/1812.05050v2.pdf | |
| PWC | https://paperswithcode.com/paper/fast-online-object-tracking-and-segmentation |
| Repo | https://github.com/foolwood/SiamMask |
| Framework | pytorch |
Reinforcement Learning for Automatic Test Case Prioritization and Selection in Continuous Integration
| Title | Reinforcement Learning for Automatic Test Case Prioritization and Selection in Continuous Integration |
| Authors | Helge Spieker, Arnaud Gotlieb, Dusica Marijan, Morten Mossige |
| Abstract | Testing in Continuous Integration (CI) involves test case prioritization, selection, and execution at each cycle. Selecting the most promising test cases to detect bugs is hard if there are uncertainties on the impact of committed code changes or, if traceability links between code and tests are not available. This paper introduces Retecs, a new method for automatically learning test case selection and prioritization in CI with the goal to minimize the round-trip time between code commits and developer feedback on failed test cases. The Retecs method uses reinforcement learning to select and prioritize test cases according to their duration, previous last execution and failure history. In a constantly changing environment, where new test cases are created and obsolete test cases are deleted, the Retecs method learns to prioritize error-prone test cases higher under guidance of a reward function and by observing previous CI cycles. By applying Retecs on data extracted from three industrial case studies, we show for the first time that reinforcement learning enables fruitful automatic adaptive test case selection and prioritization in CI and regression testing. |
| Tasks | |
| Published | 2018-11-09 |
| URL | http://arxiv.org/abs/1811.04122v1 |
| http://arxiv.org/pdf/1811.04122v1.pdf | |
| PWC | https://paperswithcode.com/paper/reinforcement-learning-for-automatic-test |
| Repo | https://github.com/codeslord/RLforATCP |
| Framework | none |
NetGAN: Generating Graphs via Random Walks
| Title | NetGAN: Generating Graphs via Random Walks |
| Authors | Aleksandar Bojchevski, Oleksandr Shchur, Daniel Zügner, Stephan Günnemann |
| Abstract | We propose NetGAN - the first implicit generative model for graphs able to mimic real-world networks. We pose the problem of graph generation as learning the distribution of biased random walks over the input graph. The proposed model is based on a stochastic neural network that generates discrete output samples and is trained using the Wasserstein GAN objective. NetGAN is able to produce graphs that exhibit well-known network patterns without explicitly specifying them in the model definition. At the same time, our model exhibits strong generalization properties, as highlighted by its competitive link prediction performance, despite not being trained specifically for this task. Being the first approach to combine both of these desirable properties, NetGAN opens exciting avenues for further research. |
| Tasks | Graph Generation, Link Prediction |
| Published | 2018-03-02 |
| URL | http://arxiv.org/abs/1803.00816v2 |
| http://arxiv.org/pdf/1803.00816v2.pdf | |
| PWC | https://paperswithcode.com/paper/netgan-generating-graphs-via-random-walks |
| Repo | https://github.com/PinliangLi/netgan |
| Framework | tf |
Pre-training with Non-expert Human Demonstration for Deep Reinforcement Learning
| Title | Pre-training with Non-expert Human Demonstration for Deep Reinforcement Learning |
| Authors | Gabriel V. de la Cruz, Yunshu Du, Matthew E. Taylor |
| Abstract | Deep reinforcement learning (deep RL) has achieved superior performance in complex sequential tasks by using deep neural networks as function approximators to learn directly from raw input images. However, learning directly from raw images is data inefficient. The agent must learn feature representation of complex states in addition to learning a policy. As a result, deep RL typically suffers from slow learning speeds and often requires a prohibitively large amount of training time and data to reach reasonable performance, making it inapplicable to real-world settings where data is expensive. In this work, we improve data efficiency in deep RL by addressing one of the two learning goals, feature learning. We leverage supervised learning to pre-train on a small set of non-expert human demonstrations and empirically evaluate our approach using the asynchronous advantage actor-critic algorithms (A3C) in the Atari domain. Our results show significant improvements in learning speed, even when the provided demonstration is noisy and of low quality. |
| Tasks | |
| Published | 2018-12-21 |
| URL | http://arxiv.org/abs/1812.08904v1 |
| http://arxiv.org/pdf/1812.08904v1.pdf | |
| PWC | https://paperswithcode.com/paper/pre-training-with-non-expert-human |
| Repo | https://github.com/gabrieledcjr/DeepRL |
| Framework | tf |
The Full Spectrum of Deepnet Hessians at Scale: Dynamics with SGD Training and Sample Size
| Title | The Full Spectrum of Deepnet Hessians at Scale: Dynamics with SGD Training and Sample Size |
| Authors | Vardan Papyan |
| Abstract | We apply state-of-the-art tools in modern high-dimensional numerical linear algebra to approximate efficiently the spectrum of the Hessian of modern deepnets, with tens of millions of parameters, trained on real data. Our results corroborate previous findings, based on small-scale networks, that the Hessian exhibits “spiked” behavior, with several outliers isolated from a continuous bulk. We decompose the Hessian into different components and study the dynamics with training and sample size of each term individually. |
| Tasks | |
| Published | 2018-11-16 |
| URL | https://arxiv.org/abs/1811.07062v2 |
| https://arxiv.org/pdf/1811.07062v2.pdf | |
| PWC | https://paperswithcode.com/paper/the-full-spectrum-of-deep-net-hessians-at |
| Repo | https://github.com/AnonymousNIPS2019/DeepnetHessian |
| Framework | pytorch |
Adversarial Examples as an Input-Fault Tolerance Problem
| Title | Adversarial Examples as an Input-Fault Tolerance Problem |
| Authors | Angus Galloway, Anna Golubeva, Graham W. Taylor |
| Abstract | We analyze the adversarial examples problem in terms of a model’s fault tolerance with respect to its input. Whereas previous work focuses on arbitrarily strict threat models, i.e., $\epsilon$-perturbations, we consider arbitrary valid inputs and propose an information-based characteristic for evaluating tolerance to diverse input faults. |
| Tasks | |
| Published | 2018-11-30 |
| URL | http://arxiv.org/abs/1811.12601v1 |
| http://arxiv.org/pdf/1811.12601v1.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-examples-as-an-input-fault |
| Repo | https://github.com/uoguelph-mlrg/nips18-secml-advex-input-fault |
| Framework | pytorch |
Zeno: Distributed Stochastic Gradient Descent with Suspicion-based Fault-tolerance
| Title | Zeno: Distributed Stochastic Gradient Descent with Suspicion-based Fault-tolerance |
| Authors | Cong Xie, Oluwasanmi Koyejo, Indranil Gupta |
| Abstract | We present Zeno, a technique to make distributed machine learning, particularly Stochastic Gradient Descent (SGD), tolerant to an arbitrary number of faulty workers. Zeno generalizes previous results that assumed a majority of non-faulty nodes; we need assume only one non-faulty worker. Our key idea is to suspect workers that are potentially defective. Since this is likely to lead to false positives, we use a ranking-based preference mechanism. We prove the convergence of SGD for non-convex problems under these scenarios. Experimental results show that Zeno outperforms existing approaches. |
| Tasks | |
| Published | 2018-05-25 |
| URL | https://arxiv.org/abs/1805.10032v3 |
| https://arxiv.org/pdf/1805.10032v3.pdf | |
| PWC | https://paperswithcode.com/paper/zeno-byzantine-suspicious-stochastic-gradient |
| Repo | https://github.com/xcgoner/icml2019_zeno |
| Framework | mxnet |
Nostalgic Adam: Weighting more of the past gradients when designing the adaptive learning rate
| Title | Nostalgic Adam: Weighting more of the past gradients when designing the adaptive learning rate |
| Authors | Haiwen Huang, Chang Wang, Bin Dong |
| Abstract | First-order optimization algorithms have been proven prominent in deep learning. In particular, algorithms such as RMSProp and Adam are extremely popular. However, recent works have pointed out the lack of ``long-term memory” in Adam-like algorithms, which could hamper their performance and lead to divergence. In our study, we observe that there are benefits of weighting more of the past gradients when designing the adaptive learning rate. We therefore propose an algorithm called the Nostalgic Adam (NosAdam) with theoretically guaranteed convergence at the best known convergence rate. NosAdam can be regarded as a fix to the non-convergence issue of Adam in alternative to the recent work of [Reddi et al., 2018]. Our preliminary numerical experiments show that NosAdam is a promising alternative algorithm to Adam. The proofs, code and other supplementary materials can be found in an anonymously shared link. | |
| Tasks | |
| Published | 2018-05-19 |
| URL | http://arxiv.org/abs/1805.07557v2 |
| http://arxiv.org/pdf/1805.07557v2.pdf | |
| PWC | https://paperswithcode.com/paper/nostalgic-adam-weighting-more-of-the-past |
| Repo | https://github.com/andrehuang/NostalgicAdam |
| Framework | pytorch |
Graph Convolution over Pruned Dependency Trees Improves Relation Extraction
| Title | Graph Convolution over Pruned Dependency Trees Improves Relation Extraction |
| Authors | Yuhao Zhang, Peng Qi, Christopher D. Manning |
| Abstract | Dependency trees help relation extraction models capture long-range relations between words. However, existing dependency-based models either neglect crucial information (e.g., negation) by pruning the dependency trees too aggressively, or are computationally inefficient because it is difficult to parallelize over different tree structures. We propose an extension of graph convolutional networks that is tailored for relation extraction, which pools information over arbitrary dependency structures efficiently in parallel. To incorporate relevant information while maximally removing irrelevant content, we further apply a novel pruning strategy to the input trees by keeping words immediately around the shortest path between the two entities among which a relation might hold. The resulting model achieves state-of-the-art performance on the large-scale TACRED dataset, outperforming existing sequence and dependency-based neural models. We also show through detailed analysis that this model has complementary strengths to sequence models, and combining them further improves the state of the art. |
| Tasks | Relation Extraction |
| Published | 2018-09-26 |
| URL | http://arxiv.org/abs/1809.10185v1 |
| http://arxiv.org/pdf/1809.10185v1.pdf | |
| PWC | https://paperswithcode.com/paper/graph-convolution-over-pruned-dependency |
| Repo | https://github.com/qipeng/gcn-over-pruned-trees |
| Framework | pytorch |
Junction Tree Variational Autoencoder for Molecular Graph Generation
| Title | Junction Tree Variational Autoencoder for Molecular Graph Generation |
| Authors | Wengong Jin, Regina Barzilay, Tommi Jaakkola |
| Abstract | We seek to automate the design of molecules based on specific chemical properties. In computational terms, this task involves continuous embedding and generation of molecular graphs. Our primary contribution is the direct realization of molecular graphs, a task previously approached by generating linear SMILES strings instead of graphs. Our junction tree variational autoencoder generates molecular graphs in two phases, by first generating a tree-structured scaffold over chemical substructures, and then combining them into a molecule with a graph message passing network. This approach allows us to incrementally expand molecules while maintaining chemical validity at every step. We evaluate our model on multiple tasks ranging from molecular generation to optimization. Across these tasks, our model outperforms previous state-of-the-art baselines by a significant margin. |
| Tasks | Drug Discovery, Graph Generation |
| Published | 2018-02-12 |
| URL | http://arxiv.org/abs/1802.04364v4 |
| http://arxiv.org/pdf/1802.04364v4.pdf | |
| PWC | https://paperswithcode.com/paper/junction-tree-variational-autoencoder-for |
| Repo | https://github.com/wengong-jin/icml18-jtnn |
| Framework | pytorch |
Automatic Bayesian Density Analysis
| Title | Automatic Bayesian Density Analysis |
| Authors | Antonio Vergari, Alejandro Molina, Robert Peharz, Zoubin Ghahramani, Kristian Kersting, Isabel Valera |
| Abstract | Making sense of a dataset in an automatic and unsupervised fashion is a challenging problem in statistics and AI. Classical approaches for {exploratory data analysis} are usually not flexible enough to deal with the uncertainty inherent to real-world data: they are often restricted to fixed latent interaction models and homogeneous likelihoods; they are sensitive to missing, corrupt and anomalous data; moreover, their expressiveness generally comes at the price of intractable inference. As a result, supervision from statisticians is usually needed to find the right model for the data. However, since domain experts are not necessarily also experts in statistics, we propose Automatic Bayesian Density Analysis (ABDA) to make exploratory data analysis accessible at large. Specifically, ABDA allows for automatic and efficient missing value estimation, statistical data type and likelihood discovery, anomaly detection and dependency structure mining, on top of providing accurate density estimation. Extensive empirical evidence shows that ABDA is a suitable tool for automatic exploratory analysis of mixed continuous and discrete tabular data. |
| Tasks | Anomaly Detection, Bayesian Inference, Density Estimation |
| Published | 2018-07-24 |
| URL | http://arxiv.org/abs/1807.09306v3 |
| http://arxiv.org/pdf/1807.09306v3.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-bayesian-density-analysis |
| Repo | https://github.com/probabilistic-learning/abda |
| Framework | none |
Efficiently measuring a quantum device using machine learning
| Title | Efficiently measuring a quantum device using machine learning |
| Authors | D. T. Lennon, H. Moon, L. C. Camenzind, Liuqi Yu, D. M. Zumbühl, G. A. D. Briggs, M. A. Osborne, E. A. Laird, N. Ares |
| Abstract | Scalable quantum technologies will present challenges for characterizing and tuning quantum devices. This is a time-consuming activity, and as the size of quantum systems increases, this task will become intractable without the aid of automation. We present measurements on a quantum dot device performed by a machine learning algorithm. The algorithm selects the most informative measurements to perform next using information theory and a probabilistic deep-generative model, the latter capable of generating multiple full-resolution reconstructions from scattered partial measurements. We demonstrate, for two different measurement configurations, that the algorithm outperforms standard grid scan techniques, reducing the number of measurements required by up to 4 times and the measurement time by 3.7 times. Our contribution goes beyond the use of machine learning for data search and analysis, and instead presents the use of algorithms to automate measurement. This work lays the foundation for automated control of large quantum circuits. |
| Tasks | |
| Published | 2018-10-23 |
| URL | http://arxiv.org/abs/1810.10042v1 |
| http://arxiv.org/pdf/1810.10042v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficiently-measuring-a-quantum-device-using |
| Repo | https://github.com/oxquantum-repo/CVAE_for_QE |
| Framework | tf |
QuickNAT: A Fully Convolutional Network for Quick and Accurate Segmentation of Neuroanatomy
| Title | QuickNAT: A Fully Convolutional Network for Quick and Accurate Segmentation of Neuroanatomy |
| Authors | Abhijit Guha Roy, Sailesh Conjeti, Nassir Navab, Christian Wachinger |
| Abstract | Whole brain segmentation from structural magnetic resonance imaging (MRI) is a prerequisite for most morphological analyses, but is computationally intense and can therefore delay the availability of image markers after scan acquisition. We introduce QuickNAT, a fully convolutional, densely connected neural network that segments a \revision{MRI brain scan} in 20 seconds. To enable training of the complex network with millions of learnable parameters using limited annotated data, we propose to first pre-train on auxiliary labels created from existing segmentation software. Subsequently, the pre-trained model is fine-tuned on manual labels to rectify errors in auxiliary labels. With this learning strategy, we are able to use large neuroimaging repositories without manual annotations for training. In an extensive set of evaluations on eight datasets that cover a wide age range, pathology, and different scanners, we demonstrate that QuickNAT achieves superior segmentation accuracy and reliability in comparison to state-of-the-art methods, while being orders of magnitude faster. The speed up facilitates processing of large data repositories and supports translation of imaging biomarkers by making them available within seconds for fast clinical decision making. |
| Tasks | Brain Segmentation, Decision Making |
| Published | 2018-01-12 |
| URL | http://arxiv.org/abs/1801.04161v2 |
| http://arxiv.org/pdf/1801.04161v2.pdf | |
| PWC | https://paperswithcode.com/paper/quicknat-a-fully-convolutional-network-for |
| Repo | https://github.com/ai-med/QuickNATv2 |
| Framework | tf |
