April 1, 2020

3274 words 16 mins read

Paper Group ANR 422

Computational Design with Crowds. Towards naturalistic human neuroscience and neuroengineering: behavior mining in long-term video and neural recordings. An Incremental Explanation of Inference in Hybrid Bayesian Networks for Increasing Model Trustworthiness and Supporting Clinical Decision Making. Semi-Supervised Class Discovery. Exploration-Explo …

Computational Design with Crowds


Title	Computational Design with Crowds
Authors	Yuki Koyama, Takeo Igarashi
Abstract	Computational design is aimed at supporting or automating design processes using computational techniques. However, some classes of design tasks involve criteria that are difficult to handle only with computers. For example, visual design tasks seeking to fulfill aesthetic goals are difficult to handle purely with computers. One promising approach is to leverage human computation; that is, to incorporate human input into the computation process. Crowdsourcing platforms provide a convenient way to integrate such human computation into a working system. In this chapter, we discuss such computational design with crowds in the domain of parameter tweaking tasks in visual design. Parameter tweaking is often performed to maximize the aesthetic quality of designed objects. Computational design powered by crowds can solve this maximization problem by leveraging human computation. We discuss the opportunities and challenges of computational design with crowds with two illustrative examples: (1) estimating the objective function (specifically, preference learning from crowds’ pairwise comparisons) to facilitate interactive design exploration by a designer and (2) directly searching for the optimal parameter setting that maximizes the objective function (specifically, crowds-in-the-loop Bayesian optimization).
Tasks
Published	2020-02-20
URL	https://arxiv.org/abs/2002.08657v1
PDF	https://arxiv.org/pdf/2002.08657v1.pdf
PWC	https://paperswithcode.com/paper/computational-design-with-crowds
Repo
Framework

Towards naturalistic human neuroscience and neuroengineering: behavior mining in long-term video and neural recordings


Title	Towards naturalistic human neuroscience and neuroengineering: behavior mining in long-term video and neural recordings
Authors	Satpreet H. Singh, Steven M. Peterson, Rajesh P. N. Rao, Bingni W. Brunton
Abstract	Recent advances in brain recording technology and artificial intelligence are propelling a new paradigm in neuroscience beyond the traditional controlled experiment. Naturalistic neuroscience studies neural computations associated with spontaneous behaviors performed in unconstrained settings. Analyzing such unstructured data lacking a priori experimental design remains a significant challenge, especially when the data is multi-modal and long-term. Here we describe an automated approach for analyzing large ($\approx$250 GB/subject) datasets of simultaneously recorded human electrocorticography (ECoG) and naturalistic behavior video data for 12 subjects. Our pipeline discovers and annotates thousands of instances of human upper-limb movement events in long-term (7–9 day) naturalistic behavior data using a combination of computer vision, discrete latent-variable modeling, and string pattern-matching. Analysis of the simultaneously recorded brain data uncovers neural signatures of movement that corroborate prior findings from traditional controlled experiments. We also prototype a decoder for a movement initiation detection task to demonstrate the efficacy of our pipeline as a source of training data for brain-computer interfacing applications. We plan to publish our curated dataset, which captures naturalistic neural and behavioral variability at a scale not previously available. We believe this data will enable further research on models of neural function and decoding that incorporate such naturalistic variability and perform more robustly in real-world settings.
Tasks
Published	2020-01-23
URL	https://arxiv.org/abs/2001.08349v1
PDF	https://arxiv.org/pdf/2001.08349v1.pdf
PWC	https://paperswithcode.com/paper/towards-naturalistic-human-neuroscience-and
Repo
Framework

An Incremental Explanation of Inference in Hybrid Bayesian Networks for Increasing Model Trustworthiness and Supporting Clinical Decision Making


Title	An Incremental Explanation of Inference in Hybrid Bayesian Networks for Increasing Model Trustworthiness and Supporting Clinical Decision Making
Authors	Evangelia Kyrimi, Somayyeh Mossadegh, Nigel Tai, William Marsh
Abstract	Various AI models are increasingly being considered as part of clinical decision-support tools. However, the trustworthiness of such models is rarely considered. Clinicians are more likely to use a model if they can understand and trust its predictions. Key to this is if its underlying reasoning can be explained. A Bayesian network (BN) model has the advantage that it is not a black-box and its reasoning can be explained. In this paper, we propose an incremental explanation of inference that can be applied to hybrid BNs, i.e. those that contain both discrete and continuous nodes. The key questions that we answer are: (1) which important evidence supports or contradicts the prediction, and (2) through which intermediate variables does the information flow. The explanation is illustrated using a real clinical case study. A small evaluation study is also conducted.
Tasks	Decision Making
Published	2020-03-05
URL	https://arxiv.org/abs/2003.02599v2
PDF	https://arxiv.org/pdf/2003.02599v2.pdf
PWC	https://paperswithcode.com/paper/an-incremental-explanation-of-inference-in
Repo
Framework

Semi-Supervised Class Discovery


Title	Semi-Supervised Class Discovery
Authors	Jeremy Nixon, Jeremiah Liu, David Berthelot
Abstract	One promising approach to dealing with datapoints that are outside of the initial training distribution (OOD) is to create new classes that capture similarities in the datapoints previously rejected as uncategorizable. Systems that generate labels can be deployed against an arbitrary amount of data, discovering classification schemes that through training create a higher quality representation of data. We introduce the Dataset Reconstruction Accuracy, a new and important measure of the effectiveness of a model’s ability to create labels. We introduce benchmarks against this Dataset Reconstruction metric. We apply a new heuristic, class learnability, for deciding whether a class is worthy of addition to the training dataset. We show that our class discovery system can be successfully applied to vision and language, and we demonstrate the value of semi-supervised learning in automatically discovering novel classes.
Tasks
Published	2020-02-10
URL	https://arxiv.org/abs/2002.03480v2
PDF	https://arxiv.org/pdf/2002.03480v2.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-class-discovery
Repo
Framework

Exploration-Exploitation in Constrained MDPs


Title	Exploration-Exploitation in Constrained MDPs
Authors	Yonathan Efroni, Shie Mannor, Matteo Pirotta
Abstract	In many sequential decision-making problems, the goal is to optimize a utility function while satisfying a set of constraints on different utilities. This learning problem is formalized through Constrained Markov Decision Processes (CMDPs). In this paper, we investigate the exploration-exploitation dilemma in CMDPs. While learning in an unknown CMDP, an agent should trade-off exploration to discover new information about the MDP, and exploitation of the current knowledge to maximize the reward while satisfying the constraints. While the agent will eventually learn a good or optimal policy, we do not want the agent to violate the constraints too often during the learning process. In this work, we analyze two approaches for learning in CMDPs. The first approach leverages the linear formulation of CMDP to perform optimistic planning at each episode. The second approach leverages the dual formulation (or saddle-point formulation) of CMDP to perform incremental, optimistic updates of the primal and dual variables. We show that both achieves sublinear regret w.r.t.\ the main utility while having a sublinear regret on the constraint violations. That being said, we highlight a crucial difference between the two approaches; the linear programming approach results in stronger guarantees than in the dual formulation based approach.
Tasks	Decision Making
Published	2020-03-04
URL	https://arxiv.org/abs/2003.02189v1
PDF	https://arxiv.org/pdf/2003.02189v1.pdf
PWC	https://paperswithcode.com/paper/exploration-exploitation-in-constrained-mdps
Repo
Framework


Title	Secure Social Recommendation based on Secret Sharing
Authors	Chaochao Chen, Liang Li, Bingzhe Wu, Cheng Hong, Li Wang, Jun Zhou
Abstract	Nowadays, privacy preserving machine learning has been drawing much attention in both industry and academy. Meanwhile, recommender systems have been extensively adopted by many commercial platforms (e.g. Amazon) and they are mainly built based on user-item interactions. Besides, social platforms (e.g. Facebook) have rich resources of user social information. It is well known that social information, which is rich on social platforms such as Facebook, are useful to recommender systems. It is anticipated to combine the social information with the user-item ratings to improve the overall recommendation performance. Most existing recommendation models are built based on the assumptions that the social information are available. However, different platforms are usually reluctant to (or cannot) share their data due to certain concerns. In this paper, we first propose a SEcure SOcial RECommendation (SeSoRec) framework which can (1) collaboratively mine knowledge from social platform to improve the recommendation performance of the rating platform, and (2) securely keep the raw data of both platforms. We then propose a Secret Sharing based Matrix Multiplication (SSMM) protocol to optimize SeSoRec and prove its correctness and security theoretically. By applying minibatch gradient descent, SeSoRec has linear time complexities in terms of both computation and communication. The comprehensive experimental results on three real-world datasets demonstrate the effectiveness of our proposed SeSoRec and SSMM.
Tasks	Recommendation Systems
Published	2020-02-06
URL	https://arxiv.org/abs/2002.02088v2
PDF	https://arxiv.org/pdf/2002.02088v2.pdf
PWC	https://paperswithcode.com/paper/secure-social-recommendation-based-on-secret
Repo
Framework

A Uniform Treatment of Aggregates and Constraints in Hybrid ASP


Title	A Uniform Treatment of Aggregates and Constraints in Hybrid ASP
Authors	Pedro Cabalar, Jorge Fandinno, Torsten Schaub, Philipp Wanko
Abstract	Characterizing hybrid ASP solving in a generic way is difficult since one needs to abstract from specific theories. Inspired by lazy SMT solving, this is usually addressed by treating theory atoms as opaque. Unlike this, we propose a slightly more transparent approach that includes an abstract notion of a term. Rather than imposing a syntax on terms, we keep them abstract by stipulating only some basic properties. With this, we further develop a semantic framework for hybrid ASP solving and provide aggregate functions for theory variables that adhere to different semantic principles, show that they generalize existing aggregate semantics in ASP and how we can rely on off-the-shelf hybrid solvers for implementation.
Tasks
Published	2020-03-09
URL	https://arxiv.org/abs/2003.04176v2
PDF	https://arxiv.org/pdf/2003.04176v2.pdf
PWC	https://paperswithcode.com/paper/a-uniform-treatment-of-aggregates-and
Repo
Framework

Can Increasing Input Dimensionality Improve Deep Reinforcement Learning?


Title	Can Increasing Input Dimensionality Improve Deep Reinforcement Learning?
Authors	Kei Ota, Tomoaki Oiki, Devesh K. Jha, Toshisada Mariyama, Daniel Nikovski
Abstract	Deep reinforcement learning (RL) algorithms have recently achieved remarkable successes in various sequential decision making tasks, leveraging advances in methods for training large deep networks. However, these methods usually require large amounts of training data, which is often a big problem for real-world applications. One natural question to ask is whether learning good representations for states and using larger networks helps in learning better policies. In this paper, we try to study if increasing input dimensionality helps improve performance and sample efficiency of model-free deep RL algorithms. To do so, we propose an online feature extractor network (OFENet) that uses neural nets to produce good representations to be used as inputs to deep RL algorithms. Even though the high dimensionality of input is usually supposed to make learning of RL agents more difficult, we show that the RL agents in fact learn more efficiently with the high-dimensional representation than with the lower-dimensional state observations. We believe that stronger feature propagation together with larger networks (and thus larger search space) allows RL agents to learn more complex functions of states and thus improves the sample efficiency. Through numerical experiments, we show that the proposed method outperforms several other state-of-the-art algorithms in terms of both sample efficiency and performance.
Tasks	Decision Making
Published	2020-03-03
URL	https://arxiv.org/abs/2003.01629v1
PDF	https://arxiv.org/pdf/2003.01629v1.pdf
PWC	https://paperswithcode.com/paper/can-increasing-input-dimensionality-improve
Repo
Framework

Propose, Test, Release: Differentially private estimation with high probability


Title	Propose, Test, Release: Differentially private estimation with high probability
Authors	Victor-Emmanuel Brunel, Marco Avella-Medina
Abstract	We derive concentration inequalities for differentially private median and mean estimators building on the “Propose, Test, Release” (PTR) mechanism introduced by Dwork and Lei (2009). We introduce a new general version of the PTR mechanism that allows us to derive high probability error bounds for differentially private estimators. Our algorithms provide the first statistical guarantees for differentially private estimation of the median and mean without any boundedness assumptions on the data, and without assuming that the target population parameter lies in some known bounded interval. Our procedures do not rely on any truncation of the data and provide the first sub-Gaussian high probability bounds for differentially private median and mean estimation, for possibly heavy tailed random variables.
Tasks
Published	2020-02-19
URL	https://arxiv.org/abs/2002.08774v1
PDF	https://arxiv.org/pdf/2002.08774v1.pdf
PWC	https://paperswithcode.com/paper/propose-test-release-differentially-private
Repo
Framework

Compressing deep neural networks on FPGAs to binary and ternary precision with HLS4ML


Title	Compressing deep neural networks on FPGAs to binary and ternary precision with HLS4ML
Authors	Giuseppe Di Guglielmo, Javier Duarte, Philip Harris, Duc Hoang, Sergo Jindariani, Edward Kreinar, Mia Liu, Vladimir Loncar, Jennifer Ngadiuba, Kevin Pedro, Maurizio Pierini, Dylan Rankin, Sheila Sagear, Sioni Summers, Nhan Tran, Zhenbin Wu
Abstract	We present the implementation of binary and ternary neural networks in the hls4ml library, designed to automatically convert deep neural network models to digital circuits with FPGA firmware. Starting from benchmark models trained with floating point precision, we investigate different strategies to reduce the network’s resource consumption by reducing the numerical precision of the network parameters to binary or ternary. We discuss the trade-off between model accuracy and resource consumption. In addition, we show how to balance between latency and accuracy by retaining full precision on a selected subset of network components. As an example, we consider two multiclass classification tasks: handwritten digit recognition with the MNIST data set and jet identification with simulated proton-proton collisions at the CERN Large Hadron Collider. The binary and ternary implementation has similar performance to the higher precision implementation while using drastically fewer FPGA resources.
Tasks	Handwritten Digit Recognition
Published	2020-03-11
URL	https://arxiv.org/abs/2003.06308v1
PDF	https://arxiv.org/pdf/2003.06308v1.pdf
PWC	https://paperswithcode.com/paper/compressing-deep-neural-networks-on-fpgas-to
Repo
Framework

Convergence Time Optimization for Federated Learning over Wireless Networks


Title	Convergence Time Optimization for Federated Learning over Wireless Networks
Authors	Mingzhe Chen, H. Vincent Poor, Walid Saad, Shuguang Cui
Abstract	In this paper, the convergence time of federated learning (FL), when deployed over a realistic wireless network, is studied. In particular, a wireless network is considered in which wireless users transmit their local FL models (trained using their locally collected data) to a base station (BS). The BS, acting as a central controller, generates a global FL model using the received local FL models and broadcasts it back to all users. Due to the limited number of resource blocks (RBs) in a wireless network, only a subset of users can be selected to transmit their local FL model parameters to the BS at each learning step. Moreover, since each user has unique training data samples, the BS prefers to include all local user FL models to generate a converged global FL model. Hence, the FL performance and convergence time will be significantly affected by the user selection scheme. Therefore, it is necessary to design an appropriate user selection scheme that enables users of higher importance to be selected more frequently. This joint learning, wireless resource allocation, and user selection problem is formulated as an optimization problem whose goal is to minimize the FL convergence time while optimizing the FL performance. To solve this problem, a probabilistic user selection scheme is proposed such that the BS is connected to the users whose local FL models have significant effects on its global FL model with high probabilities. Given the user selection policy, the uplink RB allocation can be determined. To further reduce the FL convergence time, artificial neural networks (ANNs) are used to estimate the local FL models of the users that are not allocated any RBs for local FL model transmission at each given learning step, which enables the BS to enhance its global FL model and improve the FL convergence speed and performance.
Tasks
Published	2020-01-22
URL	https://arxiv.org/abs/2001.07845v1
PDF	https://arxiv.org/pdf/2001.07845v1.pdf
PWC	https://paperswithcode.com/paper/convergence-time-optimization-for-federated
Repo
Framework

A multivariate water quality parameter prediction model using recurrent neural network


Title	A multivariate water quality parameter prediction model using recurrent neural network
Authors	Dhruti Dheda, Ling Cheng
Abstract	The global degradation of water resources is a matter of great concern, especially for the survival of humanity. The effective monitoring and management of existing water resources is necessary to achieve and maintain optimal water quality. The prediction of the quality of water resources will aid in the timely identification of possible problem areas and thus increase the efficiency of water management. The purpose of this research is to develop a water quality prediction model based on water quality parameters through the application of a specialised recurrent neural network (RNN), Long Short-Term Memory (LSTM) and the use of historical water quality data over several years. Both multivariate single and multiple step LSTM models were developed, using a Rectified Linear Unit (ReLU) activation function and a Root Mean Square Propagation (RMSprop) optimiser was developed. The single step model attained an error of 0.01 mg/L, whilst the multiple step model achieved a Root Mean Squared Error (RMSE) of 0.227 mg/L.
Tasks
Published	2020-03-25
URL	https://arxiv.org/abs/2003.11492v1
PDF	https://arxiv.org/pdf/2003.11492v1.pdf
PWC	https://paperswithcode.com/paper/a-multivariate-water-quality-parameter
Repo
Framework

Generating Electronic Health Records with Multiple Data Types and Constraints


Title	Generating Electronic Health Records with Multiple Data Types and Constraints
Authors	Chao Yan, Ziqi Zhang, Steve Nyemba, Bradley A. Malin
Abstract	Sharing electronic health records (EHRs) on a large scale may lead to privacy intrusions. Recent research has shown that risks may be mitigated by simulating EHRs through generative adversarial network (GAN) frameworks. Yet the methods developed to date are limited because they 1) focus on generating data of a single type (e.g., diagnosis codes), neglecting other data types (e.g., demographics, procedures or vital signs) and 2) do not represent constraints between features. In this paper, we introduce a method to simulate EHRs composed of multiple data types by 1) refining the GAN model, 2) accounting for feature constraints, and 3) incorporating key utility measures for such generation tasks. Our analysis with over $770,000$ EHRs from Vanderbilt University Medical Center demonstrates that the new model achieves higher performance in terms of retaining basic statistics, cross-feature correlations, latent structural properties, feature constraints and associated patterns from real data, without sacrificing privacy.
Tasks
Published	2020-03-17
URL	https://arxiv.org/abs/2003.07904v2
PDF	https://arxiv.org/pdf/2003.07904v2.pdf
PWC	https://paperswithcode.com/paper/generating-electronic-health-records-with
Repo
Framework

Dynamic Narrowing of VAE Bottlenecks Using GECO and $L_0$ Regularization


Title	Dynamic Narrowing of VAE Bottlenecks Using GECO and $L_0$ Regularization
Authors	Cedric De Boom, Samuel Wauthier, Tim Verbelen, Bart Dhoedt
Abstract	When designing variational autoencoders (VAEs) or other types of latent space models, the dimensionality of the latent space is typically defined upfront. In this process, it is possible that the number of dimensions is under- or overprovisioned for the application at hand. In case the dimensionality is not predefined, this parameter is usually determined using time- and resource-consuming cross-validation. For these reasons we have developed a technique to shrink the latent space dimensionality of VAEs automatically and on-the-fly during training using Generalized ELBO with Constrained Optimization (GECO) and the $L_0$-Augment-REINFORCE-Merge ($L_0$-ARM) gradient estimator. The GECO optimizer ensures that we are not violating a predefined upper bound on the reconstruction error. This paper presents the algorithmic details of our method along with experimental results on five different datasets. We find that our training procedure is stable and that the latent space can be pruned effectively without violating the GECO constraints.
Tasks
Published	2020-03-24
URL	https://arxiv.org/abs/2003.10901v2
PDF	https://arxiv.org/pdf/2003.10901v2.pdf
PWC	https://paperswithcode.com/paper/dynamic-narrowing-of-vae-bottlenecks-using
Repo
Framework

Contextual Reserve Price Optimization in Auctions


Title	Contextual Reserve Price Optimization in Auctions
Authors	Joey Huchette, Haihao Lu, Hossein Esfandiari, Vahab Mirrokni
Abstract	We study the problem of learning a linear model to set the reserve price in order to maximize expected revenue in an auction, given contextual information. First, we show that it is not possible to solve this problem in polynomial time unless the \emph{Exponential Time Hypothesis} fails. Second, we present a strong mixed-integer programming (MIP) formulation for this problem, which is capable of exactly modeling the nonconvex and discontinuous expected reward function. Moreover, we show that this MIP formulation is ideal (the strongest possible formulation) for the revenue function. Since it can be computationally expensive to exactly solve the MIP formulation, we also study the performance of its linear programming (LP) relaxation. We show that, unfortunately, in the worst case the objective gap of the linear programming relaxation can be $O(n)$ times larger than the optimal objective of the actual problem, where $n$ is the number of samples. Finally, we present computational results, showcasing that the mixed-integer programming formulation, along with its linear programming relaxation, are able to superior both the in-sample performance and the out-of-sample performance of the state-of-the-art algorithms on both real and synthetic datasets.
Tasks
Published	2020-02-20
URL	https://arxiv.org/abs/2002.08841v1
PDF	https://arxiv.org/pdf/2002.08841v1.pdf
PWC	https://paperswithcode.com/paper/contextual-reserve-price-optimization-in
Repo
Framework