February 1, 2020

3108 words 15 mins read

Paper Group AWR 122

ARMIN: Towards a More Efficient and Light-weight Recurrent Memory Network. Unsupervised Attributed Multiplex Network Embedding. Barack’s Wife Hillary: Using Knowledge-Graphs for Fact-Aware Language Modeling. 2D and 3D Segmentation of uncertain local collagen fiber orientations in SHG microscopy. HiGitClass: Keyword-Driven Hierarchical Classificatio …

ARMIN: Towards a More Efficient and Light-weight Recurrent Memory Network


Title	ARMIN: Towards a More Efficient and Light-weight Recurrent Memory Network
Authors	Zhangheng Li, Jia-Xing Zhong, Jingjia Huang, Tao Zhang, Thomas Li, Ge Li
Abstract	In recent years, memory-augmented neural networks(MANNs) have shown promising power to enhance the memory ability of neural networks for sequential processing tasks. However, previous MANNs suffer from complex memory addressing mechanism, making them relatively hard to train and causing computational overheads. Moreover, many of them reuse the classical RNN structure such as LSTM for memory processing, causing inefficient exploitations of memory information. In this paper, we introduce a novel MANN, the Auto-addressing and Recurrent Memory Integrating Network (ARMIN) to address these issues. The ARMIN only utilizes hidden state ht for automatic memory addressing, and uses a novel RNN cell for refined integration of memory information. Empirical results on a variety of experiments demonstrate that the ARMIN is more light-weight and efficient compared to existing memory networks. Moreover, we demonstrate that the ARMIN can achieve much lower computational overhead than vanilla LSTM while keeping similar performances. Codes are available on github.com/zoharli/armin.
Tasks
Published	2019-06-28
URL	https://arxiv.org/abs/1906.12087v1
PDF	https://arxiv.org/pdf/1906.12087v1.pdf
PWC	https://paperswithcode.com/paper/armin-towards-a-more-efficient-and-light
Repo	https://github.com/zoharli/armin
Framework	pytorch

Unsupervised Attributed Multiplex Network Embedding


Title	Unsupervised Attributed Multiplex Network Embedding
Authors	Chanyoung Park, Donghyun Kim, Jiawei Han, Hwanjo Yu
Abstract	Nodes in a multiplex network are connected by multiple types of relations. However, most existing network embedding methods assume that only a single type of relation exists between nodes. Even for those that consider the multiplexity of a network, they overlook node attributes, resort to node labels for training, and fail to model the global properties of a graph. We present a simple yet effective unsupervised network embedding method for attributed multiplex network called DMGI, inspired by Deep Graph Infomax (DGI) that maximizes the mutual information between local patches of a graph, and the global representation of the entire graph. We devise a systematic way to jointly integrate the node embeddings from multiple graphs by introducing 1) the consensus regularization framework that minimizes the disagreements among the relation-type specific node embeddings, and 2) the universal discriminator that discriminates true samples regardless of the relation types. We also show that the attention mechanism infers the importance of each relation type, and thus can be useful for filtering unnecessary relation types as a preprocessing step. Extensive experiments on various downstream tasks demonstrate that DMGI outperforms the state-of-the-art methods, even though DMGI is fully unsupervised.
Tasks	Network Embedding
Published	2019-11-15
URL	https://arxiv.org/abs/1911.06750v2
PDF	https://arxiv.org/pdf/1911.06750v2.pdf
PWC	https://paperswithcode.com/paper/unsupervised-attributed-multiplex-network
Repo	https://github.com/pcy1302/DMGI
Framework	pytorch

Barack’s Wife Hillary: Using Knowledge-Graphs for Fact-Aware Language Modeling


Title	Barack’s Wife Hillary: Using Knowledge-Graphs for Fact-Aware Language Modeling
Authors	Robert L. Logan IV, Nelson F. Liu, Matthew E. Peters, Matt Gardner, Sameer Singh
Abstract	Modeling human language requires the ability to not only generate fluent text but also encode factual knowledge. However, traditional language models are only capable of remembering facts seen at training time, and often have difficulty recalling them. To address this, we introduce the knowledge graph language model (KGLM), a neural language model with mechanisms for selecting and copying facts from a knowledge graph that are relevant to the context. These mechanisms enable the model to render information it has never seen before, as well as generate out-of-vocabulary tokens. We also introduce the Linked WikiText-2 dataset, a corpus of annotated text aligned to the Wikidata knowledge graph whose contents (roughly) match the popular WikiText-2 benchmark. In experiments, we demonstrate that the KGLM achieves significantly better performance than a strong baseline language model. We additionally compare different language model’s ability to complete sentences requiring factual knowledge, showing that the KGLM outperforms even very large language models in generating facts.
Tasks	Knowledge Graphs, Language Modelling
Published	2019-06-17
URL	https://arxiv.org/abs/1906.07241v2
PDF	https://arxiv.org/pdf/1906.07241v2.pdf
PWC	https://paperswithcode.com/paper/baracks-wife-hillary-using-knowledge-graphs
Repo	https://github.com/rloganiv/kglm-model
Framework	pytorch

2D and 3D Segmentation of uncertain local collagen fiber orientations in SHG microscopy


Title	2D and 3D Segmentation of uncertain local collagen fiber orientations in SHG microscopy
Authors	Lars Schmarje, Claudius Zelenka, Ulf Geisen, Claus-C. Glüer, Reinhard Koch
Abstract	Collagen fiber orientations in bones, visible with Second Harmonic Generation (SHG) microscopy, represent the inner structure and its alteration due to influences like cancer. While analyses of these orientations are valuable for medical research, it is not feasible to analyze the needed large amounts of local orientations manually. Since we have uncertain borders for these local orientations only rough regions can be segmented instead of a pixel-wise segmentation. We analyze the effect of these uncertain borders on human performance by a user study. Furthermore, we compare a variety of 2D and 3D methods such as classical approaches like Fourier analysis with state-of-the-art deep neural networks for the classification of local fiber orientations. We present a general way to use pretrained 2D weights in 3D neural networks, such as Inception-ResNet-3D a 3D extension of Inception-ResNet-v2. In a 10 fold cross-validation our two stage segmentation based on Inception-ResNet-3D and transferred 2D ImageNet weights achieves a human comparable accuracy.
Tasks
Published	2019-07-30
URL	https://arxiv.org/abs/1907.12868v1
PDF	https://arxiv.org/pdf/1907.12868v1.pdf
PWC	https://paperswithcode.com/paper/2d-and-3d-segmentation-of-uncertain-local
Repo	https://github.com/Emprime/uncertain-fiber-segmentation
Framework	tf

HiGitClass: Keyword-Driven Hierarchical Classification of GitHub Repositories


Title	HiGitClass: Keyword-Driven Hierarchical Classification of GitHub Repositories
Authors	Yu Zhang, Frank F. Xu, Sha Li, Yu Meng, Xuan Wang, Qi Li, Jiawei Han
Abstract	GitHub has become an important platform for code sharing and scientific exchange. With the massive number of repositories available, there is a pressing need for topic-based search. Even though the topic label functionality has been introduced, the majority of GitHub repositories do not have any labels, impeding the utility of search and topic-based analysis. This work targets the automatic repository classification problem as \textit{keyword-driven hierarchical classification}. Specifically, users only need to provide a label hierarchy with keywords to supply as supervision. This setting is flexible, adaptive to the users’ needs, accounts for the different granularity of topic labels and requires minimal human effort. We identify three key challenges of this problem, namely (1) the presence of multi-modal signals; (2) supervision scarcity and bias; (3) supervision format mismatch. In recognition of these challenges, we propose the \textsc{HiGitClass} framework, comprising of three modules: heterogeneous information network embedding; keyword enrichment; topic modeling and pseudo document generation. Experimental results on two GitHub repository collections confirm that \textsc{HiGitClass} is superior to existing weakly-supervised and dataless hierarchical classification methods, especially in its ability to integrate both structured and unstructured data for repository classification.
Tasks	Network Embedding
Published	2019-10-16
URL	https://arxiv.org/abs/1910.07115v1
PDF	https://arxiv.org/pdf/1910.07115v1.pdf
PWC	https://paperswithcode.com/paper/higitclass-keyword-driven-hierarchical
Repo	https://github.com/yuzhimanhua/HiGitClass
Framework	pytorch

Learning Attention-based Embeddings for Relation Prediction in Knowledge Graphs


Title	Learning Attention-based Embeddings for Relation Prediction in Knowledge Graphs
Authors	Deepak Nathani, Jatin Chauhan, Charu Sharma, Manohar Kaul
Abstract	The recent proliferation of knowledge graphs (KGs) coupled with incomplete or partial information, in the form of missing relations (links) between entities, has fueled a lot of research on knowledge base completion (also known as relation prediction). Several recent works suggest that convolutional neural network (CNN) based models generate richer and more expressive feature embeddings and hence also perform well on relation prediction. However, we observe that these KG embeddings treat triples independently and thus fail to cover the complex and hidden information that is inherently implicit in the local neighborhood surrounding a triple. To this effect, our paper proposes a novel attention based feature embedding that captures both entity and relation features in any given entity’s neighborhood. Additionally, we also encapsulate relation clusters and multihop relations in our model. Our empirical study offers insights into the efficacy of our attention based model and we show marked performance gains in comparison to state of the art methods on all datasets.
Tasks	Knowledge Base Completion, Knowledge Graph Embeddings, Knowledge Graphs, Link Prediction
Published	2019-06-04
URL	https://arxiv.org/abs/1906.01195v1
PDF	https://arxiv.org/pdf/1906.01195v1.pdf
PWC	https://paperswithcode.com/paper/learning-attention-based-embeddings-for
Repo	https://github.com/deepakn97/relationPrediction
Framework	pytorch

Active Learning with Gaussian Processes for High Throughput Phenotyping


Title	Active Learning with Gaussian Processes for High Throughput Phenotyping
Authors	Sumit Kumar, Wenhao Luo, George Kantor, Katia Sycara
Abstract	A looming question that must be solved before robotic plant phenotyping capabilities can have significant impact to crop improvement programs is scalability. High Throughput Phenotyping (HTP) uses robotic technologies to analyze crops in order to determine species with favorable traits, however, the current practices rely on exhaustive coverage and data collection from the entire crop field being monitored under the breeding experiment. This works well in relatively small agricultural fields but can not be scaled to the larger ones, thus limiting the progress of genetics research. In this work, we propose an active learning algorithm to enable an autonomous system to collect the most informative samples in order to accurately learn the distribution of phenotypes in the field with the help of a Gaussian Process model. We demonstrate the superior performance of our proposed algorithm compared to the current practices on sorghum phenotype data collection.
Tasks	Active Learning, Gaussian Processes
Published	2019-01-21
URL	http://arxiv.org/abs/1901.06803v1
PDF	http://arxiv.org/pdf/1901.06803v1.pdf
PWC	https://paperswithcode.com/paper/active-learning-with-gaussian-processes-for
Repo	https://github.com/sumitsk/algp
Framework	pytorch

HumanMeshNet: Polygonal Mesh Recovery of Humans


Title	HumanMeshNet: Polygonal Mesh Recovery of Humans
Authors	Abbhinav Venkat, Chaitanya Patel, Yudhik Agrawal, Avinash Sharma
Abstract	3D Human Body Reconstruction from a monocular image is an important problem in computer vision with applications in virtual and augmented reality platforms, animation industry, en-commerce domain, etc. While several of the existing works formulate it as a volumetric or parametric learning with complex and indirect reliance on re-projections of the mesh, we would like to focus on implicitly learning the mesh representation. To that end, we propose a novel model, HumanMeshNet, that regresses a template mesh’s vertices, as well as receives a regularization by the 3D skeletal locations in a multi-branch, multi-task setup. The image to mesh vertex regression is further regularized by the neighborhood constraint imposed by mesh topology ensuring smooth surface reconstruction. The proposed paradigm can theoretically learn local surface deformations induced by body shape variations and can therefore learn high-resolution meshes going ahead. We show comparable performance with SoA (in terms of surface and joint error) with far lesser computational complexity, modeling cost and therefore real-time reconstructions on three publicly available datasets. We also show the generalizability of the proposed paradigm for a similar task of predicting hand mesh models. Given these initial results, we would like to exploit the mesh topology in an explicit manner going ahead.
Tasks
Published	2019-08-19
URL	https://arxiv.org/abs/1908.06544v1
PDF	https://arxiv.org/pdf/1908.06544v1.pdf
PWC	https://paperswithcode.com/paper/humanmeshnet-polygonal-mesh-recovery-of
Repo	https://github.com/chaitanya100100/HumanMeshNet
Framework	pytorch

Single Point Transductive Prediction


Title	Single Point Transductive Prediction
Authors	Nilesh Tripuraneni, Lester Mackey
Abstract	Standard methods in supervised learning separate training and prediction: the model is fit independently of any test points it may encounter. However, can knowledge of the next test point $\mathbf{x}{\star}$ be exploited to improve prediction accuracy? We address this question in the context of linear prediction, showing how techniques from semi-parametric inference can be used transductively to combat regularization bias. We first lower bound the $\mathbf{x}{\star}$ prediction error of ridge regression and the Lasso, showing that they must incur significant bias in certain test directions. We then provide non-asymptotic upper bounds on the $\mathbf{x}_{\star}$ prediction error of two transductive prediction rules. We conclude by showing the efficacy of our methods on both synthetic and real data, highlighting the improvements single point transductive prediction can provide in settings with distribution shift.
Tasks
Published	2019-08-06
URL	https://arxiv.org/abs/1908.02341v3
PDF	https://arxiv.org/pdf/1908.02341v3.pdf
PWC	https://paperswithcode.com/paper/debiasing-linear-prediction
Repo	https://github.com/nileshtrip/DebLinPredCode
Framework	none

Analyzing Learned Molecular Representations for Property Prediction


Title	Analyzing Learned Molecular Representations for Property Prediction
Authors	Kevin Yang, Kyle Swanson, Wengong Jin, Connor Coley, Philipp Eiden, Hua Gao, Angel Guzman-Perez, Timothy Hopper, Brian Kelley, Miriam Mathea, Andrew Palmer, Volker Settels, Tommi Jaakkola, Klavs Jensen, Regina Barzilay
Abstract	Advancements in neural machinery have led to a wide range of algorithmic solutions for molecular property prediction. Two classes of models in particular have yielded promising results: neural networks applied to computed molecular fingerprints or expert-crafted descriptors, and graph convolutional neural networks that construct a learned molecular representation by operating on the graph structure of the molecule. However, recent literature has yet to clearly determine which of these two methods is superior when generalizing to new chemical space. Furthermore, prior research has rarely examined these new models in industry research settings in comparison to existing employed models. In this paper, we benchmark models extensively on 19 public and 16 proprietary industrial datasets spanning a wide variety of chemical endpoints. In addition, we introduce a graph convolutional model that consistently matches or outperforms models using fixed molecular descriptors as well as previous graph neural architectures on both public and proprietary datasets. Our empirical findings indicate that while approaches based on these representations have yet to reach the level of experimental reproducibility, our proposed model nevertheless offers significant improvements over models currently used in industrial workflows.
Tasks	Molecular Property Prediction
Published	2019-04-02
URL	https://arxiv.org/abs/1904.01561v5
PDF	https://arxiv.org/pdf/1904.01561v5.pdf
PWC	https://paperswithcode.com/paper/are-learned-molecular-representations-ready
Repo	https://github.com/swansonk14/chemprop
Framework	pytorch

GMLS-Nets: A framework for learning from unstructured data


Title	GMLS-Nets: A framework for learning from unstructured data
Authors	Nathaniel Trask, Ravi G. Patel, Ben J. Gross, Paul J. Atzberger
Abstract	Data fields sampled on irregularly spaced points arise in many applications in the sciences and engineering. For regular grids, Convolutional Neural Networks (CNNs) have been successfully used to gaining benefits from weight sharing and invariances. We generalize CNNs by introducing methods for data on unstructured point clouds based on Generalized Moving Least Squares (GMLS). GMLS is a non-parametric technique for estimating linear bounded functionals from scattered data, and has recently been used in the literature for solving partial differential equations. By parameterizing the GMLS estimator, we obtain learning methods for operators with unstructured stencils. In GMLS-Nets the necessary calculations are local, readily parallelizable, and the estimator is supported by a rigorous approximation theory. We show how the framework may be used for unstructured physical data sets to perform functional regression to identify associated differential operators and to regress quantities of interest. The results suggest the architectures to be an attractive foundation for data-driven model development in scientific machine learning applications.
Tasks
Published	2019-09-07
URL	https://arxiv.org/abs/1909.05371v2
PDF	https://arxiv.org/pdf/1909.05371v2.pdf
PWC	https://paperswithcode.com/paper/gmls-nets-a-framework-for-learning-from
Repo	https://github.com/rgp62/gmls-nets
Framework	tf

Adversarially Robust Distillation


Title	Adversarially Robust Distillation
Authors	Micah Goldblum, Liam Fowl, Soheil Feizi, Tom Goldstein
Abstract	Knowledge distillation is effective for producing small, high-performance neural networks for classification, but these small networks are vulnerable to adversarial attacks. This paper studies how adversarial robustness transfers from teacher to student during knowledge distillation. We find that a large amount of robustness may be inherited by the student even when distilled on only clean images. Second, we introduce Adversarially Robust Distillation (ARD) for distilling robustness onto student networks. In addition to producing small models with high test accuracy like conventional distillation, ARD also passes the superior robustness of large networks onto the student. In our experiments, we find that ARD student models decisively outperform adversarially trained networks of identical architecture in terms of robust accuracy, surpassing state-of-the-art methods on standard robustness benchmarks. Finally, we adapt recent fast adversarial training methods to ARD for accelerated robust distillation.
Tasks
Published	2019-05-23
URL	https://arxiv.org/abs/1905.09747v2
PDF	https://arxiv.org/pdf/1905.09747v2.pdf
PWC	https://paperswithcode.com/paper/190509747
Repo	https://github.com/goldblum/AdversariallyRobustDistillation
Framework	pytorch

Deep Video Inpainting


Title	Deep Video Inpainting
Authors	Dahun Kim, Sanghyun Woo, Joon-Young Lee, In So Kweon
Abstract	Video inpainting aims to fill spatio-temporal holes with plausible content in a video. Despite tremendous progress of deep neural networks for image inpainting, it is challenging to extend these methods to the video domain due to the additional time dimension. In this work, we propose a novel deep network architecture for fast video inpainting. Built upon an image-based encoder-decoder model, our framework is designed to collect and refine information from neighbor frames and synthesize still-unknown regions. At the same time, the output is enforced to be temporally consistent by a recurrent feedback and a temporal memory module. Compared with the state-of-the-art image inpainting algorithm, our method produces videos that are much more semantically correct and temporally smooth. In contrast to the prior video completion method which relies on time-consuming optimization, our method runs in near real-time while generating competitive video results. Finally, we applied our framework to video retargeting task, and obtain visually pleasing results.
Tasks	Image Inpainting, Video Denoising, Video Inpainting, Video-to-Video Synthesis
Published	2019-05-05
URL	https://arxiv.org/abs/1905.01639v1
PDF	https://arxiv.org/pdf/1905.01639v1.pdf
PWC	https://paperswithcode.com/paper/deep-video-inpainting
Repo	https://github.com/mcahny/Deep-Video-Inpainting
Framework	pytorch

Twin Auxiliary Classifiers GAN


Title	Twin Auxiliary Classifiers GAN
Authors	Mingming Gong, Yanwu Xu, Chunyuan Li, Kun Zhang, Kayhan Batmanghelich
Abstract	Conditional generative models enjoy remarkable progress over the past few years. One of the popular conditional models is Auxiliary Classifier GAN (AC-GAN), which generates highly discriminative images by extending the loss function of GAN with an auxiliary classifier. However, the diversity of the generated samples by AC-GAN tends to decrease as the number of classes increases, hence limiting its power on large-scale data. In this paper, we identify the source of the low diversity issue theoretically and propose a practical solution to solve the problem. We show that the auxiliary classifier in AC-GAN imposes perfect separability, which is disadvantageous when the supports of the class distributions have significant overlap. To address the issue, we propose Twin Auxiliary Classifiers Generative Adversarial Net (TAC-GAN) that further benefits from a new player that interacts with other players (the generator and the discriminator) in GAN. Theoretically, we demonstrate that TAC-GAN can effectively minimize the divergence between the generated and real-data distributions. Extensive experimental results show that our TAC-GAN can successfully replicate the true data distributions on simulated data, and significantly improves the diversity of class-conditional image generation on real datasets.
Tasks	Conditional Image Generation, Image Generation
Published	2019-07-05
URL	https://arxiv.org/abs/1907.02690v4
PDF	https://arxiv.org/pdf/1907.02690v4.pdf
PWC	https://paperswithcode.com/paper/twin-auxiliary-classifiers-gan
Repo	https://github.com/batmanlab/twin_ac
Framework	pytorch

TorchGAN: A Flexible Framework for GAN Training and Evaluation


Title	TorchGAN: A Flexible Framework for GAN Training and Evaluation
Authors	Avik Pal, Aniket Das
Abstract	TorchGAN is a PyTorch based framework for writing succinct and comprehensible code for training and evaluation of Generative Adversarial Networks. The framework’s modular design allows effortless customization of the model architecture, loss functions, training paradigms, and evaluation metrics. The key features of TorchGAN are its extensibility, built-in support for a large number of popular models, losses and evaluation metrics, and zero overhead compared to vanilla PyTorch. By using the framework to implement several popular GAN models, we demonstrate its extensibility and ease of use. We also benchmark the training time of our framework for said models against the corresponding baseline PyTorch implementations and observe that TorchGAN’s features bear almost zero overhead.
Tasks	Conditional Image Generation, Image Generation
Published	2019-09-08
URL	https://arxiv.org/abs/1909.03410v1
PDF	https://arxiv.org/pdf/1909.03410v1.pdf
PWC	https://paperswithcode.com/paper/torchgan-a-flexible-framework-for-gan
Repo	https://github.com/torchgan/torchgan
Framework	pytorch