May 7, 2019

2946 words 14 mins read

Paper Group AWR 51

ROCS-Derived Features for Virtual Screening. Learning to Pivot with Adversarial Networks. Reinforcement Learning with Unsupervised Auxiliary Tasks. On the Potential of Simple Framewise Approaches to Piano Transcription. An Incremental Parser for Abstract Meaning Representation. Multi-way Monte Carlo Method for Linear Systems. TensorFlow: A system f …

ROCS-Derived Features for Virtual Screening


Title	ROCS-Derived Features for Virtual Screening
Authors	Steven Kearnes, Vijay Pande
Abstract	Rapid overlay of chemical structures (ROCS) is a standard tool for the calculation of 3D shape and chemical (“color”) similarity. ROCS uses unweighted sums to combine many aspects of similarity, yielding parameter-free models for virtual screening. In this report, we decompose the ROCS color force field into “color components” and “color atom overlaps”, novel color similarity features that can be weighted in a system-specific manner by machine learning algorithms. In cross-validation experiments, these additional features significantly improve virtual screening performance (ROC AUC scores) relative to standard ROCS.
Tasks
Published	2016-06-06
URL	http://arxiv.org/abs/1606.01822v3
PDF	http://arxiv.org/pdf/1606.01822v3.pdf
PWC	https://paperswithcode.com/paper/rocs-derived-features-for-virtual-screening
Repo	https://github.com/skearnes/color-features
Framework	none

Learning to Pivot with Adversarial Networks


Title	Learning to Pivot with Adversarial Networks
Authors	Gilles Louppe, Michael Kagan, Kyle Cranmer
Abstract	Several techniques for domain adaptation have been proposed to account for differences in the distribution of the data used for training and testing. The majority of this work focuses on a binary domain label. Similar problems occur in a scientific context where there may be a continuous family of plausible data generation processes associated to the presence of systematic uncertainties. Robust inference is possible if it is based on a pivot – a quantity whose distribution does not depend on the unknown values of the nuisance parameters that parametrize this family of data generation processes. In this work, we introduce and derive theoretical results for a training procedure based on adversarial networks for enforcing the pivotal property (or, equivalently, fairness with respect to continuous attributes) on a predictive model. The method includes a hyperparameter to control the trade-off between accuracy and robustness. We demonstrate the effectiveness of this approach with a toy example and examples from particle physics.
Tasks	Domain Adaptation
Published	2016-11-03
URL	http://arxiv.org/abs/1611.01046v3
PDF	http://arxiv.org/pdf/1611.01046v3.pdf
PWC	https://paperswithcode.com/paper/learning-to-pivot-with-adversarial-networks
Repo	https://github.com/Nellaker-group/FairUnsupervisedRepresentations
Framework	pytorch

Reinforcement Learning with Unsupervised Auxiliary Tasks


Title	Reinforcement Learning with Unsupervised Auxiliary Tasks
Authors	Max Jaderberg, Volodymyr Mnih, Wojciech Marian Czarnecki, Tom Schaul, Joel Z Leibo, David Silver, Koray Kavukcuoglu
Abstract	Deep reinforcement learning agents have achieved state-of-the-art results by directly maximising cumulative reward. However, environments contain a much wider variety of possible training signals. In this paper, we introduce an agent that also maximises many other pseudo-reward functions simultaneously by reinforcement learning. All of these tasks share a common representation that, like unsupervised learning, continues to develop in the absence of extrinsic rewards. We also introduce a novel mechanism for focusing this representation upon extrinsic rewards, so that learning can rapidly adapt to the most relevant aspects of the actual task. Our agent significantly outperforms the previous state-of-the-art on Atari, averaging 880% expert human performance, and a challenging suite of first-person, three-dimensional \emph{Labyrinth} tasks leading to a mean speedup in learning of 10$\times$ and averaging 87% expert human performance on Labyrinth.
Tasks
Published	2016-11-16
URL	http://arxiv.org/abs/1611.05397v1
PDF	http://arxiv.org/pdf/1611.05397v1.pdf
PWC	https://paperswithcode.com/paper/reinforcement-learning-with-unsupervised
Repo	https://github.com/hjgithub1/reinforcement-learning-notes
Framework	none

On the Potential of Simple Framewise Approaches to Piano Transcription


Title	On the Potential of Simple Framewise Approaches to Piano Transcription
Authors	Rainer Kelz, Matthias Dorfer, Filip Korzeniowski, Sebastian Böck, Andreas Arzt, Gerhard Widmer
Abstract	In an attempt at exploring the limitations of simple approaches to the task of piano transcription (as usually defined in MIR), we conduct an in-depth analysis of neural network-based framewise transcription. We systematically compare different popular input representations for transcription systems to determine the ones most suitable for use with neural networks. Exploiting recent advances in training techniques and new regularizers, and taking into account hyper-parameter tuning, we show that it is possible, by simple bottom-up frame-wise processing, to obtain a piano transcriber that outperforms the current published state of the art on the publicly available MAPS dataset – without any complex post-processing steps. Thus, we propose this simple approach as a new baseline for this dataset, for future transcription research to build on and improve.
Tasks
Published	2016-12-15
URL	http://arxiv.org/abs/1612.05153v1
PDF	http://arxiv.org/pdf/1612.05153v1.pdf
PWC	https://paperswithcode.com/paper/on-the-potential-of-simple-framewise
Repo	https://github.com/rainerkelz/framewise_2016
Framework	pytorch

An Incremental Parser for Abstract Meaning Representation


Title	An Incremental Parser for Abstract Meaning Representation
Authors	Marco Damonte, Shay B. Cohen, Giorgio Satta
Abstract	Meaning Representation (AMR) is a semantic representation for natural language that embeds annotations related to traditional tasks such as named entity recognition, semantic role labeling, word sense disambiguation and co-reference resolution. We describe a transition-based parser for AMR that parses sentences left-to-right, in linear time. We further propose a test-suite that assesses specific subtasks that are helpful in comparing AMR parsers, and show that our parser is competitive with the state of the art on the LDC2015E86 dataset and that it outperforms state-of-the-art parsers for recovering named entities and handling polarity.
Tasks	Named Entity Recognition, Semantic Role Labeling, Word Sense Disambiguation
Published	2016-08-22
URL	http://arxiv.org/abs/1608.06111v5
PDF	http://arxiv.org/pdf/1608.06111v5.pdf
PWC	https://paperswithcode.com/paper/an-incremental-parser-for-abstract-meaning
Repo	https://github.com/mdtux89/amr-eager-multilingual
Framework	torch

Multi-way Monte Carlo Method for Linear Systems


Title	Multi-way Monte Carlo Method for Linear Systems
Authors	Tao Wu, David F. Gleich
Abstract	We study the Monte Carlo method for solving a linear system of the form $x = H x + b$. A sufficient condition for the method to work is $\ H \ < 1$, which greatly limits the usability of this method. We improve this condition by proposing a new multi-way Markov random walk, which is a generalization of the standard Markov random walk. Under our new framework we prove that the necessary and sufficient condition for our method to work is the spectral radius $\rho(H^{+}) < 1$, which is a weaker requirement than $\ H \ < 1$. In addition to solving more problems, our new method can work faster than the standard algorithm. In numerical experiments on both synthetic and real world matrices, we demonstrate the effectiveness of our new method.
Tasks
Published	2016-08-15
URL	http://arxiv.org/abs/1608.04361v1
PDF	http://arxiv.org/pdf/1608.04361v1.pdf
PWC	https://paperswithcode.com/paper/multi-way-monte-carlo-method-for-linear
Repo	https://github.com/wutao27/multi-way-MC
Framework	none

TensorFlow: A system for large-scale machine learning


Title	TensorFlow: A system for large-scale machine learning
Authors	Martín Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, Manjunath Kudlur, Josh Levenberg, Rajat Monga, Sherry Moore, Derek G. Murray, Benoit Steiner, Paul Tucker, Vijay Vasudevan, Pete Warden, Martin Wicke, Yuan Yu, Xiaoqiang Zheng
Abstract	TensorFlow is a machine learning system that operates at large scale and in heterogeneous environments. TensorFlow uses dataflow graphs to represent computation, shared state, and the operations that mutate that state. It maps the nodes of a dataflow graph across many machines in a cluster, and within a machine across multiple computational devices, including multicore CPUs, general-purpose GPUs, and custom designed ASICs known as Tensor Processing Units (TPUs). This architecture gives flexibility to the application developer: whereas in previous “parameter server” designs the management of shared state is built into the system, TensorFlow enables developers to experiment with novel optimizations and training algorithms. TensorFlow supports a variety of applications, with particularly strong support for training and inference on deep neural networks. Several Google services use TensorFlow in production, we have released it as an open-source project, and it has become widely used for machine learning research. In this paper, we describe the TensorFlow dataflow model in contrast to existing systems, and demonstrate the compelling performance that TensorFlow achieves for several real-world applications.
Tasks
Published	2016-05-27
URL	http://arxiv.org/abs/1605.08695v2
PDF	http://arxiv.org/pdf/1605.08695v2.pdf
PWC	https://paperswithcode.com/paper/tensorflow-a-system-for-large-scale-machine
Repo	https://github.com/Allen-Czyysx/Paper-Reading
Framework	tf

Clustering Millions of Faces by Identity


Title	Clustering Millions of Faces by Identity
Authors	Charles Otto, Dayong Wang, Anil K. Jain
Abstract	In this work, we attempt to address the following problem: Given a large number of unlabeled face images, cluster them into the individual identities present in this data. We consider this a relevant problem in different application scenarios ranging from social media to law enforcement. In large-scale scenarios the number of faces in the collection can be of the order of hundreds of million, while the number of clusters can range from a few thousand to millions–leading to difficulties in terms of both run-time complexity and evaluating clustering and per-cluster quality. An efficient and effective Rank-Order clustering algorithm is developed to achieve the desired scalability, and better clustering accuracy than other well-known algorithms such as k-means and spectral clustering. We cluster up to 123 million face images into over 10 million clusters, and analyze the results in terms of both external cluster quality measures (known face labels) and internal cluster quality measures (unknown face labels) and run-time. Our algorithm achieves an F-measure of 0.87 on a benchmark unconstrained face dataset (LFW, consisting of 13K faces), and 0.27 on the largest dataset considered (13K images in LFW, plus 123M distractor images). Additionally, we present preliminary work on video frame clustering (achieving 0.71 F-measure when clustering all frames in the benchmark YouTube Faces dataset). A per-cluster quality measure is developed which can be used to rank individual clusters and to automatically identify a subset of good quality clusters for manual exploration.
Tasks
Published	2016-04-04
URL	http://arxiv.org/abs/1604.00989v1
PDF	http://arxiv.org/pdf/1604.00989v1.pdf
PWC	https://paperswithcode.com/paper/clustering-millions-of-faces-by-identity
Repo	https://github.com/varun-suresh/Clustering
Framework	none

Depth-Based Object Tracking Using a Robust Gaussian Filter


Title	Depth-Based Object Tracking Using a Robust Gaussian Filter
Authors	Jan Issac, Manuel Wüthrich, Cristina Garcia Cifuentes, Jeannette Bohg, Sebastian Trimpe, Stefan Schaal
Abstract	We consider the problem of model-based 3D-tracking of objects given dense depth images as input. Two difficulties preclude the application of a standard Gaussian filter to this problem. First of all, depth sensors are characterized by fat-tailed measurement noise. To address this issue, we show how a recently published robustification method for Gaussian filters can be applied to the problem at hand. Thereby, we avoid using heuristic outlier detection methods that simply reject measurements if they do not match the model. Secondly, the computational cost of the standard Gaussian filter is prohibitive due to the high-dimensional measurement, i.e. the depth image. To address this problem, we propose an approximation to reduce the computational complexity of the filter. In quantitative experiments on real data we show how our method clearly outperforms the standard Gaussian filter. Furthermore, we compare its performance to a particle-filter-based tracking method, and observe comparable computational efficiency and improved accuracy and smoothness of the estimates.
Tasks	Object Tracking, Outlier Detection
Published	2016-02-19
URL	http://arxiv.org/abs/1602.06157v1
PDF	http://arxiv.org/pdf/1602.06157v1.pdf
PWC	https://paperswithcode.com/paper/depth-based-object-tracking-using-a-robust
Repo	https://github.com/bayesian-object-tracking/dbot
Framework	none

NED: An Inter-Graph Node Metric Based On Edit Distance


Title	NED: An Inter-Graph Node Metric Based On Edit Distance
Authors	Haohan Zhu, Xianrui Meng, George Kollios
Abstract	Node similarity is a fundamental problem in graph analytics. However, node similarity between nodes in different graphs (inter-graph nodes) has not received a lot of attention yet. The inter-graph node similarity is important in learning a new graph based on the knowledge of an existing graph (transfer learning on graphs) and has applications in biological, communication, and social networks. In this paper, we propose a novel distance function for measuring inter-graph node similarity with edit distance, called NED. In NED, two nodes are compared according to their local neighborhood structures which are represented as unordered k-adjacent trees, without relying on labels or other assumptions. Since the computation problem of tree edit distance on unordered trees is NP-Complete, we propose a modified tree edit distance, called TED, for comparing neighborhood trees. TED is a metric distance, as the original tree edit distance, but more importantly, TED* is polynomially computable. As a metric distance, NED admits efficient indexing, provides interpretable results, and shows to perform better than existing approaches on a number of data analysis tasks, including graph de-anonymization. Finally, the efficiency and effectiveness of NED are empirically demonstrated using real-world graphs.
Tasks	Transfer Learning
Published	2016-02-07
URL	http://arxiv.org/abs/1602.02358v3
PDF	http://arxiv.org/pdf/1602.02358v3.pdf
PWC	https://paperswithcode.com/paper/ned-an-inter-graph-node-metric-based-on-edit
Repo	https://github.com/zhuhaohan/NED
Framework	none

Variational Intrinsic Control


Title	Variational Intrinsic Control
Authors	Karol Gregor, Danilo Jimenez Rezende, Daan Wierstra
Abstract	In this paper we introduce a new unsupervised reinforcement learning method for discovering the set of intrinsic options available to an agent. This set is learned by maximizing the number of different states an agent can reliably reach, as measured by the mutual information between the set of options and option termination states. To this end, we instantiate two policy gradient based algorithms, one that creates an explicit embedding space of options and one that represents options implicitly. The algorithms also provide an explicit measure of empowerment in a given state that can be used by an empowerment maximizing agent. The algorithm scales well with function approximation and we demonstrate the applicability of the algorithm on a range of tasks.
Tasks
Published	2016-11-22
URL	http://arxiv.org/abs/1611.07507v1
PDF	http://arxiv.org/pdf/1611.07507v1.pdf
PWC	https://paperswithcode.com/paper/variational-intrinsic-control
Repo	https://github.com/jbinas/gym-mnist
Framework	pytorch

Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment


Title	Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment
Authors	Muhammad Bilal Zafar, Isabel Valera, Manuel Gomez Rodriguez, Krishna P. Gummadi
Abstract	Automated data-driven decision making systems are increasingly being used to assist, or even replace humans in many settings. These systems function by learning from historical decisions, often taken by humans. In order to maximize the utility of these systems (or, classifiers), their training involves minimizing the errors (or, misclassifications) over the given historical data. However, it is quite possible that the optimally trained classifier makes decisions for people belonging to different social groups with different misclassification rates (e.g., misclassification rates for females are higher than for males), thereby placing these groups at an unfair disadvantage. To account for and avoid such unfairness, in this paper, we introduce a new notion of unfairness, disparate mistreatment, which is defined in terms of misclassification rates. We then propose intuitive measures of disparate mistreatment for decision boundary-based classifiers, which can be easily incorporated into their formulation as convex-concave constraints. Experiments on synthetic as well as real world datasets show that our methodology is effective at avoiding disparate mistreatment, often at a small cost in terms of accuracy.
Tasks	Decision Making
Published	2016-10-26
URL	http://arxiv.org/abs/1610.08452v2
PDF	http://arxiv.org/pdf/1610.08452v2.pdf
PWC	https://paperswithcode.com/paper/fairness-beyond-disparate-treatment-disparate
Repo	https://github.com/mbilalzafar/fair-classification
Framework	none

RenderGAN: Generating Realistic Labeled Data


Title	RenderGAN: Generating Realistic Labeled Data
Authors	Leon Sixt, Benjamin Wild, Tim Landgraf
Abstract	Deep Convolutional Neuronal Networks (DCNNs) are showing remarkable performance on many computer vision tasks. Due to their large parameter space, they require many labeled samples when trained in a supervised setting. The costs of annotating data manually can render the use of DCNNs infeasible. We present a novel framework called RenderGAN that can generate large amounts of realistic, labeled images by combining a 3D model and the Generative Adversarial Network framework. In our approach, image augmentations (e.g. lighting, background, and detail) are learned from unlabeled data such that the generated images are strikingly realistic while preserving the labels known from the 3D model. We apply the RenderGAN framework to generate images of barcode-like markers that are attached to honeybees. Training a DCNN on data generated by the RenderGAN yields considerably better performance than training it on various baselines.
Tasks
Published	2016-11-04
URL	http://arxiv.org/abs/1611.01331v5
PDF	http://arxiv.org/pdf/1611.01331v5.pdf
PWC	https://paperswithcode.com/paper/rendergan-generating-realistic-labeled-data
Repo	https://github.com/berleon/deepdecoder
Framework	none

Recovery of non-linear cause-effect relationships from linearly mixed neuroimaging data


Title	Recovery of non-linear cause-effect relationships from linearly mixed neuroimaging data
Authors	Sebastian Weichwald, Arthur Gretton, Bernhard Schölkopf, Moritz Grosse-Wentrup
Abstract	Causal inference concerns the identification of cause-effect relationships between variables. However, often only linear combinations of variables constitute meaningful causal variables. For example, recovering the signal of a cortical source from electroencephalography requires a well-tuned combination of signals recorded at multiple electrodes. We recently introduced the MERLiN (Mixture Effect Recovery in Linear Networks) algorithm that is able to recover, from an observed linear mixture, a causal variable that is a linear effect of another given variable. Here we relax the assumption of this cause-effect relationship being linear and present an extended algorithm that can pick up non-linear cause-effect relationships. Thus, the main contribution is an algorithm (and ready to use code) that has broader applicability and allows for a richer model class. Furthermore, a comparative analysis indicates that the assumption of linear cause-effect relationships is not restrictive in analysing electroencephalographic data.
Tasks	Causal Inference
Published	2016-05-02
URL	http://arxiv.org/abs/1605.00391v2
PDF	http://arxiv.org/pdf/1605.00391v2.pdf
PWC	https://paperswithcode.com/paper/recovery-of-non-linear-cause-effect
Repo	https://github.com/sweichwald/MERLiN
Framework	none

Neuro-symbolic representation learning on biological knowledge graphs


Title	Neuro-symbolic representation learning on biological knowledge graphs
Authors	Mona Alshahrani, Mohammed Asif Khan, Omar Maddouri, Akira R Kinjo, Núria Queralt-Rosinach, Robert Hoehndorf
Abstract	Motivation: Biological data and knowledge bases increasingly rely on Semantic Web technologies and the use of knowledge graphs for data integration, retrieval and federated queries. In the past years, feature learning methods that are applicable to graph-structured data are becoming available, but have not yet widely been applied and evaluated on structured biological knowledge. Results: We develop a novel method for feature learning on biological knowledge graphs. Our method combines symbolic methods, in particular knowledge representation using symbolic logic and automated reasoning, with neural networks to generate embeddings of nodes that encode for related information within knowledge graphs. Through the use of symbolic logic, these embeddings contain both explicit and implicit information. We apply these embeddings to the prediction of edges in the knowledge graph representing problems of function prediction, finding candidate genes of diseases, protein-protein interactions, or drug target relations, and demonstrate performance that matches and sometimes outperforms traditional approaches based on manually crafted features. Our method can be applied to any biological knowledge graph, and will thereby open up the increasing amount of Semantic Web based knowledge bases in biology to use in machine learning and data analytics. Availability and Implementation: https://github.com/bio-ontology-research-group/walking-rdf-and-owl Contact: robert.hoehndorf@kaust.edu.sa
Tasks	Knowledge Graphs, Representation Learning
Published	2016-12-13
URL	http://arxiv.org/abs/1612.04256v1
PDF	http://arxiv.org/pdf/1612.04256v1.pdf
PWC	https://paperswithcode.com/paper/neuro-symbolic-representation-learning-on
Repo	https://github.com/bio-ontology-research-group/walking-rdf-and-owl
Framework	none