Paper Group ANR 9
Novel Machine Learning Algorithms for Centrality and Cliques Detection in Youtube Social Networks. Compositional Languages Emerge in a Neural Iterated Learning Model. Self-supervised Single-view 3D Reconstruction via Semantic Consistency. STD-Net: Structure-preserving and Topology-adaptive Deformation Network for 3D Reconstruction from a Single Ima …
Novel Machine Learning Algorithms for Centrality and Cliques Detection in Youtube Social Networks
| Title | Novel Machine Learning Algorithms for Centrality and Cliques Detection in Youtube Social Networks |
| Authors | Craigory Coppola, Heba Elgazzar |
| Abstract | The goal of this research project is to analyze the dynamics of social networks using machine learning techniques to locate maximal cliques and to find clusters for the purpose of identifying a target demographic. Unsupervised machine learning techniques are designed and implemented in this project to analyze a dataset from YouTube to discover communities in the social network and find central nodes. Different clustering algorithms are implemented and applied to the YouTube dataset. The well-known Bron-Kerbosch algorithm is used effectively in this research to find maximal cliques. The results obtained from this research could be used for advertising purposes and for building smart recommendation systems. All algorithms were implemented using Python programming language. The experimental results show that we were able to successfully find central nodes through clique-centrality and degree centrality. By utilizing clique detection algorithms, the research shown how machine learning algorithms can detect close knit groups within a larger network. |
| Tasks | Recommendation Systems |
| Published | 2020-02-10 |
| URL | https://arxiv.org/abs/2002.03893v1 |
| https://arxiv.org/pdf/2002.03893v1.pdf | |
| PWC | https://paperswithcode.com/paper/novel-machine-learning-algorithms-for |
| Repo | |
| Framework | |
Compositional Languages Emerge in a Neural Iterated Learning Model
| Title | Compositional Languages Emerge in a Neural Iterated Learning Model |
| Authors | Yi Ren, Shangmin Guo, Matthieu Labeau, Shay B. Cohen, Simon Kirby |
| Abstract | The principle of compositionality, which enables natural language to represent complex concepts via a structured combination of simpler ones, allows us to convey an open-ended set of messages using a limited vocabulary. If compositionality is indeed a natural property of language, we may expect it to appear in communication protocols that are created by neural agents in language games. In this paper, we propose an effective neural iterated learning (NIL) algorithm that, when applied to interacting neural agents, facilitates the emergence of a more structured type of language. Indeed, these languages provide learning speed advantages to neural agents during training, which can be incrementally amplified via NIL. We provide a probabilistic model of NIL and an explanation of why the advantage of compositional language exist. Our experiments confirm our analysis, and also demonstrate that the emerged languages largely improve the generalizing power of the neural agent communication. |
| Tasks | |
| Published | 2020-02-04 |
| URL | https://arxiv.org/abs/2002.01365v2 |
| https://arxiv.org/pdf/2002.01365v2.pdf | |
| PWC | https://paperswithcode.com/paper/compositional-languages-emerge-in-a-neural-1 |
| Repo | |
| Framework | |
Self-supervised Single-view 3D Reconstruction via Semantic Consistency
| Title | Self-supervised Single-view 3D Reconstruction via Semantic Consistency |
| Authors | Xueting Li, Sifei Liu, Kihwan Kim, Shalini De Mello, Varun Jampani, Ming-Hsuan Yang, Jan Kautz |
| Abstract | We learn a self-supervised, single-view 3D reconstruction model that predicts the 3D mesh shape, texture and camera pose of a target object with a collection of 2D images and silhouettes. The proposed method does not necessitate 3D supervision, manually annotated keypoints, multi-view images of an object or a prior 3D template. The key insight of our work is that objects can be represented as a collection of deformable parts, and each part is semantically coherent across different instances of the same category (e.g., wings on birds and wheels on cars). Therefore, by leveraging self-supervisedly learned part segmentation of a large collection of category-specific images, we can effectively enforce semantic consistency between the reconstructed meshes and the original images. This significantly reduces ambiguities during joint prediction of shape and camera pose of an object, along with texture. To the best of our knowledge, we are the first to try and solve the single-view reconstruction problem without a category-specific template mesh or semantic keypoints. Thus our model can easily generalize to various object categories without such labels, e.g., horses, penguins, etc. Through a variety of experiments on several categories of deformable and rigid objects, we demonstrate that our unsupervised method performs comparably if not better than existing category-specific reconstruction methods learned with supervision. |
| Tasks | 3D Reconstruction, Single-View 3D Reconstruction |
| Published | 2020-03-13 |
| URL | https://arxiv.org/abs/2003.06473v1 |
| https://arxiv.org/pdf/2003.06473v1.pdf | |
| PWC | https://paperswithcode.com/paper/self-supervised-single-view-3d-reconstruction |
| Repo | |
| Framework | |
STD-Net: Structure-preserving and Topology-adaptive Deformation Network for 3D Reconstruction from a Single Image
| Title | STD-Net: Structure-preserving and Topology-adaptive Deformation Network for 3D Reconstruction from a Single Image |
| Authors | Aihua Mao, Canglan Dai, Lin Gao, Ying He, Yong-jin Liu |
| Abstract | 3D reconstruction from a single view image is a long-standing prob-lem in computer vision. Various methods based on different shape representations(such as point cloud or volumetric representations) have been proposed. However,the 3D shape reconstruction with fine details and complex structures are still chal-lenging and have not yet be solved. Thanks to the recent advance of the deepshape representations, it becomes promising to learn the structure and detail rep-resentation using deep neural networks. In this paper, we propose a novel methodcalled STD-Net to reconstruct the 3D models utilizing the mesh representationthat is well suitable for characterizing complex structure and geometry details.To reconstruct complex 3D mesh models with fine details, our method consists of(1) an auto-encoder network for recovering the structure of an object with bound-ing box representation from a single image, (2) a topology-adaptive graph CNNfor updating vertex position for meshes of complex topology, and (3) an unifiedmesh deformation block that deforms the structural boxes into structure-awaremeshed models. Experimental results on the images from ShapeNet show that ourproposed STD-Net has better performance than other state-of-the-art methods onreconstructing 3D objects with complex structures and fine geometric details. |
| Tasks | 3D Reconstruction |
| Published | 2020-03-07 |
| URL | https://arxiv.org/abs/2003.03551v1 |
| https://arxiv.org/pdf/2003.03551v1.pdf | |
| PWC | https://paperswithcode.com/paper/std-net-structure-preserving-and-topology |
| Repo | |
| Framework | |
Improved Algorithms for Conservative Exploration in Bandits
| Title | Improved Algorithms for Conservative Exploration in Bandits |
| Authors | Evrard Garcelon, Mohammad Ghavamzadeh, Alessandro Lazaric, Matteo Pirotta |
| Abstract | In many fields such as digital marketing, healthcare, finance, and robotics, it is common to have a well-tested and reliable baseline policy running in production (e.g., a recommender system). Nonetheless, the baseline policy is often suboptimal. In this case, it is desirable to deploy online learning algorithms (e.g., a multi-armed bandit algorithm) that interact with the system to learn a better/optimal policy under the constraint that during the learning process the performance is almost never worse than the performance of the baseline itself. In this paper, we study the conservative learning problem in the contextual linear bandit setting and introduce a novel algorithm, the Conservative Constrained LinUCB (CLUCB2). We derive regret bounds for CLUCB2 that match existing results and empirically show that it outperforms state-of-the-art conservative bandit algorithms in a number of synthetic and real-world problems. Finally, we consider a more realistic constraint where the performance is verified only at predefined checkpoints (instead of at every step) and show how this relaxed constraint favorably impacts the regret and empirical performance of CLUCB2. |
| Tasks | Recommendation Systems |
| Published | 2020-02-08 |
| URL | https://arxiv.org/abs/2002.03221v1 |
| https://arxiv.org/pdf/2002.03221v1.pdf | |
| PWC | https://paperswithcode.com/paper/improved-algorithms-for-conservative |
| Repo | |
| Framework | |
Graph Convolution Machine for Context-aware Recommender System
| Title | Graph Convolution Machine for Context-aware Recommender System |
| Authors | Jiancan Wu, Xiangnan He, Xiang Wang, Qifan Wang, Weijian Chen, Jianxun Lian, Xing Xie, Yongdong Zhang |
| Abstract | The latest advance in recommendation shows that better user and item representations can be learned via performing graph convolutions on the user-item interaction graph. However, such finding is mostly restricted to the collaborative filtering (CF) scenario, where the interaction contexts are not available. In this work, we extend the advantages of graph convolutions to context-aware recommender system (CARS, which represents a generic type of models that can handle various side information). We propose Graph Convolution Machine (GCM), an end-to-end framework that consists of three components: an encoder, graph convolution (GC) layers, and a decoder. The encoder projects users, items, and contexts into embedding vectors, which are passed to the GC layers that refine user and item embeddings with context-aware graph convolutions on user-item graph. The decoder digests the refined embeddings to output the prediction score by considering the interactions among user, item, and context embeddings. We conduct experiments on three real-world datasets from Yelp, validating the effectiveness of GCM and the benefits of performing graph convolutions for CARS. |
| Tasks | Recommendation Systems |
| Published | 2020-01-30 |
| URL | https://arxiv.org/abs/2001.11402v1 |
| https://arxiv.org/pdf/2001.11402v1.pdf | |
| PWC | https://paperswithcode.com/paper/graph-convolution-machine-for-context-aware |
| Repo | |
| Framework | |
Hybrid Classification and Reasoning for Image-based Constraint Solving
| Title | Hybrid Classification and Reasoning for Image-based Constraint Solving |
| Authors | Maxime Mulamba, Jayanta Mandi, Rocsildes Canoy, Tias Guns |
| Abstract | There is an increased interest in solving complex constrained problems where part of the input is not given as facts but received as raw sensor data such as images or speech. We will use “visual sudoku” as a prototype problem, where the given cell digits are handwritten and provided as an image thereof. In this case, one first has to train and use a classifier to label the images, so that the labels can be used for solving the problem. In this paper, we explore the hybridization of classifying the images with the reasoning of a constraint solver. We show that pure constraint reasoning on predictions does not give satisfactory results. Instead, we explore the possibilities of a tighter integration, by exposing the probabilistic estimates of the classifier to the constraint solver. This allows joint inference on these probabilistic estimates, where we use the solver to find the maximum likelihood solution. We explore the trade-off between the power of the classifier and the power of the constraint reasoning, as well as further integration through the additional use of structural knowledge. Furthermore, we investigate the effect of calibration of the probabilistic estimates on the reasoning. Our results show that such hybrid approaches vastly outperform a separate approach, which encourages a further integration of prediction (probabilities) and constraint solving. |
| Tasks | Calibration |
| Published | 2020-03-24 |
| URL | https://arxiv.org/abs/2003.11001v1 |
| https://arxiv.org/pdf/2003.11001v1.pdf | |
| PWC | https://paperswithcode.com/paper/hybrid-classification-and-reasoning-for-image |
| Repo | |
| Framework | |
Stacked Adversarial Network for Zero-Shot Sketch based Image Retrieval
| Title | Stacked Adversarial Network for Zero-Shot Sketch based Image Retrieval |
| Authors | Anubha Pandey, Ashish Mishra, Vinay Kumar Verma, Anurag Mittal, Hema A. Murthy |
| Abstract | Conventional approaches to Sketch-Based Image Retrieval (SBIR) assume that the data of all the classes are available during training. The assumption may not always be practical since the data of a few classes may be unavailable, or the classes may not appear at the time of training. Zero-Shot Sketch-Based Image Retrieval (ZS-SBIR) relaxes this constraint and allows the algorithm to handle previously unseen classes during the test. This paper proposes a generative approach based on the Stacked Adversarial Network (SAN) and the advantage of Siamese Network (SN) for ZS-SBIR. While SAN generates a high-quality sample, SN learns a better distance metric compared to that of the nearest neighbor search. The capability of the generative model to synthesize image features based on the sketch reduces the SBIR problem to that of an image-to-image retrieval problem. We evaluate the efficacy of our proposed approach on TU-Berlin, and Sketchy database in both standard ZSL and generalized ZSL setting. The proposed method yields a significant improvement in standard ZSL as well as in a more challenging generalized ZSL setting (GZSL) for SBIR. |
| Tasks | Image Retrieval, Sketch-Based Image Retrieval |
| Published | 2020-01-18 |
| URL | https://arxiv.org/abs/2001.06657v1 |
| https://arxiv.org/pdf/2001.06657v1.pdf | |
| PWC | https://paperswithcode.com/paper/stacked-adversarial-network-for-zero-shot |
| Repo | |
| Framework | |
Globally optimal point set registration by joint symmetry plane fitting
| Title | Globally optimal point set registration by joint symmetry plane fitting |
| Authors | Lan Hu, Haomin Shi, Laurent Kneip |
| Abstract | The present work proposes a solution to the challenging problem of registering two partial point sets of the same object with very limited overlap. We leverage the fact that most objects found in man-made environments contain a plane of symmetry. By reflecting the points of each set with respect to the plane of symmetry, we can largely increase the overlap between the sets and therefore boost the registration process. However, prior knowledge about the plane of symmetry is generally unavailable or at least very hard to find, especially with limited partial views, and finding this plane could strongly benefit from a prior alignment of the partial point sets. We solve this chicken-and-egg problem by jointly optimizing the relative pose and symmetry plane parameters, and notably do so under global optimality by employing the branch-and-bound (BnB) paradigm. Our results demonstrate a great improvement over the current state-of-the-art in globally optimal point set registration for common objects. We furthermore show an interesting application of our method to dense 3D reconstruction of scenes with repetitive objects. |
| Tasks | 3D Reconstruction |
| Published | 2020-02-19 |
| URL | https://arxiv.org/abs/2002.07988v1 |
| https://arxiv.org/pdf/2002.07988v1.pdf | |
| PWC | https://paperswithcode.com/paper/globally-optimal-point-set-registration-by |
| Repo | |
| Framework | |
Towards a predictive spatio-temporal representation of brain data
| Title | Towards a predictive spatio-temporal representation of brain data |
| Authors | Tiago Azevedo, Luca Passamonti, Pietro Liò, Nicola Toschi |
| Abstract | The characterisation of the brain as a “connectome”, in which the connections are represented by correlational values across timeseries and as summary measures derived from graph theory analyses, has been very popular in the last years. However, although this representation has advanced our understanding of the brain function, it may represent an oversimplified model. This is because the typical fMRI datasets are constituted by complex and highly heterogeneous timeseries that vary across space (i.e., location of brain regions). We compare various modelling techniques from deep learning and geometric deep learning to pave the way for future research in effectively leveraging the rich spatial and temporal domains of typical fMRI datasets, as well as of other similar datasets. As a proof-of-concept, we compare our approaches in the homogeneous and publicly available Human Connectome Project (HCP) dataset on a supervised binary classification task. We hope that our methodological advances relative to previous “connectomic” measures can ultimately be clinically and computationally relevant by leading to a more nuanced understanding of the brain dynamics in health and disease. Such understanding of the brain can fundamentally reduce the constant specialised clinical expertise in order to accurately understand brain variability. |
| Tasks | |
| Published | 2020-02-29 |
| URL | https://arxiv.org/abs/2003.03290v1 |
| https://arxiv.org/pdf/2003.03290v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-a-predictive-spatio-temporal |
| Repo | |
| Framework | |
How to Answer Why – Evaluating the Explanations of AI Through Mental Model Analysis
| Title | How to Answer Why – Evaluating the Explanations of AI Through Mental Model Analysis |
| Authors | Tim Schrills, Thomas Franke |
| Abstract | To achieve optimal human-system integration in the context of user-AI interaction it is important that users develop a valid representation of how AI works. In most of the everyday interaction with technical systems users construct mental models (i.e., an abstraction of the anticipated mechanisms a system uses to perform a given task). If no explicit explanations are provided by a system (e.g. by a self-explaining AI) or other sources (e.g. an instructor), the mental model is typically formed based on experiences, i.e. the observations of the user during the interaction. The congruence of this mental model and the actual systems functioning is vital, as it is used for assumptions, predictions and consequently for decisions regarding system use. A key question for human-centered AI research is therefore how to validly survey users’ mental models. The objective of the present research is to identify suitable elicitation methods for mental model analysis. We evaluated whether mental models are suitable as an empirical research method. Additionally, methods of cognitive tutoring are integrated. We propose an exemplary method to evaluate explainable AI approaches in a human-centered way. |
| Tasks | |
| Published | 2020-01-11 |
| URL | https://arxiv.org/abs/2002.02526v1 |
| https://arxiv.org/pdf/2002.02526v1.pdf | |
| PWC | https://paperswithcode.com/paper/how-to-answer-why-evaluating-the-explanations |
| Repo | |
| Framework | |
Performance Comparison of Crowdworkers and NLP Tools onNamed-Entity Recognition and Sentiment Analysis of Political Tweets
| Title | Performance Comparison of Crowdworkers and NLP Tools onNamed-Entity Recognition and Sentiment Analysis of Political Tweets |
| Authors | Mona Jalal, Kate K. Mays, Lei Guo, Margrit Betke |
| Abstract | We report results of a comparison of the accuracy of crowdworkers and seven NaturalLanguage Processing (NLP) toolkits in solving two important NLP tasks, named-entity recognition (NER) and entity-level sentiment(ELS) analysis. We here focus on a challenging dataset, 1,000 political tweets that were collected during the U.S. presidential primary election in February 2016. Each tweet refers to at least one of four presidential candidates,i.e., four named entities. The groundtruth, established by experts in political communication, has entity-level sentiment information for each candidate mentioned in the tweet. We tested several commercial and open-source tools. Our experiments show that, for our dataset of political tweets, the most accurate NER system, Google Cloud NL, performed almost on par with crowdworkers, but the most accurate ELS analysis system, TensiStrength, did not match the accuracy of crowdworkers by a large margin of more than 30 percent points. |
| Tasks | Named Entity Recognition, Sentiment Analysis |
| Published | 2020-02-11 |
| URL | https://arxiv.org/abs/2002.04181v1 |
| https://arxiv.org/pdf/2002.04181v1.pdf | |
| PWC | https://paperswithcode.com/paper/performance-comparison-of-crowdworkers-and |
| Repo | |
| Framework | |
Real-time Kinematic Ground Truth for the Oxford RobotCar Dataset
| Title | Real-time Kinematic Ground Truth for the Oxford RobotCar Dataset |
| Authors | Will Maddern, Geoffrey Pascoe, Matthew Gadd, Dan Barnes, Brian Yeomans, Paul Newman |
| Abstract | We describe the release of reference data towards a challenging long-term localisation and mapping benchmark based on the large-scale Oxford RobotCar Dataset. The release includes 72 traversals of a route through Oxford, UK, gathered in all illumination, weather and traffic conditions, and is representative of the conditions an autonomous vehicle would be expected to operate reliably in. Using post-processed raw GPS, IMU, and static GNSS base station recordings, we have produced a globally-consistent centimetre-accurate ground truth for the entire year-long duration of the dataset. Coupled with a planned online benchmarking service, we hope to enable quantitative evaluation and comparison of different localisation and mapping approaches focusing on long-term autonomy for road vehicles in urban environments challenged by changing weather. |
| Tasks | |
| Published | 2020-02-24 |
| URL | https://arxiv.org/abs/2002.10152v1 |
| https://arxiv.org/pdf/2002.10152v1.pdf | |
| PWC | https://paperswithcode.com/paper/real-time-kinematic-ground-truth-for-the |
| Repo | |
| Framework | |
Solving Missing-Annotation Object Detection with Background Recalibration Loss
| Title | Solving Missing-Annotation Object Detection with Background Recalibration Loss |
| Authors | Han Zhang, Fangyi Chen, Zhiqiang Shen, Qiqi Hao, Chenchen Zhu, Marios Savvides |
| Abstract | This paper focuses on a novel and challenging detection scenario: A majority of true objects/instances is unlabeled in the datasets, so these missing-labeled areas will be regarded as the background during training. Previous art on this problem has proposed to use soft sampling to re-weight the gradients of RoIs based on the overlaps with positive instances, while their method is mainly based on the two-stage detector (i.e. Faster RCNN) which is more robust and friendly for the missing label scenario. In this paper, we introduce a superior solution called Background Recalibration Loss (BRL) that can automatically re-calibrate the loss signals according to the pre-defined IoU threshold and input image. Our design is built on the one-stage detector which is faster and lighter. Inspired by the Focal Loss formulation, we make several significant modifications to fit on the missing-annotation circumstance. We conduct extensive experiments on the curated PASCAL VOC and MS COCO datasets. The results demonstrate that our proposed method outperforms the baseline and other state-of-the-arts by a large margin. |
| Tasks | Object Detection |
| Published | 2020-02-12 |
| URL | https://arxiv.org/abs/2002.05274v1 |
| https://arxiv.org/pdf/2002.05274v1.pdf | |
| PWC | https://paperswithcode.com/paper/solving-missing-annotation-object-detection |
| Repo | |
| Framework | |
Variance Reduction with Sparse Gradients
| Title | Variance Reduction with Sparse Gradients |
| Authors | Melih Elibol, Lihua Lei, Michael I. Jordan |
| Abstract | Variance reduction methods such as SVRG and SpiderBoost use a mixture of large and small batch gradients to reduce the variance of stochastic gradients. Compared to SGD, these methods require at least double the number of operations per update to model parameters. To reduce the computational cost of these methods, we introduce a new sparsity operator: The random-top-k operator. Our operator reduces computational complexity by estimating gradient sparsity exhibited in a variety of applications by combining the top-k operator and the randomized coordinate descent operator. With this operator, large batch gradients offer an extra benefit beyond variance reduction: A reliable estimate of gradient sparsity. Theoretically, our algorithm is at least as good as the best algorithm (SpiderBoost), and further excels in performance whenever the random-top-k operator captures gradient sparsity. Empirically, our algorithm consistently outperforms SpiderBoost using various models on various tasks including image classification, natural language processing, and sparse matrix factorization. We also provide empirical evidence to support the intuition behind our algorithm via a simple gradient entropy computation, which serves to quantify gradient sparsity at every iteration. |
| Tasks | Image Classification |
| Published | 2020-01-27 |
| URL | https://arxiv.org/abs/2001.09623v1 |
| https://arxiv.org/pdf/2001.09623v1.pdf | |
| PWC | https://paperswithcode.com/paper/variance-reduction-with-sparse-gradients-1 |
| Repo | |
| Framework | |
