April 2, 2020

3294 words 16 mins read

Paper Group ANR 339

Towards Interpretable and Robust Hand Detection via Pixel-wise Prediction. DynamicPPL: Stan-like Speed for Dynamic Probabilistic Models. Designing Network Design Spaces. Fast Adaptively Weighted Matrix Factorization for Recommendation with Implicit Feedback. Structure-Feature based Graph Self-adaptive Pooling. A Multiclass Classification Approach t …

Towards Interpretable and Robust Hand Detection via Pixel-wise Prediction


Title	Towards Interpretable and Robust Hand Detection via Pixel-wise Prediction
Authors	Dan Liu, Libo Zhang, Tiejian Luo, Lili Tao, Yanjun Wu
Abstract	The lack of interpretability of existing CNN-based hand detection methods makes it difficult to understand the rationale behind their predictions. In this paper, we propose a novel neural network model, which introduces interpretability into hand detection for the first time. The main improvements include: (1) Detect hands at pixel level to explain what pixels are the basis for its decision and improve transparency of the model. (2) The explainable Highlight Feature Fusion block highlights distinctive features among multiple layers and learns discriminative ones to gain robust performance. (3) We introduce a transparent representation, the rotation map, to learn rotation features instead of complex and non-transparent rotation and derotation layers. (4) Auxiliary supervision accelerates the training process, which saves more than 10 hours in our experiments. Experimental results on the VIVA and Oxford hand detection and tracking datasets show competitive accuracy of our method compared with state-of-the-art methods with higher speed.
Tasks
Published	2020-01-13
URL	https://arxiv.org/abs/2001.04163v1
PDF	https://arxiv.org/pdf/2001.04163v1.pdf
PWC	https://paperswithcode.com/paper/towards-interpretable-and-robust-hand
Repo
Framework

DynamicPPL: Stan-like Speed for Dynamic Probabilistic Models


Title	DynamicPPL: Stan-like Speed for Dynamic Probabilistic Models
Authors	Mohamed Tarek, Kai Xu, Martin Trapp, Hong Ge, Zoubin Ghahramani
Abstract	We present the preliminary high-level design and features of DynamicPPL.jl, a modular library providing a lightning-fast infrastructure for probabilistic programming. Besides a computational performance that is often close to or better than Stan, DynamicPPL provides an intuitive DSL that allows the rapid development of complex dynamic probabilistic programs. Being entirely written in Julia, a high-level dynamic programming language for numerical computing, DynamicPPL inherits a rich set of features available through the Julia ecosystem. Since DynamicPPL is a modular, stand-alone library, any probabilistic programming system written in Julia, such as Turing.jl, can use DynamicPPL to specify models and trace their model parameters. The main features of DynamicPPL are: 1) a meta-programming based DSL for specifying dynamic models using an intuitive tilde-based notation; 2) a tracing data-structure for tracking RVs in dynamic probabilistic models; 3) a rich contextual dispatch system allowing tailored behaviour during model execution; and 4) a user-friendly syntax for probabilistic queries. Finally, we show in a variety of experiments that DynamicPPL, in combination with Turing.jl, achieves computational performance that is often close to or better than Stan.
Tasks	Probabilistic Programming
Published	2020-02-07
URL	https://arxiv.org/abs/2002.02702v1
PDF	https://arxiv.org/pdf/2002.02702v1.pdf
PWC	https://paperswithcode.com/paper/dynamicppl-stan-like-speed-for-dynamic
Repo
Framework

Designing Network Design Spaces


Title	Designing Network Design Spaces
Authors	Ilija Radosavovic, Raj Prateek Kosaraju, Ross Girshick, Kaiming He, Piotr Dollár
Abstract	In this work, we present a new network design paradigm. Our goal is to help advance the understanding of network design and discover design principles that generalize across settings. Instead of focusing on designing individual network instances, we design network design spaces that parametrize populations of networks. The overall process is analogous to classic manual design of networks, but elevated to the design space level. Using our methodology we explore the structure aspect of network design and arrive at a low-dimensional design space consisting of simple, regular networks that we call RegNet. The core insight of the RegNet parametrization is surprisingly simple: widths and depths of good networks can be explained by a quantized linear function. We analyze the RegNet design space and arrive at interesting findings that do not match the current practice of network design. The RegNet design space provides simple and fast networks that work well across a wide range of flop regimes. Under comparable training settings and flops, the RegNet models outperform the popular EfficientNet models while being up to 5x faster on GPUs.
Tasks
Published	2020-03-30
URL	https://arxiv.org/abs/2003.13678v1
PDF	https://arxiv.org/pdf/2003.13678v1.pdf
PWC	https://paperswithcode.com/paper/designing-network-design-spaces
Repo
Framework

Fast Adaptively Weighted Matrix Factorization for Recommendation with Implicit Feedback


Title	Fast Adaptively Weighted Matrix Factorization for Recommendation with Implicit Feedback
Authors	Jiawei Chen, Can Wang, Sheng Zhou, Qihao Shi, Jingbang Chen, Yan Feng, Chun Chen
Abstract	Recommendation from implicit feedback is a highly challenging task due to the lack of the reliable observed negative data. A popular and effective approach for implicit recommendation is to treat unobserved data as negative but downweight their confidence. Naturally, how to assign confidence weights and how to handle the large number of the unobserved data are two key problems for implicit recommendation models. However, existing methods either pursuit fast learning by manually assigning simple confidence weights, which lacks flexibility and may create empirical bias in evaluating user’s preference; or adaptively infer personalized confidence weights but suffer from low efficiency. To achieve both adaptive weights assignment and efficient model learning, we propose a fast adaptively weighted matrix factorization (FAWMF) based on variational auto-encoder. The personalized data confidence weights are adaptively assigned with a parameterized neural network (function) and the network can be inferred from the data. Further, to support fast and stable learning of FAWMF, a new specific batch-based learning algorithm fBGD has been developed, which trains on all feedback data but its complexity is linear to the number of observed data. Extensive experiments on real-world datasets demonstrate the superiority of the proposed FAWMF and its learning algorithm fBGD.
Tasks
Published	2020-03-04
URL	https://arxiv.org/abs/2003.01892v1
PDF	https://arxiv.org/pdf/2003.01892v1.pdf
PWC	https://paperswithcode.com/paper/fast-adaptively-weighted-matrix-factorization
Repo
Framework

Structure-Feature based Graph Self-adaptive Pooling


Title	Structure-Feature based Graph Self-adaptive Pooling
Authors	Liang Zhang, Xudong Wang, Hongsheng Li, Guangming Zhu, Peiyi Shen, Ping Li, Xiaoyuan Lu, Syed Afaq Ali Shah, Mohammed Bennamoun
Abstract	Various methods to deal with graph data have been proposed in recent years. However, most of these methods focus on graph feature aggregation rather than graph pooling. Besides, the existing top-k selection graph pooling methods have a few problems. First, to construct the pooled graph topology, current top-k selection methods evaluate the importance of the node from a single perspective only, which is simplistic and unobjective. Second, the feature information of unselected nodes is directly lost during the pooling process, which inevitably leads to a massive loss of graph feature information. To solve these problems mentioned above, we propose a novel graph self-adaptive pooling method with the following objectives: (1) to construct a reasonable pooled graph topology, structure and feature information of the graph are considered simultaneously, which provide additional veracity and objectivity in node selection; and (2) to make the pooled nodes contain sufficiently effective graph information, node feature information is aggregated before discarding the unimportant nodes; thus, the selected nodes contain information from neighbor nodes, which can enhance the use of features of the unselected nodes. Experimental results on four different datasets demonstrate that our method is effective in graph classification and outperforms state-of-the-art graph pooling methods.
Tasks	Graph Classification
Published	2020-01-30
URL	https://arxiv.org/abs/2002.00848v1
PDF	https://arxiv.org/pdf/2002.00848v1.pdf
PWC	https://paperswithcode.com/paper/structure-feature-based-graph-self-adaptive
Repo
Framework

A Multiclass Classification Approach to Label Ranking


Title	A Multiclass Classification Approach to Label Ranking
Authors	Stephan Clémençon, Robin Vogel
Abstract	In multiclass classification, the goal is to learn how to predict a random label $Y$, valued in $\mathcal{Y}={1,; \ldots,; K }$ with $K\geq 3$, based upon observing a r.v. $X$, taking its values in $\mathbb{R}^q$ with $q\geq 1$ say, by means of a classification rule $g:\mathbb{R}^q\to \mathcal{Y}$ with minimum probability of error $\mathbb{P}{Y\neq g(X) }$. However, in a wide variety of situations, the task targeted may be more ambitious, consisting in sorting all the possible label values $y$ that may be assigned to $X$ by decreasing order of the posterior probability $\eta_y(X)=\mathbb{P}{Y=y \mid X }$. This article is devoted to the analysis of this statistical learning problem, halfway between multiclass classification and posterior probability estimation (regression) and referred to as label ranking here. We highlight the fact that it can be viewed as a specific variant of ranking median regression (RMR), where, rather than observing a random permutation $\Sigma$ assigned to the input vector $X$ and drawn from a Bradley-Terry-Luce-Plackett model with conditional preference vector $(\eta_1(X),; \ldots,; \eta_K(X))$, the sole information available for training a label ranking rule is the label $Y$ ranked on top, namely $\Sigma^{-1}(1)$. Inspired by recent results in RMR, we prove that under appropriate noise conditions, the One-Versus-One (OVO) approach to multiclassification yields, as a by-product, an optimal ranking of the labels with overwhelming probability. Beyond theoretical guarantees, the relevance of the approach to label ranking promoted in this article is supported by experimental results.
Tasks
Published	2020-02-21
URL	https://arxiv.org/abs/2002.09420v1
PDF	https://arxiv.org/pdf/2002.09420v1.pdf
PWC	https://paperswithcode.com/paper/a-multiclass-classification-approach-to-label
Repo
Framework

Understanding Graph Isomorphism Network for Brain MR Functional Connectivity Analysis


Title	Understanding Graph Isomorphism Network for Brain MR Functional Connectivity Analysis
Authors	Byung-Hoon Kim, Jong Chul Ye
Abstract	Graph neural networks (GNN) rely on graph operations that include neural network training for various graph related tasks. Recently, several attempts have been made to apply the GNNs to functional magnetic resonance image (fMRI) data. Despite the recent progress, a common limitation is its difficulty to explain the classification results in a neuroscientifically explainable way. Here, we develop a framework for analyzing the fMRI data using the Graph Isomorphism Network (GIN), which was recently proposed as a state-of-the-art GNN for graph classification. One important observation in this paper is that the GIN is a realization of convolutional neural network (CNN) with two-tab filters in the graph space where the shift operation is realized using the adjacent matrix. Based on this observation, we visualize the important regions of the brain by a saliency mapping method of the trained GIN. We validate our proposed framework using large-scale resting-state fMRI data for classifying the sex of the subject based on the graph structure of the brain. The experiment was consistent with our expectation such that the obtained saliency map show high correspondence with previous neuroimaging evidences related to sex differences.
Tasks	Graph Classification
Published	2020-01-10
URL	https://arxiv.org/abs/2001.03690v1
PDF	https://arxiv.org/pdf/2001.03690v1.pdf
PWC	https://paperswithcode.com/paper/understanding-graph-isomorphism-network-for
Repo
Framework

Investigating the interaction between gradient-only line searches and different activation functions


Title	Investigating the interaction between gradient-only line searches and different activation functions
Authors	D. Kafka, Daniel. N. Wilke
Abstract	Gradient-only line searches (GOLS) adaptively determine step sizes along search directions for discontinuous loss functions resulting from dynamic mini-batch sub-sampling in neural network training. Step sizes in GOLS are determined by localizing Stochastic Non-Negative Associated Gradient Projection Points (SNN-GPPs) along descent directions. These are identified by a sign change in the directional derivative from negative to positive along a descent direction. Activation functions are a significant component of neural network architectures as they introduce non-linearities essential for complex function approximations. The smoothness and continuity characteristics of the activation functions directly affect the gradient characteristics of the loss function to be optimized. Therefore, it is of interest to investigate the relationship between activation functions and different neural network architectures in the context of GOLS. We find that GOLS are robust for a range of activation functions, but sensitive to the Rectified Linear Unit (ReLU) activation function in standard feedforward architectures. The zero-derivative in ReLU’s negative input domain can lead to the gradient-vector becoming sparse, which severely affects training. We show that implementing architectural features such as batch normalization and skip connections can alleviate these difficulties and benefit training with GOLS for all activation functions considered.
Tasks
Published	2020-02-23
URL	https://arxiv.org/abs/2002.09889v1
PDF	https://arxiv.org/pdf/2002.09889v1.pdf
PWC	https://paperswithcode.com/paper/investigating-the-interaction-between
Repo
Framework

Progressive Graph Convolutional Networks for Semi-Supervised Node Classification


Title	Progressive Graph Convolutional Networks for Semi-Supervised Node Classification
Authors	Negar Heidari, Alexandros Iosifidis
Abstract	Graph convolutional networks have been successful in addressing graph-based tasks such as semi-supervised node classification. Existing methods use a network structure defined by the user based on experimentation with fixed number of layers and employ a layer-wise propagation rule to obtain the node embeddings. Designing an automatic process to define a problem-dependant architecture for graph convolutional networks can greatly help to reduce the computational complexity of the training process. In this paper, we propose a method to automatically build compact and task-specific graph convolutional networks. Experimental results on widely used publicly available datasets indicate that the proposed method outperforms the related graph-based learning algorithms in terms of classification performance and network compactness.
Tasks	Node Classification
Published	2020-03-27
URL	https://arxiv.org/abs/2003.12277v1
PDF	https://arxiv.org/pdf/2003.12277v1.pdf
PWC	https://paperswithcode.com/paper/progressive-graph-convolutional-networks-for
Repo
Framework

Scattering GCN: Overcoming Oversmoothness in Graph Convolutional Networks


Title	Scattering GCN: Overcoming Oversmoothness in Graph Convolutional Networks
Authors	Yimeng Min, Frederik Wenkel, Guy Wolf
Abstract	Graph convolutional networks (GCNs) have shown promising results in processing graph data by extracting structure-aware features. This gave rise to extensive work in geometric deep learning, focusing on designing network architectures that ensure neuron activations conform to regularity patterns within the input graph. However, in most cases the graph structure is only accounted for by considering the similarity of activations between adjacent nodes, which in turn degrades the results. In this work, we augment GCN models by incorporating richer notions of regularity by leveraging cascades of band-pass filters, known as geometric scatterings. The produced graph features incorporate multiscale representations of local graph structures, while avoiding overly smooth activations forced by previous architectures. Moreover, inspired by skip connections used in residual networks, we introduce graph residual convolutions that reduce high-frequency noise caused by joining together information at multiple scales. Our hybrid architecture introduces a new model for semi-supervised learning on graph-structured data, and its potential is demonstrated for node classification tasks on multiple graph datasets, where it outperforms leading GCN models.
Tasks	Node Classification
Published	2020-03-18
URL	https://arxiv.org/abs/2003.08414v1
PDF	https://arxiv.org/pdf/2003.08414v1.pdf
PWC	https://paperswithcode.com/paper/scattering-gcn-overcoming-oversmoothness-in
Repo
Framework

Factorized Graph Representations for Semi-Supervised Learning from Sparse Data


Title	Factorized Graph Representations for Semi-Supervised Learning from Sparse Data
Authors	Krishna Kumar P., Paul Langton, Wolfgang Gatterbauer
Abstract	Node classification is an important problem in graph data management. It is commonly solved by various label propagation methods that work iteratively starting from a few labeled seed nodes. For graphs with arbitrary compatibilities between classes, these methods crucially depend on knowing the compatibility matrix that must be provided by either domain experts or heuristics. Can we instead directly estimate the correct compatibilities from a sparsely labeled graph in a principled and scalable way? We answer this question affirmatively and suggest a method called distant compatibility estimation that works even on extremely sparsely labeled graphs (e.g., 1 in 10,000 nodes is labeled) in a fraction of the time it later takes to label the remaining nodes. Our approach first creates multiple factorized graph representations (with size independent of the graph) and then performs estimation on these smaller graph sketches. We define algebraic amplification as the more general idea of leveraging algebraic properties of an algorithm’s update equations to amplify sparse signals. We show that our estimator is by orders of magnitude faster than an alternative approach and that the end-to-end classification accuracy is comparable to using gold standard compatibilities. This makes it a cheap preprocessing step for any existing label propagation method and removes the current dependence on heuristics.
Tasks	Node Classification
Published	2020-03-05
URL	https://arxiv.org/abs/2003.02829v1
PDF	https://arxiv.org/pdf/2003.02829v1.pdf
PWC	https://paperswithcode.com/paper/factorized-graph-representations-for-semi
Repo
Framework

Unsupervised Community Detection with a Potts Model Hamiltonian, an Efficient Algorithmic Solution, and Applications in Digital Pathology


Title	Unsupervised Community Detection with a Potts Model Hamiltonian, an Efficient Algorithmic Solution, and Applications in Digital Pathology
Authors	Brendon Lutnick, Wen Dong, Zohar Nussinov, Pinaki Sarder
Abstract	Unsupervised segmentation of large images using a Potts model Hamiltonian is unique in that segmentation is governed by a resolution parameter which scales the sensitivity to small clusters. Here, the input image is first modeled as a graph, which is then segmented by minimizing a Hamiltonian cost function defined on the graph and the respective segments. However, there exists no closed form solution of this optimization, and using previous iterative algorithmic solution techniques, the problem scales quadratically in the Input Length. Therefore, while Potts model segmentation gives accurate segmentation, it is grossly underutilized as an unsupervised learning technique. We propose a fast statistical down-sampling of input image pixels based on the respective color features, and a new iterative method to minimize the Potts model energy considering pixel to segment relationship. This method is generalizable and can be extended for image pixel texture features as well as spatial features. We demonstrate that this new method is highly efficient, and outperforms existing methods for Potts model based image segmentation. We demonstrate the application of our method in medical microscopy image segmentation; particularly, in segmenting renal glomerular micro-environment in renal pathology. Our method is not limited to image segmentation, and can be extended to any image/data segmentation/clustering task for arbitrary datasets with discrete features.
Tasks	Community Detection, Semantic Segmentation
Published	2020-02-05
URL	https://arxiv.org/abs/2002.01599v1
PDF	https://arxiv.org/pdf/2002.01599v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-community-detection-with-a-potts
Repo
Framework

Imagination-Augmented Deep Learning for Goal Recognition


Title	Imagination-Augmented Deep Learning for Goal Recognition
Authors	Thibault Duhamel, Mariane Maynard, Froduald Kabanza
Abstract	Being able to infer the goal of people we observe, interact with, or read stories about is one of the hallmarks of human intelligence. A prominent idea in current goal-recognition research is to infer the likelihood of an agent’s goal from the estimations of the costs of plans to the different goals the agent might have. Different approaches implement this idea by relying only on handcrafted symbolic representations. Their application to real-world settings is, however, quite limited, mainly because extracting rules for the factors that influence goal-oriented behaviors remains a complicated task. In this paper, we introduce a novel idea of using a symbolic planner to compute plan-cost insights, which augment a deep neural network with an imagination capability, leading to improved goal recognition accuracy in real and synthetic domains compared to a symbolic recognizer or a deep-learning goal recognizer alone.
Tasks
Published	2020-03-20
URL	https://arxiv.org/abs/2003.09529v1
PDF	https://arxiv.org/pdf/2003.09529v1.pdf
PWC	https://paperswithcode.com/paper/imagination-augmented-deep-learning-for-goal
Repo
Framework

Graph Generators: State of the Art and Open Challenges


Title	Graph Generators: State of the Art and Open Challenges
Authors	Angela Bonifati, Irena Holubová, Arnau Prat-Pérez, Sherif Sakr
Abstract	The abundance of interconnected data has fueled the design and implementation of graph generators reproducing real-world linking properties, or gauging the effectiveness of graph algorithms, techniques and applications manipulating these data. We consider graph generation across multiple subfields, such as Semantic Web, graph databases, social networks, and community detection, along with general graphs. Despite the disparate requirements of modern graph generators throughout these communities, we analyze them under a common umbrella, reaching out the functionalities, the practical usage, and their supported operations. We argue that this classification is serving the need of providing scientists, researchers and practitioners with the right data generator at hand for their work. This survey provides a comprehensive overview of the state-of-the-art graph generators by focusing on those that are pertinent and suitable for several data-intensive tasks. Finally, we discuss open challenges and missing requirements of current graph generators along with their future extensions to new emerging fields.
Tasks	Community Detection, Graph Generation
Published	2020-01-22
URL	https://arxiv.org/abs/2001.07906v1
PDF	https://arxiv.org/pdf/2001.07906v1.pdf
PWC	https://paperswithcode.com/paper/graph-generators-state-of-the-art-and-open
Repo
Framework

Notes on neighborhood semantics for logics of unknown truths and false beliefs


Title	Notes on neighborhood semantics for logics of unknown truths and false beliefs
Authors	Jie Fan
Abstract	In this article, we study logics of unknown truths and false beliefs under neighborhood semantics. We compare the relative expressivity of the two logics. It turns out that they are incomparable over various classes of neighborhood models, and the combination of the two logics are equally expressive as standard modal logic over any class of neighborhood models. We propose morphisms for each logic, which can help us explore the frame definability problem, show a general soundness and completeness result, and generalize some results in the literature. We axiomatize the two logics over various classes of neighborhood frames. Last but not least, we extend the results to the case of public announcements, which has good applications to Moore sentences and some others.
Tasks
Published	2020-02-22
URL	https://arxiv.org/abs/2002.09622v1
PDF	https://arxiv.org/pdf/2002.09622v1.pdf
PWC	https://paperswithcode.com/paper/notes-on-neighborhood-semantics-for-logics-of
Repo
Framework