October 20, 2019

3429 words 17 mins read

Paper Group AWR 262

Incremental Sparse Bayesian Ordinal Regression. Not to Cry Wolf: Distantly Supervised Multitask Learning in Critical Care. Playing by the Book: An Interactive Game Approach for Action Graph Extraction from Text. Learning Multi-touch Conversion Attribution with Dual-attention Mechanisms for Online Advertising. Semiparametric Contextual Bandits. Mask …

Incremental Sparse Bayesian Ordinal Regression


Title	Incremental Sparse Bayesian Ordinal Regression
Authors	Chang Li, Maarten de Rijke
Abstract	Ordinal Regression (OR) aims to model the ordering information between different data categories, which is a crucial topic in multi-label learning. An important class of approaches to OR models the problem as a linear combination of basis functions that map features to a high dimensional non-linear space. However, most of the basis function-based algorithms are time consuming. We propose an incremental sparse Bayesian approach to OR tasks and introduce an algorithm to sequentially learn the relevant basis functions in the ordinal scenario. Our method, called Incremental Sparse Bayesian Ordinal Regression (ISBOR), automatically optimizes the hyper-parameters via the type-II maximum likelihood method. By exploiting fast marginal likelihood optimization, ISBOR can avoid big matrix inverses, which is the main bottleneck in applying basis function-based algorithms to OR tasks on large-scale datasets. We show that ISBOR can make accurate predictions with parsimonious basis functions while offering automatic estimates of the prediction uncertainty. Extensive experiments on synthetic and real word datasets demonstrate the efficiency and effectiveness of ISBOR compared to other basis function-based OR approaches.
Tasks	Multi-Label Learning
Published	2018-06-18
URL	http://arxiv.org/abs/1806.06553v1
PDF	http://arxiv.org/pdf/1806.06553v1.pdf
PWC	https://paperswithcode.com/paper/incremental-sparse-bayesian-ordinal
Repo	https://github.com/chang-li/SBOR
Framework	none

Not to Cry Wolf: Distantly Supervised Multitask Learning in Critical Care


Title	Not to Cry Wolf: Distantly Supervised Multitask Learning in Critical Care
Authors	Patrick Schwab, Emanuela Keller, Carl Muroi, David J. Mack, Christian Strässle, Walter Karlen
Abstract	Patients in the intensive care unit (ICU) require constant and close supervision. To assist clinical staff in this task, hospitals use monitoring systems that trigger audiovisual alarms if their algorithms indicate that a patient’s condition may be worsening. However, current monitoring systems are extremely sensitive to movement artefacts and technical errors. As a result, they typically trigger hundreds to thousands of false alarms per patient per day - drowning the important alarms in noise and adding to the exhaustion of clinical staff. In this setting, data is abundantly available, but obtaining trustworthy annotations by experts is laborious and expensive. We frame the problem of false alarm reduction from multivariate time series as a machine-learning task and address it with a novel multitask network architecture that utilises distant supervision through multiple related auxiliary tasks in order to reduce the number of expensive labels required for training. We show that our approach leads to significant improvements over several state-of-the-art baselines on real-world ICU data and provide new insights on the importance of task selection and architectural choices in distantly supervised multitask learning.
Tasks	Time Series
Published	2018-02-14
URL	http://arxiv.org/abs/1802.05027v2
PDF	http://arxiv.org/pdf/1802.05027v2.pdf
PWC	https://paperswithcode.com/paper/not-to-cry-wolf-distantly-supervised
Repo	https://github.com/d909b/DSMT-Nets
Framework	none

Playing by the Book: An Interactive Game Approach for Action Graph Extraction from Text


Title	Playing by the Book: An Interactive Game Approach for Action Graph Extraction from Text
Authors	Ronen Tamari, Hiroyuki Shindo, Dafna Shahaf, Yuji Matsumoto
Abstract	Understanding procedural text requires tracking entities, actions and effects as the narrative unfolds. We focus on the challenging real-world problem of action-graph extraction from material science papers, where language is highly specialized and data annotation is expensive and scarce. We propose a novel approach, Text2Quest, where procedural text is interpreted as instructions for an interactive game. A learning agent completes the game by executing the procedure correctly in a text-based simulated lab environment. The framework can complement existing approaches and enables richer forms of learning compared to static texts. We discuss potential limitations and advantages of the approach, and release a prototype proof-of-concept, hoping to encourage research in this direction.
Tasks
Published	2018-11-10
URL	http://arxiv.org/abs/1811.04319v3
PDF	http://arxiv.org/pdf/1811.04319v3.pdf
PWC	https://paperswithcode.com/paper/playing-by-the-book-towards-agent-based
Repo	https://github.com/ronentk/TextLabs
Framework	none

Learning Multi-touch Conversion Attribution with Dual-attention Mechanisms for Online Advertising


Title	Learning Multi-touch Conversion Attribution with Dual-attention Mechanisms for Online Advertising
Authors	Kan Ren, Yuchen Fang, Weinan Zhang, Shuhao Liu, Jiajun Li, Ya Zhang, Yong Yu, Jun Wang
Abstract	In online advertising, the Internet users may be exposed to a sequence of different ad campaigns, i.e., display ads, search, or referrals from multiple channels, before led up to any final sales conversion and transaction. For both campaigners and publishers, it is fundamentally critical to estimate the contribution from ad campaign touch-points during the customer journey (conversion funnel) and assign the right credit to the right ad exposure accordingly. However, the existing research on the multi-touch attribution problem lacks a principled way of utilizing the users’ pre-conversion actions (i.e., clicks), and quite often fails to model the sequential patterns among the touch points from a user’s behavior data. To make it worse, the current industry practice is merely employing a set of arbitrary rules as the attribution model, e.g., the popular last-touch model assigns 100% credit to the final touch-point regardless of actual attributions. In this paper, we propose a Dual-attention Recurrent Neural Network (DARNN) for the multi-touch attribution problem. It learns the attribution values through an attention mechanism directly from the conversion estimation objective. To achieve this, we utilize sequence-to-sequence prediction for user clicks, and combine both post-view and post-click attribution patterns together for the final conversion estimation. To quantitatively benchmark attribution models, we also propose a novel yet practical attribution evaluation scheme through the proxy of budget allocation (under the estimated attributions) over ad channels. The experimental results on two real datasets demonstrate the significant performance gains of our attribution model against the state of the art.
Tasks
Published	2018-08-11
URL	http://arxiv.org/abs/1808.03737v2
PDF	http://arxiv.org/pdf/1808.03737v2.pdf
PWC	https://paperswithcode.com/paper/learning-multi-touch-conversion-attribution
Repo	https://github.com/rk2900/deep-conv-attr
Framework	tf

Semiparametric Contextual Bandits


Title	Semiparametric Contextual Bandits
Authors	Akshay Krishnamurthy, Zhiwei Steven Wu, Vasilis Syrgkanis
Abstract	This paper studies semiparametric contextual bandits, a generalization of the linear stochastic bandit problem where the reward for an action is modeled as a linear function of known action features confounded by an non-linear action-independent term. We design new algorithms that achieve $\tilde{O}(d\sqrt{T})$ regret over $T$ rounds, when the linear function is $d$-dimensional, which matches the best known bounds for the simpler unconfounded case and improves on a recent result of Greenewald et al. (2017). Via an empirical evaluation, we show that our algorithms outperform prior approaches when there are non-linear confounding effects on the rewards. Technically, our algorithms use a new reward estimator inspired by doubly-robust approaches and our proofs require new concentration inequalities for self-normalized martingales.
Tasks	Multi-Armed Bandits
Published	2018-03-12
URL	http://arxiv.org/abs/1803.04204v2
PDF	http://arxiv.org/pdf/1803.04204v2.pdf
PWC	https://paperswithcode.com/paper/semiparametric-contextual-bandits
Repo	https://github.com/akshaykr/oracle_cb
Framework	none

MaskGAN: Better Text Generation via Filling in the______


Title	MaskGAN: Better Text Generation via Filling in the______
Authors	William Fedus, Ian Goodfellow, Andrew M. Dai
Abstract	Neural text generation models are often autoregressive language models or seq2seq models. These models generate text by sampling words sequentially, with each word conditioned on the previous word, and are state-of-the-art for several machine translation and summarization benchmarks. These benchmarks are often defined by validation perplexity even though this is not a direct measure of the quality of the generated text. Additionally, these models are typically trained via maxi- mum likelihood and teacher forcing. These methods are well-suited to optimizing perplexity but can result in poor sample quality since generating text requires conditioning on sequences of words that may have never been observed at training time. We propose to improve sample quality using Generative Adversarial Networks (GANs), which explicitly train the generator to produce high quality samples and have shown a lot of success in image generation. GANs were originally designed to output differentiable values, so discrete language generation is challenging for them. We claim that validation perplexity alone is not indicative of the quality of text generated by a model. We introduce an actor-critic conditional GAN that fills in missing text conditioned on the surrounding context. We show qualitatively and quantitatively, evidence that this produces more realistic conditional and unconditional text samples compared to a maximum likelihood trained model.
Tasks	Multivariate Time Series Imputation, Text Generation
Published	2018-01-23
URL	http://arxiv.org/abs/1801.07736v3
PDF	http://arxiv.org/pdf/1801.07736v3.pdf
PWC	https://paperswithcode.com/paper/maskgan-better-text-generation-via-filling-in
Repo	https://github.com/tensorflow/models/tree/master/research/maskgan
Framework	tf

Video Object Segmentation using Teacher-Student Adaptation in a Human Robot Interaction (HRI) Setting


Title	Video Object Segmentation using Teacher-Student Adaptation in a Human Robot Interaction (HRI) Setting
Authors	Mennatullah Siam, Chen Jiang, Steven Lu, Laura Petrich, Mahmoud Gamal, Mohamed Elhoseiny, Martin Jagersand
Abstract	Video object segmentation is an essential task in robot manipulation to facilitate grasping and learning affordances. Incremental learning is important for robotics in unstructured environments, since the total number of objects and their variations can be intractable. Inspired by the children learning process, human robot interaction (HRI) can be utilized to teach robots about the world guided by humans similar to how children learn from a parent or a teacher. A human teacher can show potential objects of interest to the robot, which is able to self adapt to the teaching signal without providing manual segmentation labels. We propose a novel teacher-student learning paradigm to teach robots about their surrounding environment. A two-stream motion and appearance “teacher” network provides pseudo-labels to adapt an appearance “student” network. The student network is able to segment the newly learned objects in other scenes, whether they are static or in motion. We also introduce a carefully designed dataset that serves the proposed HRI setup, denoted as (I)nteractive (V)ideo (O)bject (S)egmentation. Our IVOS dataset contains teaching videos of different objects, and manipulation tasks. Unlike previous datasets, IVOS provides manipulation tasks sequences with segmentation annotation along with the waypoints for the robot trajectories. It also provides segmentation annotation for the different transformations such as translation, scale, planar rotation, and out-of-plane rotation. Our proposed adaptation method outperforms the state-of-the-art on DAVIS and FBMS with 6.8% and 1.2% in F-measure respectively. It improves over the baseline on IVOS dataset with 46.1% and 25.9% in mIoU.
Tasks	Semantic Segmentation, Video Object Segmentation, Video Semantic Segmentation
Published	2018-10-17
URL	http://arxiv.org/abs/1810.07733v4
PDF	http://arxiv.org/pdf/1810.07733v4.pdf
PWC	https://paperswithcode.com/paper/video-object-segmentation-using-teacher
Repo	https://github.com/MSiam/motion_adaptation
Framework	tf

Retina U-Net: Embarrassingly Simple Exploitation of Segmentation Supervision for Medical Object Detection


Title	Retina U-Net: Embarrassingly Simple Exploitation of Segmentation Supervision for Medical Object Detection
Authors	Paul F. Jaeger, Simon A. A. Kohl, Sebastian Bickelhaupt, Fabian Isensee, Tristan Anselm Kuder, Heinz-Peter Schlemmer, Klaus H. Maier-Hein
Abstract	The task of localizing and categorizing objects in medical images often remains formulated as a semantic segmentation problem. This approach, however, only indirectly solves the coarse localization task by predicting pixel-level scores, requiring ad-hoc heuristics when mapping back to object-level scores. State-of-the-art object detectors on the other hand, allow for individual object scoring in an end-to-end fashion, while ironically trading in the ability to exploit the full pixel-wise supervision signal. This can be particularly disadvantageous in the setting of medical image analysis, where data sets are notoriously small. In this paper, we propose Retina U-Net, a simple architecture, which naturally fuses the Retina Net one-stage detector with the U-Net architecture widely used for semantic segmentation in medical images. The proposed architecture recaptures discarded supervision signals by complementing object detection with an auxiliary task in the form of semantic segmentation without introducing the additional complexity of previously proposed two-stage detectors. We evaluate the importance of full segmentation supervision on two medical data sets, provide an in-depth analysis on a series of toy experiments and show how the corresponding performance gain grows in the limit of small data sets. Retina U-Net yields strong detection performance only reached by its more complex two-staged counterparts. Our framework including all methods implemented for operation on 2D and 3D images is available at github.com/pfjaeger/medicaldetectiontoolkit.
Tasks	Medical Object Detection, Object Detection, Semantic Segmentation
Published	2018-11-21
URL	http://arxiv.org/abs/1811.08661v1
PDF	http://arxiv.org/pdf/1811.08661v1.pdf
PWC	https://paperswithcode.com/paper/retina-u-net-embarrassingly-simple
Repo	https://github.com/MIC-DKFZ/RegRCNN
Framework	pytorch

BayesLands: A Bayesian inference approach for parameter uncertainty quantification in Badlands


Title	BayesLands: A Bayesian inference approach for parameter uncertainty quantification in Badlands
Authors	Rohitash Chandra, Danial Azam, R. Dietmar Müller, Tristan Salles, Sally Cripps
Abstract	Bayesian inference provides a principled approach towards uncertainty quantification of free parameters in geophysical forward models. This provides advantages over optimization methods that provide single point estimates as solutions, which lack uncertainty quantification. Badlands (basin and landscape dynamics model) is geophysical forward model that simulates topography development at various space and time scales. Badlands consists of a number of geophysical parameters that need to be estimated with appropriate uncertainty quantification, given the observed ground truth such as surface topography, sediment thickness and stratigraphy through time. This is challenging due to the scarcity of data, sensitivity of the parameters and complexity of the Badlands model. In this paper, we take a Bayesian approach to provide inference using Markov chain Monte Carlo sampling (MCMC). Hence, we present \textit{BayesLands}, a Bayesian framework for Badlands that fuses information obtained from complex forward models with observational data and prior knowledge. As a proof-of-concept, we consider a synthetic and real-world topography with two free parameters, namely precipitation and erodibility, that we need to estimate through BayesLands. The results of the experiments shows that BayesLands yields a promising distribution of the parameters. Moreover, the challenge in sampling due to multi-modality is presented through visualizing a likelihood surface that has a range of suboptimal modes.
Tasks	Bayesian Inference
Published	2018-05-02
URL	http://arxiv.org/abs/1805.03696v1
PDF	http://arxiv.org/pdf/1805.03696v1.pdf
PWC	https://paperswithcode.com/paper/bayeslands-a-bayesian-inference-approach-for
Repo	https://github.com/badlands-model/Bayeslands_Workshop
Framework	none

Unsupervised Controllable Text Formalization


Title	Unsupervised Controllable Text Formalization
Authors	Parag Jain, Abhijit Mishra, Amar Prakash Azad, Karthik Sankaranarayanan
Abstract	We propose a novel framework for controllable natural language transformation. Realizing that the requirement of parallel corpus is practically unsustainable for controllable generation tasks, an unsupervised training scheme is introduced. The crux of the framework is a deep neural encoder-decoder that is reinforced with text-transformation knowledge through auxiliary modules (called scorers). The scorers, based on off-the-shelf language processing tools, decide the learning scheme of the encoder-decoder based on its actions. We apply this framework for the text-transformation task of formalizing an input text by improving its readability grade; the degree of required formalization can be controlled by the user at run-time. Experiments on public datasets demonstrate the efficacy of our model towards: (a) transforming a given text to a more formal style, and (b) introducing appropriate amount of formalness in the output text pertaining to the input control. Our code and datasets are released for academic use.
Tasks
Published	2018-09-10
URL	http://arxiv.org/abs/1809.04556v6
PDF	http://arxiv.org/pdf/1809.04556v6.pdf
PWC	https://paperswithcode.com/paper/unsupervised-controllable-text-formalization
Repo	https://github.com/parajain/uctf
Framework	pytorch

Solving Bongard Problems with a Visual Language and Pragmatic Reasoning


Title	Solving Bongard Problems with a Visual Language and Pragmatic Reasoning
Authors	Stefan Depeweg, Constantin A. Rothkopf, Frank Jäkel
Abstract	More than 50 years ago Bongard introduced 100 visual concept learning problems as a testbed for intelligent vision systems. These problems are now known as Bongard problems. Although they are well known in the cognitive science and AI communities only moderate progress has been made towards building systems that can solve a substantial subset of them. In the system presented here, visual features are extracted through image processing and then translated into a symbolic visual vocabulary. We introduce a formal language that allows representing complex visual concepts based on this vocabulary. Using this language and Bayesian inference, complex visual concepts can be induced from the examples that are provided in each Bongard problem. Contrary to other concept learning problems the examples from which concepts are induced are not random in Bongard problems, instead they are carefully chosen to communicate the concept, hence requiring pragmatic reasoning. Taking pragmatic reasoning into account we find good agreement between the concepts with high posterior probability and the solutions formulated by Bongard himself. While this approach is far from solving all Bongard problems, it solves the biggest fraction yet.
Tasks	Bayesian Inference
Published	2018-04-12
URL	http://arxiv.org/abs/1804.04452v1
PDF	http://arxiv.org/pdf/1804.04452v1.pdf
PWC	https://paperswithcode.com/paper/solving-bongard-problems-with-a-visual
Repo	https://github.com/LSaldyt/unitary-proposal
Framework	none

Conditionally Independent Multiresolution Gaussian Processes


Title	Conditionally Independent Multiresolution Gaussian Processes
Authors	Jalil Taghia, Thomas B. Schön
Abstract	The multiresolution Gaussian process (GP) has gained increasing attention as a viable approach towards improving the quality of approximations in GPs that scale well to large-scale data. Most of the current constructions assume full independence across resolutions. This assumption simplifies the inference, but it underestimates the uncertainties in transitioning from one resolution to another. This in turn results in models which are prone to overfitting in the sense of excessive sensitivity to the chosen resolution, and predictions which are non-smooth at the boundaries. Our contribution is a new construction which instead assumes conditional independence among GPs across resolutions. We show that relaxing the full independence assumption enables robustness against overfitting, and that it delivers predictions that are smooth at the boundaries. Our new model is compared against current state of the art on 2 synthetic and 9 real-world datasets. In most cases, our new conditionally independent construction performed favorably when compared against models based on the full independence assumption. In particular, it exhibits little to no signs of overfitting.
Tasks	Bayesian Inference, Gaussian Processes
Published	2018-02-25
URL	http://arxiv.org/abs/1802.09086v3
PDF	http://arxiv.org/pdf/1802.09086v3.pdf
PWC	https://paperswithcode.com/paper/conditionally-independent-multiresolution
Repo	https://github.com/jtaghia/ciMRGP
Framework	none

Improving Quadrature for Constrained Integrands


Title	Improving Quadrature for Constrained Integrands
Authors	Henry Chai, Roman Garnett
Abstract	We present an improved Bayesian framework for performing inference of affine transformations of constrained functions. We focus on quadrature with nonnegative functions, a common task in Bayesian inference. We consider constraints on the range of the function of interest, such as nonnegativity or boundedness. Although our framework is general, we derive explicit approximation schemes for these constraints, and argue for the use of a log transformation for functions with high dynamic range such as likelihood surfaces. We propose a novel method for optimizing hyperparameters in this framework: we optimize the marginal likelihood in the original space, as opposed to in the transformed space. The result is a model that better explains the actual data. Experiments on synthetic and real-world data demonstrate our framework achieves superior estimates using less wall-clock time than existing Bayesian quadrature procedures.
Tasks	Bayesian Inference
Published	2018-02-13
URL	http://arxiv.org/abs/1802.04782v4
PDF	http://arxiv.org/pdf/1802.04782v4.pdf
PWC	https://paperswithcode.com/paper/improving-quadrature-for-constrained
Repo	https://github.com/hchai-wustl/mmlt
Framework	none

Interpretable preference learning: a game theoretic framework for large margin on-line feature and rule learning


Title	Interpretable preference learning: a game theoretic framework for large margin on-line feature and rule learning
Authors	Mirko Polato, Fabio Aiolli
Abstract	A large body of research is currently investigating on the connection between machine learning and game theory. In this work, game theory notions are injected into a preference learning framework. Specifically, a preference learning problem is seen as a two-players zero-sum game. An algorithm is proposed to incrementally include new useful features into the hypothesis. This can be particularly important when dealing with a very large number of potential features like, for instance, in relational learning and rule extraction. A game theoretical analysis is used to demonstrate the convergence of the algorithm. Furthermore, leveraging on the natural analogy between features and rules, the resulting models can be easily interpreted by humans. An extensive set of experiments on classification tasks shows the effectiveness of the proposed method in terms of interpretability and feature selection quality, with accuracy at the state-of-the-art.
Tasks	Feature Selection, Relational Reasoning
Published	2018-12-19
URL	http://arxiv.org/abs/1812.07895v1
PDF	http://arxiv.org/pdf/1812.07895v1.pdf
PWC	https://paperswithcode.com/paper/interpretable-preference-learning-a-game
Repo	https://github.com/makgyver/PRL
Framework	none

GAN Dissection: Visualizing and Understanding Generative Adversarial Networks


Title	GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
Authors	David Bau, Jun-Yan Zhu, Hendrik Strobelt, Bolei Zhou, Joshua B. Tenenbaum, William T. Freeman, Antonio Torralba
Abstract	Generative Adversarial Networks (GANs) have recently achieved impressive results for many real-world applications, and many GAN variants have emerged with improvements in sample quality and training stability. However, they have not been well visualized or understood. How does a GAN represent our visual world internally? What causes the artifacts in GAN results? How do architectural choices affect GAN learning? Answering such questions could enable us to develop new insights and better models. In this work, we present an analytic framework to visualize and understand GANs at the unit-, object-, and scene-level. We first identify a group of interpretable units that are closely related to object concepts using a segmentation-based network dissection method. Then, we quantify the causal effect of interpretable units by measuring the ability of interventions to control objects in the output. We examine the contextual relationship between these units and their surroundings by inserting the discovered object concepts into new images. We show several practical applications enabled by our framework, from comparing internal representations across different layers, models, and datasets, to improving GANs by locating and removing artifact-causing units, to interactively manipulating objects in a scene. We provide open source interpretation tools to help researchers and practitioners better understand their GAN models.
Tasks	Image Generation
Published	2018-11-26
URL	http://arxiv.org/abs/1811.10597v2
PDF	http://arxiv.org/pdf/1811.10597v2.pdf
PWC	https://paperswithcode.com/paper/gan-dissection-visualizing-and-understanding
Repo	https://github.com/CSAILVision/gandissect
Framework	pytorch