January 28, 2020

3191 words 15 mins read

Paper Group ANR 857

Asynchronous Coagent Networks: Stochastic Networks for Reinforcement Learning without Backpropagation or a Clock. Time-weighted Attentional Session-Aware Recommender System. How to make latent factors interpretable by feeding Factorization machines with knowledge graphs. How robust is MovieLens? A dataset analysis for recommender systems. Geometry …

Asynchronous Coagent Networks: Stochastic Networks for Reinforcement Learning without Backpropagation or a Clock


Title	Asynchronous Coagent Networks: Stochastic Networks for Reinforcement Learning without Backpropagation or a Clock
Authors	James Kostas, Chris Nota, Philip S. Thomas
Abstract	In this paper we introduce a reinforcement learning (RL) approach for training policies, including artificial neural network policies, that is both backpropagation-free and clock-free. It is backpropagation-free in that it does not propagate any information backwards through the network. It is clock-free in that no signal is given to each node in the network to specify when it should compute its output and when it should update its weights. We contend that these two properties increase the biological plausibility of our algorithms and facilitate distributed implementations. Additionally, our approach eliminates the need for customized learning rules for hierarchical RL algorithms like the option-critic.
Tasks
Published	2019-02-15
URL	http://arxiv.org/abs/1902.05650v3
PDF	http://arxiv.org/pdf/1902.05650v3.pdf
PWC	https://paperswithcode.com/paper/asynchronous-coagent-networks-stochastic
Repo
Framework

Time-weighted Attentional Session-Aware Recommender System


Title	Time-weighted Attentional Session-Aware Recommender System
Authors	Mei Wang, Weizhi Li, Yan Yan
Abstract	Session-based Recurrent Neural Networks (RNNs) are gaining increasing popularity for recommendation task, due to the high autocorrelation of user’s behavior on the latest session and the effectiveness of RNN to capture the sequence order information. However, most existing session-based RNN recommender systems still solely focus on the short-term interactions within a single session and completely discard all the other long-term data across different sessions. While traditional Collaborative Filtering (CF) methods have many advanced research works on exploring long-term dependency, which show great value to be explored and exploited in deep learning models. Therefore, in this paper, we propose ASARS, a novel framework that effectively imports the temporal dynamics methodology in CF into session-based RNN system in DL, such that the temporal info can act as scalable weights by a parallel attentional network. Specifically, we first conduct an extensive data analysis to show the distribution and importance of such temporal interactions data both within sessions and across sessions. And then, our ASARS framework promotes two novel models: (1) an inter-session temporal dynamic model that captures the long-term user interaction for RNN recommender system. We integrate the time changes in session RNN and add user preferences as model drifting; and (2) a novel triangle parallel attention network that enhances the original RNN model by incorporating time information. Such triangle parallel network is also specially designed for realizing data argumentation in sequence-to-scalar RNN architecture, and thus it can be trained very efficiently. Our extensive experiments on four real datasets from different domains demonstrate the effectiveness and large improvement of ASARS for personalized recommendation.
Tasks	Recommendation Systems
Published	2019-09-12
URL	https://arxiv.org/abs/1909.05414v1
PDF	https://arxiv.org/pdf/1909.05414v1.pdf
PWC	https://paperswithcode.com/paper/time-weighted-attentional-session-aware
Repo
Framework

How to make latent factors interpretable by feeding Factorization machines with knowledge graphs


Title	How to make latent factors interpretable by feeding Factorization machines with knowledge graphs
Authors	Vito Walter Anelli, Tommaso Di Noia, Eugenio Di Sciascio, Azzurra Ragone, Joseph Trotta
Abstract	Model-based approaches to recommendation can recommend items with a very high level of accuracy. Unfortunately, even when the model embeds content-based information, if we move to a latent space we miss references to the actual semantics of recommended items. Consequently, this makes non-trivial the interpretation of a recommendation process. In this paper, we show how to initialize latent factors in Factorization Machines by using semantic features coming from a knowledge graph in order to train an interpretable model. With our model, semantic features are injected into the learning process to retain the original informativeness of the items available in the dataset. The accuracy and effectiveness of the trained model have been tested using two well-known recommender systems datasets. By relying on the information encoded in the original knowledge graph, we have also evaluated the semantic accuracy and robustness for the knowledge-aware interpretability of the final model.
Tasks	Knowledge Graphs, Recommendation Systems
Published	2019-09-11
URL	https://arxiv.org/abs/1909.05038v1
PDF	https://arxiv.org/pdf/1909.05038v1.pdf
PWC	https://paperswithcode.com/paper/how-to-make-latent-factors-interpretable-by
Repo
Framework

How robust is MovieLens? A dataset analysis for recommender systems


Title	How robust is MovieLens? A dataset analysis for recommender systems
Authors	Anne-Marie Tousch
Abstract	Research publication requires public datasets. In recommender systems, some datasets are largely used to compare algorithms against a –supposedly– common benchmark. Problem: for various reasons, these datasets are heavily preprocessed, making the comparison of results across papers difficult. This paper makes explicit the variety of preprocessing and evaluation protocols to test the robustness of a dataset (or lack of flexibility). While robustness is good to compare results across papers, for flexible datasets we propose a method to select a preprocessing protocol and share results more transparently.
Tasks	Recommendation Systems
Published	2019-09-12
URL	https://arxiv.org/abs/1909.12799v1
PDF	https://arxiv.org/pdf/1909.12799v1.pdf
PWC	https://paperswithcode.com/paper/how-robust-is-movielens-a-dataset-analysis
Repo
Framework

Geometry of Deep Convolutional Networks


Title	Geometry of Deep Convolutional Networks
Authors	Stefan Carlsson
Abstract	We give a formal procedure for computing preimages of convolutional network outputs using the dual basis defined from the set of hyperplanes associated with the layers of the network. We point out the special symmetry associated with arrangements of hyperplanes of convolutional networks that take the form of regular multidimensional polyhedral cones. We discuss the efficiency of large number of layers of nested cones that result from incremental small size convolutions in order to give a good compromise between efficient contraction of data to low dimensions and shaping of preimage manifolds. We demonstrate how a specific network flattens a non linear input manifold to an affine output manifold and discuss its relevance to understanding classification properties of deep networks.
Tasks
Published	2019-05-21
URL	https://arxiv.org/abs/1905.08922v1
PDF	https://arxiv.org/pdf/1905.08922v1.pdf
PWC	https://paperswithcode.com/paper/geometry-of-deep-convolutional-networks
Repo
Framework

Policy-Gradient Algorithms Have No Guarantees of Convergence in Linear Quadratic Games


Title	Policy-Gradient Algorithms Have No Guarantees of Convergence in Linear Quadratic Games
Authors	Eric Mazumdar, Lillian J. Ratliff, Michael I. Jordan, S. Shankar Sastry
Abstract	We show by counterexample that policy-gradient algorithms have no guarantees of even local convergence to Nash equilibria in continuous action and state space multi-agent settings. To do so, we analyze gradient-play in N-player general-sum linear quadratic games, a classic game setting which is recently emerging as a benchmark in the field of multi-agent learning. In such games the state and action spaces are continuous and global Nash equilibria can be found be solving coupled Ricatti equations. Further, gradient-play in LQ games is equivalent to multi agent policy-gradient. We first show that these games are surprisingly not convex games. Despite this, we are still able to show that the only critical points of the gradient dynamics are global Nash equilibria. We then give sufficient conditions under which policy-gradient will avoid the Nash equilibria, and generate a large number of general-sum linear quadratic games that satisfy these conditions. In such games we empirically observe the players converging to limit cycles for which the time average does not coincide with a Nash equilibrium. The existence of such games indicates that one of the most popular approaches to solving reinforcement learning problems in the classic reinforcement learning setting has no local guarantee of convergence in multi-agent settings. Further, the ease with which we can generate these counterexamples suggests that such situations are not mere edge cases and are in fact quite common.
Tasks
Published	2019-07-08
URL	https://arxiv.org/abs/1907.03712v2
PDF	https://arxiv.org/pdf/1907.03712v2.pdf
PWC	https://paperswithcode.com/paper/policy-gradient-algorithms-have-no-guarantees
Repo
Framework

On the Relation between Weak Completion Semantics and Answer Set Semantics


Title	On the Relation between Weak Completion Semantics and Answer Set Semantics
Authors	Emmanuelle-Anna Dietz Saldanha, Jorge Fandinno
Abstract	The Weak Completion Semantics (WCS) is a computational cognitive theory that has shown to be successful in modeling episodes of human reasoning. As the WCS is a recently developed logic programming approach, this paper investigates the correspondence of the WCS with respect to the well-established Answer Set Semantics (ASP). The underlying three-valued logic of both semantics is different and their models are evaluated with respect to different program transformations. We first illustrate these differences by the formal representation of some examples of a well-known psychological experiment, the suppression task. After that, we will provide a translation from logic programs understood under the WCS into logic programs understood under the ASP. In particular, we will show that logic programs under the WCS can be represented as logic programs under the ASP by means of a definition completion, where all defined atoms in a program must be false when their definitions are false.
Tasks
Published	2019-10-16
URL	https://arxiv.org/abs/1910.07278v1
PDF	https://arxiv.org/pdf/1910.07278v1.pdf
PWC	https://paperswithcode.com/paper/on-the-relation-between-weak-completion
Repo
Framework

Working memory facilitates reward-modulated Hebbian learning in recurrent neural networks


Title	Working memory facilitates reward-modulated Hebbian learning in recurrent neural networks
Authors	Roman Pogodin, Dane Corneil, Alexander Seeholzer, Joseph Heng, Wulfram Gerstner
Abstract	Reservoir computing is a powerful tool to explain how the brain learns temporal sequences, such as movements, but existing learning schemes are either biologically implausible or too inefficient to explain animal performance. We show that a network can learn complicated sequences with a reward-modulated Hebbian learning rule if the network of reservoir neurons is combined with a second network that serves as a dynamic working memory and provides a spatio-temporal backbone signal to the reservoir. In combination with the working memory, reward-modulated Hebbian learning of the readout neurons performs as well as FORCE learning, but with the advantage of a biologically plausible interpretation of both the learning rule and the learning paradigm.
Tasks
Published	2019-10-23
URL	https://arxiv.org/abs/1910.10559v1
PDF	https://arxiv.org/pdf/1910.10559v1.pdf
PWC	https://paperswithcode.com/paper/working-memory-facilitates-reward-modulated
Repo
Framework

A Tandem Learning Rule for Efficient and Rapid Inference on Deep Spiking Neural Networks


Title	A Tandem Learning Rule for Efficient and Rapid Inference on Deep Spiking Neural Networks
Authors	Jibin Wu, Yansong Chua, Malu Zhang, Guoqi Li, Haizhou Li, Kay Chen Tan
Abstract	Emerging neuromorphic computing (NC) architectures have shown compelling energy efficiency in machine learning tasks using spiking neural networks (SNNs). However, due to the non-differentiable nature of spiking neuronal functions, the standard error back-propagation algorithm is not directly applicable to SNNs. In this work, we propose a tandem learning framework, that consists of a SNN and an Artificial Neural Network (ANN) that share weights. The ANN is an auxiliary structure that facilitates the error back-propagation for the training of the SNN. To this end, we consider the spike count as the discrete neural representation and design ANN neuronal activation function that can effectively approximate the spike count of the coupled SNN. The SNNs that are trained with the proposed tandem learning rule show competitive classification accuracies on the CIFAR-10 and ImageNet-2012 datasets with significantly reduced inference time and total synaptic operations over other state-of-the-art SNN implementations. The proposed tandem learning rule offers a novel solution to training efficient, low latency and high accuracy deep SNNs with low computing resources.
Tasks
Published	2019-07-02
URL	https://arxiv.org/abs/1907.01167v2
PDF	https://arxiv.org/pdf/1907.01167v2.pdf
PWC	https://paperswithcode.com/paper/a-hybrid-learning-rule-for-efficient-and
Repo
Framework

Taxonomical hierarchy of canonicalized relations from multiple Knowledge Bases


Title	Taxonomical hierarchy of canonicalized relations from multiple Knowledge Bases
Authors	Akshay Parekh, Ashish Anand, Amit Awekar
Abstract	This work addresses two important questions pertinent to Relation Extraction (RE). First, what are all possible relations that could exist between any two given entity types? Second, how do we define an unambiguous taxonomical (is-a) hierarchy among the identified relations? To address the first question, we use three resources Wikipedia Infobox, Wikidata, and DBpedia. This study focuses on relations between person, organization and location entity types. We exploit Wikidata and DBpedia in a data-driven manner, and Wikipedia Infobox templates manually to generate lists of relations. Further, to address the second question, we canonicalize, filter, and combine the identified relations from the three resources to construct a taxonomical hierarchy. This hierarchy contains 623 canonical relations with highest contribution from Wikipedia Infobox followed by DBpedia and Wikidata. The generated relation list subsumes an average of 85% of relations from RE datasets when entity types are restricted.
Tasks	Relation Extraction
Published	2019-09-13
URL	https://arxiv.org/abs/1909.06249v4
PDF	https://arxiv.org/pdf/1909.06249v4.pdf
PWC	https://paperswithcode.com/paper/taxonomical-hierarchy-of-canonicalized
Repo
Framework

Detection of small changes in medical and random-dot images comparing self-organizing map performance to human detection


Title	Detection of small changes in medical and random-dot images comparing self-organizing map performance to human detection
Authors	John Wandeto, Henry Nyongesa, Yves Remond, Birgitta Dresp-Langley
Abstract	Radiologists use time series of medical images to monitor the progression of a patient condition. They compare information gleaned from sequences of images to gain insight on progression or remission of the lesions, thus evaluating the progress of a patient condition or response to therapy. Visual methods of determining differences between one series of images to another can be subjective or fail to detect very small differences. We propose the use of quantization errors obtained from Self Organizing Maps for image content analysis. We tested this technique with MRI images to which we progressively added synthetic lesions. We have used a global approach that considers changes on the entire image as opposed to changes in segmented lesion regions only. We claim that this approach does not suffer from the limitations imposed by segmentation, which may compromise the results. Results show quantization errors increased with the increase in lesions on the images. The results are also consistent with previous studies using alternative approaches. We then compared the detectability ability of our method to that of human novice observers having to detect very small local differences in random-dot images. The quantization errors of the SOM outputs compared with correct positive rates, after subtraction of false positive rates (guess rates), increased noticeably and consistently with small increases in local dot size that were not detectable by humans. We conclude that our method detects very small changes in complex images and suggest that it could be implemented to assist human operators in image based decision making.
Tasks	Decision Making, Human Detection, Quantization, Time Series
Published	2019-06-26
URL	https://arxiv.org/abs/1906.11675v1
PDF	https://arxiv.org/pdf/1906.11675v1.pdf
PWC	https://paperswithcode.com/paper/detection-of-small-changes-in-medical-and
Repo
Framework

Automated Human Claustrum Segmentation using Deep Learning Technologies


Title	Automated Human Claustrum Segmentation using Deep Learning Technologies
Authors	Ahmed Awad Albishri, Syed Jawad Hussain Shah, Anthony Schmiedler, Seung Suk Kang, Yugyung Lee
Abstract	In recent years, Deep Learning (DL) has shown promising results in conducting AI tasks such as computer vision and image segmentation. Specifically, Convolutional Neural Network (CNN) models in DL have been applied to prevention,detection, and diagnosis in predictive medicine. Image segmentation plays a significant role in disease detection and prevention.However, there are enormous challenges in performing DL-based automatic segmentation due to the nature of medical images such as heterogeneous modalities and formats, insufficient labeled training data, and the high-class imbalance in the labeled data. Furthermore, automating segmentation of medical images,like magnetic resonance images (MRI), becomes a challenging task. The need for automated segmentation or annotation is what motivates our work. In this paper, we propose a fully automated approach that aims to segment the human claustrum for analytical purposes. We applied a U-Net CNN model to segment the claustrum (Cl) from a MRI dataset. With this approach, we have achieved an average Dice per case score of 0.72 for Cl segmentation, with K=5 for cross-validation. The expert in the medical domain also evaluates these results.
Tasks	Semantic Segmentation
Published	2019-11-18
URL	https://arxiv.org/abs/1911.07515v1
PDF	https://arxiv.org/pdf/1911.07515v1.pdf
PWC	https://paperswithcode.com/paper/automated-human-claustrum-segmentation-using
Repo
Framework

Instance Segmentation with Point Supervision


Title	Instance Segmentation with Point Supervision
Authors	Issam H. Laradji, Negar Rostamzadeh, Pedro O. Pinheiro, David Vazquez, Mark Schmidt
Abstract	Instance segmentation methods often require costly per-pixel labels. We propose a method that only requires point-level annotations. During training, the model only has access to a single pixel label per object, yet the task is to output full segmentation masks. To address this challenge, we construct a network with two branches: (1) a localization network (L-Net) that predicts the location of each object; and (2) an embedding network (E-Net) that learns an embedding space where pixels of the same object are close. The segmentation masks for the located objects are obtained by grouping pixels with similar embeddings. At training time, while L-Net only requires point-level annotations, E-Net uses pseudo-labels generated by a class-agnostic object proposal method. We evaluate our approach on PASCAL VOC, COCO, KITTI and CityScapes datasets. The experiments show that our method (1) obtains competitive results compared to fully-supervised methods in certain scenarios; (2) outperforms fully- and weakly- supervised methods with a fixed annotation budget; and (3) is a first strong baseline for instance segmentation with point-level supervision.
Tasks	Instance Segmentation, Semantic Segmentation
Published	2019-06-14
URL	https://arxiv.org/abs/1906.06392v1
PDF	https://arxiv.org/pdf/1906.06392v1.pdf
PWC	https://paperswithcode.com/paper/instance-segmentation-with-point-supervision
Repo
Framework

Exploiting Offset-guided Network for Pose Estimation and Tracking


Title	Exploiting Offset-guided Network for Pose Estimation and Tracking
Authors	Rui Zhang, Zheng Zhu, Peng Li, Rui Wu, Chaoxu Guo, Guan Huang, Hailun Xia
Abstract	Human pose estimation has witnessed a significant advance thanks to the development of deep learning. Recent human pose estimation approaches tend to directly predict the location heatmaps, which causes quantization errors and inevitably deteriorates the performance within the reduced network output. Aim at solving it, we revisit the heatmap-offset aggregation method and propose the Offset-guided Network (OGN) with an intuitive but effective fusion strategy for both two-stages pose estimation and Mask R-CNN. For two-stages pose estimation, a greedy box generation strategy is also proposed to keep more necessary candidates while performing person detection. For mask R-CNN, ratio-consistent is adopted to improve the generalization ability of the network. State-of-the-art results on COCO and PoseTrack dataset verify the effectiveness of our offset-guided pose estimation and tracking.
Tasks	Human Detection, Pose Estimation, Quantization
Published	2019-06-04
URL	https://arxiv.org/abs/1906.01344v1
PDF	https://arxiv.org/pdf/1906.01344v1.pdf
PWC	https://paperswithcode.com/paper/exploiting-offset-guided-network-for-pose
Repo
Framework

Deep Image-to-Video Adaptation and Fusion Networks for Action Recognition


Title	Deep Image-to-Video Adaptation and Fusion Networks for Action Recognition
Authors	Yang Liu, Zhaoyang Lu, Jing Li, Tao Yang, Chao Yao
Abstract	Existing deep learning methods for action recognition in videos require a large number of labeled videos for training, which is labor-intensive and time-consuming. For the same action, the knowledge learned from different media types, e.g., videos and images, may be related and complementary. However, due to the domain shifts and heterogeneous feature representations between videos and images, the performance of classifiers trained on images may be dramatically degraded when directly deployed to videos. In this paper, we propose a novel method, named Deep Image-to-Video Adaptation and Fusion Networks (DIVAFN), to enhance action recognition in videos by transferring knowledge from images using video keyframes as a bridge. The DIVAFN is a unified deep learning model, which integrates domain-invariant representations learning and cross-modal feature fusion into a unified optimization framework. Specifically, we design an efficient cross-modal similarities metric to reduce the modality shift among images, keyframes and videos. Then, we adopt an autoencoder architecture, whose hidden layer is constrained to be the semantic representations of the action class names. In this way, when the autoencoder is adopted to project the learned features from different domains to the same space, more compact, informative and discriminative representations can be obtained. Finally, the concatenation of the learned semantic feature representations from these three autoencoders are used to train the classifier for action recognition in videos. Comprehensive experiments on four real-world datasets show that our method outperforms some state-of-the-art domain adaptation and action recognition methods.
Tasks	Action Recognition In Videos, Domain Adaptation
Published	2019-11-25
URL	https://arxiv.org/abs/1911.10751v1
PDF	https://arxiv.org/pdf/1911.10751v1.pdf
PWC	https://paperswithcode.com/paper/deep-image-to-video-adaptation-and-fusion
Repo
Framework