April 1, 2020

3630 words 18 mins read

Paper Group ANR 510

Rotation, Translation, and Cropping for Zero-Shot Generalization. ALPINE: Active Link Prediction using Network Embedding. A Block-based Generative Model for Attributed Networks Embedding. Cross-modal variational inference for bijective signal-symbol translation. Scalable Multi-Task Imitation Learning with Autonomous Improvement. Metric-Based Imitat …

Rotation, Translation, and Cropping for Zero-Shot Generalization


Title	Rotation, Translation, and Cropping for Zero-Shot Generalization
Authors	Chang Ye, Ahmed Khalifa, Philip Bontrager, Julian Togelius
Abstract	Deep Reinforcement Learning (DRL) has shown impressive performance on domains with visual inputs, in particular various games. However, the agent is usually trained on a fixed environment, e.g. a fixed number of levels. A growing mass of evidence suggests that these trained models fail to generalize to even slight variations of the environments they were trained on. This paper advances the hypothesis that the lack of generalization is partly due to the input representation, and explores how rotation, cropping and translation could increase generality. We show that a cropped, translated and rotated observation can get better generalization on unseen levels of a two-dimensional arcade game. The generality of the agent is evaluated on a set of human-designed levels.
Tasks
Published	2020-01-27
URL	https://arxiv.org/abs/2001.09908v1
PDF	https://arxiv.org/pdf/2001.09908v1.pdf
PWC	https://paperswithcode.com/paper/rotation-translation-and-cropping-for-zero
Repo
Framework

ALPINE: Active Link Prediction using Network Embedding


Title	ALPINE: Active Link Prediction using Network Embedding
Authors	Xi Chen, Bo Kang, Jefrey Lijffijt, Tijl De Bie
Abstract	Many real-world problems can be formalized as predicting links in a partially observed network. Examples include Facebook friendship suggestions, consumer-product recommendations, and the identification of hidden interactions between actors in a crime network. Several link prediction algorithms, notably those recently introduced using network embedding, are capable of doing this by just relying on the observed part of the network. Often, the link status of a node pair can be queried, which can be used as additional information by the link prediction algorithm. Unfortunately, such queries can be expensive or time-consuming, mandating the careful consideration of which node pairs to query. In this paper we estimate the improvement in link prediction accuracy after querying any particular node pair, to use in an active learning setup. Specifically, we propose ALPINE (Active Link Prediction usIng Network Embedding), the first method to achieve this for link prediction based on network embedding. To this end, we generalized the notion of V-optimality from experimental design to this setting, as well as more basic active learning heuristics originally developed in standard classification settings. Empirical results on real data show that ALPINE is scalable, and boosts link prediction accuracy with far fewer queries.
Tasks	Active Learning, Link Prediction, Network Embedding
Published	2020-02-04
URL	https://arxiv.org/abs/2002.01227v1
PDF	https://arxiv.org/pdf/2002.01227v1.pdf
PWC	https://paperswithcode.com/paper/alpine-active-link-prediction-using-network
Repo
Framework

A Block-based Generative Model for Attributed Networks Embedding


Title	A Block-based Generative Model for Attributed Networks Embedding
Authors	Xueyan Liu, Wenzhuo Song, Wanli Zuo, Katarzyna Musial, Bo Yang
Abstract	Attributed network embedding has attracted plenty of interests in recent years. It aims to learn task-independent, low-dimension, and continuous vectors for nodes preserving both topology and attribute information. Most existing methods, such as GCN and its variations, mainly focus on the local information, i.e., the attributes of the neighbors. Thus, they have been well studied for assortative networks but ignored disassortative networks, which are common in real scenes. To address this issue, we propose a block-based generative model for attributed network embedding on a probability perspective inspired by the stochastic block model (SBM). Specifically, the nodes are assigned to several blocks wherein the nodes in the same block share the similar link patterns. These patterns can define assortative networks containing communities or disassortative networks with the multipartite, hub, or any hybrid structures. Concerning the attribute information, we assume that each node has a hidden embedding related to its assigned block, and then we use a neural network to characterize the nonlinearity between the node embedding and its attribute. We perform extensive experiments on real-world and synthetic attributed networks, and the experimental results show that our proposed method remarkably outperforms state-of-the-art embedding methods for both clustering and classification tasks, especially on disassortative networks.
Tasks	Network Embedding
Published	2020-01-06
URL	https://arxiv.org/abs/2001.01383v1
PDF	https://arxiv.org/pdf/2001.01383v1.pdf
PWC	https://paperswithcode.com/paper/a-block-based-generative-model-for-attributed
Repo
Framework


Title	Cross-modal variational inference for bijective signal-symbol translation
Authors	Axel Chemla–Romeu-Santos, Stavros Ntalampiras, Philippe Esling, Goffredo Haus, Gérard Assayag
Abstract	Extraction of symbolic information from signals is an active field of research enabling numerous applications especially in the Musical Information Retrieval domain. This complex task, that is also related to other topics such as pitch extraction or instrument recognition, is a demanding subject that gave birth to numerous approaches, mostly based on advanced signal processing-based algorithms. However, these techniques are often non-generic, allowing the extraction of definite physical properties of the signal (pitch, octave), but not allowing arbitrary vocabularies or more general annotations. On top of that, these techniques are one-sided, meaning that they can extract symbolic data from an audio signal, but cannot perform the reverse process and make symbol-to-signal generation. In this paper, we propose an bijective approach for signal/symbol translation by turning this problem into a density estimation task over signal and symbolic domains, considered both as related random variables. We estimate this joint distribution with two different variational auto-encoders, one for each domain, whose inner representations are forced to match with an additive constraint, allowing both models to learn and generate separately while allowing signal-to-symbol and symbol-to-signal inference. In this article, we test our models on pitch, octave and dynamics symbols, which comprise a fundamental step towards music transcription and label-constrained audio generation. In addition to its versatility, this system is rather light during training and generation while allowing several interesting creative uses that we outline at the end of the article.
Tasks	Audio Generation, Density Estimation, Information Retrieval
Published	2020-02-10
URL	https://arxiv.org/abs/2002.03862v1
PDF	https://arxiv.org/pdf/2002.03862v1.pdf
PWC	https://paperswithcode.com/paper/cross-modal-variational-inference-for
Repo
Framework

Scalable Multi-Task Imitation Learning with Autonomous Improvement


Title	Scalable Multi-Task Imitation Learning with Autonomous Improvement
Authors	Avi Singh, Eric Jang, Alexander Irpan, Daniel Kappler, Murtaza Dalal, Sergey Levine, Mohi Khansari, Chelsea Finn
Abstract	While robot learning has demonstrated promising results for enabling robots to automatically acquire new skills, a critical challenge in deploying learning-based systems is scale: acquiring enough data for the robot to effectively generalize broadly. Imitation learning, in particular, has remained a stable and powerful approach for robot learning, but critically relies on expert operators for data collection. In this work, we target this challenge, aiming to build an imitation learning system that can continuously improve through autonomous data collection, while simultaneously avoiding the explicit use of reinforcement learning, to maintain the stability, simplicity, and scalability of supervised imitation. To accomplish this, we cast the problem of imitation with autonomous improvement into a multi-task setting. We utilize the insight that, in a multi-task setting, a failed attempt at one task might represent a successful attempt at another task. This allows us to leverage the robot’s own trials as demonstrations for tasks other than the one that the robot actually attempted. Using an initial dataset of multi-task demonstration data, the robot autonomously collects trials which are only sparsely labeled with a binary indication of whether the trial accomplished any useful task or not. We then embed the trials into a learned latent space of tasks, trained using only the initial demonstration dataset, to draw similarities between various trials, enabling the robot to achieve one-shot generalization to new tasks. In contrast to prior imitation learning approaches, our method can autonomously collect data with sparse supervision for continuous improvement, and in contrast to reinforcement learning algorithms, our method can effectively improve from sparse, task-agnostic reward signals.
Tasks	Imitation Learning
Published	2020-02-25
URL	https://arxiv.org/abs/2003.02636v1
PDF	https://arxiv.org/pdf/2003.02636v1.pdf
PWC	https://paperswithcode.com/paper/scalable-multi-task-imitation-learning-with
Repo
Framework

Metric-Based Imitation Learning Between Two Dissimilar Anthropomorphic Robotic Arms


Title	Metric-Based Imitation Learning Between Two Dissimilar Anthropomorphic Robotic Arms
Authors	Marcus Ebner von Eschenbach, Binyamin Manela, Jan Peters, Armin Biess
Abstract	The development of autonomous robotic systems that can learn from human demonstrations to imitate a desired behavior - rather than being manually programmed - has huge technological potential. One major challenge in imitation learning is the correspondence problem: how to establish corresponding states and actions between expert and learner, when the embodiments of the agents are different (morphology, dynamics, degrees of freedom, etc.). Many existing approaches in imitation learning circumvent the correspondence problem, for example, kinesthetic teaching or teleoperation, which are performed on the robot. In this work we explicitly address the correspondence problem by introducing a distance measure between dissimilar embodiments. This measure is then used as a loss function for static pose imitation and as a feedback signal within a model-free deep reinforcement learning framework for dynamic movement imitation between two anthropomorphic robotic arms in simulation. We find that the measure is well suited for describing the similarity between embodiments and for learning imitation policies by distance minimization.
Tasks	Imitation Learning
Published	2020-02-25
URL	https://arxiv.org/abs/2003.02638v1
PDF	https://arxiv.org/pdf/2003.02638v1.pdf
PWC	https://paperswithcode.com/paper/metric-based-imitation-learning-between-two
Repo
Framework

Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences


Title	Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences
Authors	Daniel S. Brown, Russell Coleman, Ravi Srinivasan, Scott Niekum
Abstract	Bayesian reward learning from demonstrations enables rigorous safety and uncertainty analysis when performing imitation learning. However, Bayesian reward learning methods are typically computationally intractable for complex control problems. We propose a highly efficient Bayesian reward learning algorithm that scales to high-dimensional imitation learning problems by first pre-training a low-dimensional feature encoding via self-supervised tasks and then leveraging preferences over demonstrations to perform fast Bayesian inference. We evaluate our proposed approach on the task of learning to play Atari games from demonstrations, without access to the game score. For Atari games our approach enables us to generate 100,000 samples from the posterior over reward functions in only 5 minutes using a personal laptop. Furthermore, our proposed approach achieves comparable or better imitation learning performance than state-of-the-art methods that only find a point estimate of the reward function. Finally, we show that our approach enables efficient high-confidence policy performance bounds. We show that these high-confidence performance bounds can be used to rank the performance and risk of a variety of evaluation policies, despite not having samples of the reward function. We also show evidence that high-confidence performance bounds can be used to detect reward hacking in complex imitation learning problems.
Tasks	Atari Games, Bayesian Inference, Imitation Learning
Published	2020-02-21
URL	https://arxiv.org/abs/2002.09089v1
PDF	https://arxiv.org/pdf/2002.09089v1.pdf
PWC	https://paperswithcode.com/paper/safe-imitation-learning-via-fast-bayesian
Repo
Framework

A Bayesian Monte-Carlo Uncertainty Model for Assessment of Shear Stress Entropy


Title	A Bayesian Monte-Carlo Uncertainty Model for Assessment of Shear Stress Entropy
Authors	Amin Kazemian-Kale-Kale, Azadeh Gholami, Mohammad Rezaie-Balf, Amir Mosavi, Ahmed A Sattar, Bahram Gharabaghi, Hossein Bonakdari
Abstract	The entropy models have been recently adopted in many studies to evaluate the distribution of the shear stress in circular channels. However, the uncertainty in their predictions and their reliability remains an open question. We present a novel method to evaluate the uncertainty of four popular entropy models, including Shannon, Shannon-Power Low (PL), Tsallis, and Renyi, in shear stress estimation in circular channels. The Bayesian Monte-Carlo (BMC) uncertainty method is simplified considering a 95% Confidence Bound (CB). We developed a new statistic index called as FREEopt-based OCB (FOCB) using the statistical indices Forecasting Range of Error Estimation (FREE) and the percentage of observed data in the CB (Nin), which integrates their combined effect. The Shannon and Shannon PL entropies had close values of the FOCB equal to 8.781 and 9.808, respectively, had the highest certainty in the calculation of shear stress values in circular channels followed by traditional uniform flow shear stress and Tsallis models with close values of 14.491 and 14.895, respectively. However, Renyi entropy with much higher values of FOCB equal to 57.726 has less certainty in the estimation of shear stress than other models. Using the presented results in this study, the amount of confidence in entropy methods in the calculation of shear stress to design and implement different types of open channels and their stability is determined.
Tasks
Published	2020-01-10
URL	https://arxiv.org/abs/2001.04802v1
PDF	https://arxiv.org/pdf/2001.04802v1.pdf
PWC	https://paperswithcode.com/paper/a-bayesian-monte-carlo-uncertainty-model-for
Repo
Framework

Deep Neural Networks for Automatic Speech Processing: A Survey from Large Corpora to Limited Data


Title	Deep Neural Networks for Automatic Speech Processing: A Survey from Large Corpora to Limited Data
Authors	Vincent Roger, Jérôme Farinas, Julien Pinquier
Abstract	Most state-of-the-art speech systems are using Deep Neural Networks (DNNs). Those systems require a large amount of data to be learned. Hence, learning state-of-the-art frameworks on under-resourced speech languages/problems is a difficult task. Problems could be the limited amount of data for impaired speech. Furthermore, acquiring more data and/or expertise is time-consuming and expensive. In this paper we position ourselves for the following speech processing tasks: Automatic Speech Recognition, speaker identification and emotion recognition. To assess the problem of limited data, we firstly investigate state-of-the-art Automatic Speech Recognition systems as it represents the hardest tasks (due to the large variability in each language). Next, we provide an overview of techniques and tasks requiring fewer data. In the last section we investigate few-shot techniques as we interpret under-resourced speech as a few-shot problem. In that sense we propose an overview of few-shot techniques and perspectives of using such techniques for the focused speech problems in this survey. It occurs that the reviewed techniques are not well adapted for large datasets. Nevertheless, some promising results from the literature encourage the usage of such techniques for speech processing.
Tasks	Emotion Recognition, Speaker Identification, Speech Recognition
Published	2020-03-09
URL	https://arxiv.org/abs/2003.04241v1
PDF	https://arxiv.org/pdf/2003.04241v1.pdf
PWC	https://paperswithcode.com/paper/deep-neural-networks-for-automatic-speech
Repo
Framework

Crowdsourcing the Perception of Machine Teaching


Title	Crowdsourcing the Perception of Machine Teaching
Authors	Jonggi Hong, Kyungjun Lee, June Xu, Hernisa Kacorri
Abstract	Teachable interfaces can empower end-users to attune machine learning systems to their idiosyncratic characteristics and environment by explicitly providing pertinent training examples. While facilitating control, their effectiveness can be hindered by the lack of expertise or misconceptions. We investigate how users may conceptualize, experience, and reflect on their engagement in machine teaching by deploying a mobile teachable testbed in Amazon Mechanical Turk. Using a performance-based payment scheme, Mechanical Turkers (N = 100) are called to train, test, and re-train a robust recognition model in real-time with a few snapshots taken in their environment. We find that participants incorporate diversity in their examples drawing from parallels to how humans recognize objects independent of size, viewpoint, location, and illumination. Many of their misconceptions relate to consistency and model capabilities for reasoning. With limited variation and edge cases in testing, the majority of them do not change strategies on a second training attempt.
Tasks
Published	2020-02-05
URL	https://arxiv.org/abs/2002.01618v1
PDF	https://arxiv.org/pdf/2002.01618v1.pdf
PWC	https://paperswithcode.com/paper/crowdsourcing-the-perception-of-machine
Repo
Framework

Memristor Hardware-Friendly Reinforcement Learning


Title	Memristor Hardware-Friendly Reinforcement Learning
Authors	Nan Wu, Adrien Vincent, Dmitri Strukov, Yuan Xie
Abstract	Recently, significant progress has been made in solving sophisticated problems among various domains by using reinforcement learning (RL), which allows machines or agents to learn from interactions with environments rather than explicit supervision. As the end of Moore’s law seems to be imminent, emerging technologies that enable high performance neuromorphic hardware systems are attracting increasing attention. Namely, neuromorphic architectures that leverage memristors, the programmable and nonvolatile two-terminal devices, as synaptic weights in hardware neural networks, are candidates of choice to realize such highly energy-efficient and complex nervous systems. However, one of the challenges for memristive hardware with integrated learning capabilities is prohibitively large number of write cycles that might be required during learning process, and this situation is even exacerbated under RL situations. In this work we propose a memristive neuromorphic hardware implementation for the actor-critic algorithm in RL. By introducing a two-fold training procedure (i.e., ex-situ pre-training and in-situ re-training) and several training techniques, the number of weight updates can be significantly reduced and thus it will be suitable for efficient in-situ learning implementations. As a case study, we consider the task of balancing an inverted pendulum, a classical problem in both RL and control theory. We believe that this study shows the promise of using memristor-based hardware neural networks for handling complex tasks through in-situ reinforcement learning.
Tasks
Published	2020-01-20
URL	https://arxiv.org/abs/2001.06930v1
PDF	https://arxiv.org/pdf/2001.06930v1.pdf
PWC	https://paperswithcode.com/paper/memristor-hardware-friendly-reinforcement
Repo
Framework

Should Artificial Intelligence Governance be Centralised? Design Lessons from History


Title	Should Artificial Intelligence Governance be Centralised? Design Lessons from History
Authors	Peter Cihon, Matthijs M. Maas, Luke Kemp
Abstract	Can effective international governance for artificial intelligence remain fragmented, or is there a need for a centralised international organisation for AI? We draw on the history of other international regimes to identify advantages and disadvantages in centralising AI governance. Some considerations, such as efficiency and political power, speak in favour of centralisation. Conversely, the risk of creating a slow and brittle institution speaks against it, as does the difficulty in securing participation while creating stringent rules. Other considerations depend on the specific design of a centralised institution. A well-designed body may be able to deter forum shopping and ensure policy coordination. However, forum shopping can be beneficial and a fragmented landscape of institutions can be self-organising. Centralisation entails trade-offs and the details matter. We conclude with two core recommendations. First, the outcome will depend on the exact design of a central institution. A well-designed centralised regime covering a set of coherent issues could be beneficial. But locking-in an inadequate structure may pose a fate worse than fragmentation. Second, for now fragmentation will likely persist. This should be closely monitored to see if it is self-organising or simply inadequate.
Tasks
Published	2020-01-10
URL	https://arxiv.org/abs/2001.03573v1
PDF	https://arxiv.org/pdf/2001.03573v1.pdf
PWC	https://paperswithcode.com/paper/should-artificial-intelligence-governance-be
Repo
Framework

Towards automated kernel selection in machine learning systems: A SYCL case study


Title	Towards automated kernel selection in machine learning systems: A SYCL case study
Authors	John Lawson
Abstract	Automated tuning of compute kernels is a popular area of research, mainly focused on finding optimal kernel parameters for a problem with fixed input sizes. This approach is good for deploying machine learning models, where the network topology is constant, but machine learning research often involves changing network topologies and hyperparameters. Traditional kernel auto-tuning has limited impact in this case; a more general selection of kernels is required for libraries to accelerate machine learning research. In this paper we present initial results using machine learning to select kernels in a case study deploying high performance SYCL kernels in libraries that target a range of heterogeneous devices from desktop GPUs to embedded accelerators. The techniques investigated apply more generally and could similarly be integrated with other heterogeneous programming systems. By combining auto-tuning and machine learning these kernel selection processes can be deployed with little developer effort to achieve high performance on new hardware.
Tasks
Published	2020-03-15
URL	https://arxiv.org/abs/2003.06795v1
PDF	https://arxiv.org/pdf/2003.06795v1.pdf
PWC	https://paperswithcode.com/paper/towards-automated-kernel-selection-in-machine
Repo
Framework

The Tensor Brain: Semantic Decoding for Perception and Memory


Title	The Tensor Brain: Semantic Decoding for Perception and Memory
Authors	Volker Tresp, Sahand Sharifzadeh, Dario Konopatzki, Yunpu Ma
Abstract	We analyse perception and memory, using mathematical models for knowledge graphs and tensors, to gain insights into the corresponding functionalities of the human mind. Our discussion is based on the concept of propositional sentences consisting of \textit{subject-predicate-object} (SPO) triples for expressing elementary facts. SPO sentences are the basis for most natural languages but might also be important for explicit perception and declarative memories, as well as intra-brain communication and the ability to argue and reason. A set of SPO sentences can be described as a knowledge graph, which can be transformed into an adjacency tensor. We introduce tensor models, where concepts have dual representations as indices and associated embeddings, two constructs we believe are essential for the understanding of implicit and explicit perception and memory in the brain. We argue that a biological realization of perception and memory imposes constraints on information processing. In particular, we propose that explicit perception and declarative memories require a semantic decoder, which, in a simple realization, is based on four layers: First, a sensory memory layer, as a buffer for sensory input, second, an index layer representing concepts, third, a memoryless representation layer for the broadcasting of information —the “blackboard”, or the “canvas” of the brain— and fourth, a working memory layer as a processing center and data buffer. We discuss the operations of the four layers and relate them to the global workspace theory. In a Bayesian brain interpretation, semantic memory defines the prior for observable triple statements. We propose that —in evolution and during development— semantic memory, episodic memory, and natural language evolved as emergent properties in agents’ process to gain a deeper understanding of sensory information.
Tasks	Knowledge Graphs
Published	2020-01-29
URL	https://arxiv.org/abs/2001.11027v3
PDF	https://arxiv.org/pdf/2001.11027v3.pdf
PWC	https://paperswithcode.com/paper/the-tensor-brain-semantic-decoding-for
Repo
Framework

Unsupervised Learning of the Set of Local Maxima


Title	Unsupervised Learning of the Set of Local Maxima
Authors	Lior Wolf, Sagie Benaim, Tomer Galanti
Abstract	This paper describes a new form of unsupervised learning, whose input is a set of unlabeled points that are assumed to be local maxima of an unknown value function v in an unknown subset of the vector space. Two functions are learned: (i) a set indicator c, which is a binary classifier, and (ii) a comparator function h that given two nearby samples, predicts which sample has the higher value of the unknown function v. Loss terms are used to ensure that all training samples x are a local maxima of v, according to h and satisfy c(x)=1. Therefore, c and h provide training signals to each other: a point x’ in the vicinity of x satisfies c(x)=-1 or is deemed by h to be lower in value than x. We present an algorithm, show an example where it is more efficient to use local maxima as an indicator function than to employ conventional classification, and derive a suitable generalization bound. Our experiments show that the method is able to outperform one-class classification algorithms in the task of anomaly detection and also provide an additional signal that is extracted in a completely unsupervised way.
Tasks	Anomaly Detection
Published	2020-01-14
URL	https://arxiv.org/abs/2001.05026v1
PDF	https://arxiv.org/pdf/2001.05026v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-learning-of-the-set-of-local-1
Repo
Framework