Paper Group ANR 489
Upper, Middle and Lower Region Learning for Facial Action Unit Detection. The impossibility of low rank representations for triangle-rich complex networks. Multi-faceted Trust-based Collaborative Filtering. Linearly Constrained Gaussian Processes with Boundary Conditions. Developing a Recommendation Benchmark for MLPerf Training and Inference. Tech …
Upper, Middle and Lower Region Learning for Facial Action Unit Detection
| Title | Upper, Middle and Lower Region Learning for Facial Action Unit Detection |
| Authors | Yao Xia |
| Abstract | Facial action units (AUs) detection is fundamental to facial expression analysis. As AU occurs only in a small area of the face, region-based learning has been widely recognized useful for AU detection. Most region-based studies focus on a small region where the AU occurs. Focusing on a specific region helps eliminate the influence of identity, but bringing a risk for losing information. It is challenging to find balance. In this study, I propose a simple strategy. I divide the face into three broad regions, upper, middle, and lower region, and group AUs based on where it occurs. I propose a new end-to-end deep learning framework named three regions based attention network (TRA-Net). After extracting the global feature, TRA-Net uses a hard attention module to extract three feature maps, each of which contains only a specific region. Each region-specific feature map is fed to an independent branch. For each branch, three continuous soft attention modules are used to extract higher-level features for final AU detection. In the DISFA dataset, this model achieves the highest F1 scores for the detection of AU1, AU2, and AU4, and produces the highest accuracy in comparison with the state-of-the-art methods. |
| Tasks | Action Unit Detection, Facial Action Unit Detection |
| Published | 2020-02-10 |
| URL | https://arxiv.org/abs/2002.04023v2 |
| https://arxiv.org/pdf/2002.04023v2.pdf | |
| PWC | https://paperswithcode.com/paper/upper-middle-and-lower-region-learning-for |
| Repo | |
| Framework | |
The impossibility of low rank representations for triangle-rich complex networks
| Title | The impossibility of low rank representations for triangle-rich complex networks |
| Authors | C. Seshadhri, Aneesh Sharma, Andrew Stolman, Ashish Goel |
| Abstract | The study of complex networks is a significant development in modern science, and has enriched the social sciences, biology, physics, and computer science. Models and algorithms for such networks are pervasive in our society, and impact human behavior via social networks, search engines, and recommender systems to name a few. A widely used algorithmic technique for modeling such complex networks is to construct a low-dimensional Euclidean embedding of the vertices of the network, where proximity of vertices is interpreted as the likelihood of an edge. Contrary to the common view, we argue that such graph embeddings do not}capture salient properties of complex networks. The two properties we focus on are low degree and large clustering coefficients, which have been widely established to be empirically true for real-world networks. We mathematically prove that any embedding (that uses dot products to measure similarity) that can successfully create these two properties must have rank nearly linear in the number of vertices. Among other implications, this establishes that popular embedding techniques such as Singular Value Decomposition and node2vec fail to capture significant structural aspects of real-world complex networks. Furthermore, we empirically study a number of different embedding techniques based on dot product, and show that they all fail to capture the triangle structure. |
| Tasks | Recommendation Systems |
| Published | 2020-03-27 |
| URL | https://arxiv.org/abs/2003.12635v1 |
| https://arxiv.org/pdf/2003.12635v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-impossibility-of-low-rank-representations |
| Repo | |
| Framework | |
Multi-faceted Trust-based Collaborative Filtering
| Title | Multi-faceted Trust-based Collaborative Filtering |
| Authors | Noemi Mauro, Liliana Ardissono, Zhongli Filippo Hu |
| Abstract | Many collaborative recommender systems leverage social correlation theories to improve suggestion performance. However, they focus on explicit relations between users and they leave out other types of information that can contribute to determine users’ global reputation; e.g., public recognition of reviewers’ quality. We are interested in understanding if and when these additional types of feedback improve Top-N recommendation. For this purpose, we propose a multi-faceted trust model to integrate local trust, represented by social links, with various types of global trust evidence provided by social networks. We aim at identifying general classes of data in order to make our model applicable to different case studies. Then, we test the model by applying it to a variant of User-to-User Collaborative filtering (U2UCF) which supports the fusion of rating similarity, local trust derived from social relations, and multi-faceted reputation for rating prediction. We test our model on two datasets: the Yelp one publishes generic friend relations between users but provides different types of trust feedback, including user profile endorsements. The LibraryThing dataset offers fewer types of feedback but it provides more selective friend relations aimed at content sharing. The results of our experiments show that, on the Yelp dataset, our model outperforms both U2UCF and state-of-the-art trust-based recommenders that only use rating similarity and social relations. Differently, in the LibraryThing dataset, the combination of social relations and rating similarity achieves the best results. The lesson we learn is that multi-faceted trust can be a valuable type of information for recommendation. However, before using it in an application domain, an analysis of the type and amount of available trust evidence has to be done to assess its real impact on recommendation performance. |
| Tasks | Recommendation Systems |
| Published | 2020-03-25 |
| URL | https://arxiv.org/abs/2003.11445v1 |
| https://arxiv.org/pdf/2003.11445v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-faceted-trust-based-collaborative |
| Repo | |
| Framework | |
Linearly Constrained Gaussian Processes with Boundary Conditions
| Title | Linearly Constrained Gaussian Processes with Boundary Conditions |
| Authors | Markus Lange-Hegermann |
| Abstract | One goal in Bayesian machine learning is to encode prior knowledge into prior distributions, to model data efficiently. We consider prior knowledge from systems of linear (partial and ordinary) differential equations together with their boundary conditions. We construct multi-output Gaussian process priors with realizations dense in the solution set of such systems, in particular any solution (and only such solutions) can be represented to arbitrary precision by Gaussian process regression. The construction is fully algorithmic via Gr"obner bases and it does not employ any approximation. It builds these priors combining two parametrizations via a pullback: the first parametrizes the solutions for the system of differential equations and the second parametrizes all functions adhering to the boundary conditions. |
| Tasks | Gaussian Processes |
| Published | 2020-02-03 |
| URL | https://arxiv.org/abs/2002.00818v2 |
| https://arxiv.org/pdf/2002.00818v2.pdf | |
| PWC | https://paperswithcode.com/paper/linearly-constrained-gaussian-processes-with |
| Repo | |
| Framework | |
Developing a Recommendation Benchmark for MLPerf Training and Inference
| Title | Developing a Recommendation Benchmark for MLPerf Training and Inference |
| Authors | Carole-Jean Wu, Robin Burke, Ed Chi, Joseph Konstan, Julian McAuley, Yves Raimond, Hao Zhang |
| Abstract | Deep learning-based recommendation models are used pervasively and broadly, for example, to recommend movies, products, or other information most relevant to users, in order to enhance the user experience. Among various application domains which have received significant industry and academia research attention, such as image classification, object detection, language and speech translation, the performance of deep learning-based recommendation models is less well explored, even though recommendation tasks unarguably represent significant AI inference cycles at large-scale datacenter fleets. To advance the state of understanding and enable machine learning system development and optimization for the commerce domain, we aim to define an industry-relevant recommendation benchmark for the MLPerf Training andInference Suites. The paper synthesizes the desirable modeling strategies for personalized recommendation systems. We lay out desirable characteristics of recommendation model architectures and data sets. We then summarize the discussions and advice from the MLPerf Recommendation Advisory Board. |
| Tasks | Image Classification, Object Detection, Recommendation Systems |
| Published | 2020-03-16 |
| URL | https://arxiv.org/abs/2003.07336v1 |
| https://arxiv.org/pdf/2003.07336v1.pdf | |
| PWC | https://paperswithcode.com/paper/developing-a-recommendation-benchmark-for |
| Repo | |
| Framework | |
Technical report: Training Mixture Density Networks with full covariance matrices
| Title | Technical report: Training Mixture Density Networks with full covariance matrices |
| Authors | Jakob Kruse |
| Abstract | Mixture Density Networks are a tried and tested tool for modelling conditional probability distributions. As such, they constitute a great baseline for novel approaches to this problem. In the standard formulation, an MDN takes some input and outputs parameters for a Gaussian mixture model with restrictions on the mixture components’ covariance. Since covariance between random variables is a central issue in the conditional modeling problems we were investigating, I derived and implemented an MDN formulation with unrestricted covariances. It is likely that this has been done before, but I could not find any resources online. For this reason, I have documented my approach in the form of this technical report, in hopes that it may be useful to others facing a similar situation. |
| Tasks | |
| Published | 2020-03-04 |
| URL | https://arxiv.org/abs/2003.05739v1 |
| https://arxiv.org/pdf/2003.05739v1.pdf | |
| PWC | https://paperswithcode.com/paper/technical-report-training-mixture-density |
| Repo | |
| Framework | |
Reliable Estimation of Kullback-Leibler Divergence by Controlling Discriminator Complexity in the Reproducing Kernel Hilbert Space
| Title | Reliable Estimation of Kullback-Leibler Divergence by Controlling Discriminator Complexity in the Reproducing Kernel Hilbert Space |
| Authors | Sandesh Ghimire, Prashnna K Gyawali, Linwei Wang |
| Abstract | Several scalable methods to compute the Kullback Leibler (KL) divergence between two distributions using their samples have been proposed and applied in large-scale machine learning models. While they have been found to be unstable, the theoretical root cause of the problem is not clear. In this paper, we study in detail a generative adversarial network based approach that uses a neural network discriminator to estimate KL divergence. We argue that, in such case, high fluctuations in the estimates are a consequence of not controlling the complexity of the discriminator function space. We provide a theoretical underpinning and remedy for this problem through the following contributions. First, we construct a discriminator in the Reproducing Kernel Hilbert Space (RKHS). This enables us to leverage sample complexity and mean embedding to theoretically relate the error probability bound of the KL estimates to the complexity of the neural-net discriminator. Based on this theory, we then present a scalable way to control the complexity of the discriminator for a consistent estimation of KL divergence. We support both our proposed theory and method to control the complexity of the RKHS discriminator in controlled experiments. |
| Tasks | |
| Published | 2020-02-25 |
| URL | https://arxiv.org/abs/2002.11187v2 |
| https://arxiv.org/pdf/2002.11187v2.pdf | |
| PWC | https://paperswithcode.com/paper/reliable-estimation-of-kullback-leibler |
| Repo | |
| Framework | |
Parameter-Free Style Projection for Arbitrary Style Transfer
| Title | Parameter-Free Style Projection for Arbitrary Style Transfer |
| Authors | Siyu Huang, Haoyi Xiong, Tianyang Wang, Qingzhong Wang, Zeyu Chen, Jun Huan, Dejing Dou |
| Abstract | Arbitrary image style transfer is a challenging task which aims to stylize a content image conditioned on an arbitrary style image. In this task the content-style feature transformation is a critical component for a proper fusion of features. Existing feature transformation algorithms often suffer from unstable learning, loss of content and style details, and non-natural stroke patterns. To mitigate these issues, this paper proposes a parameter-free algorithm, Style Projection, for fast yet effective content-style transformation. To leverage the proposed Style Projection~component, this paper further presents a real-time feed-forward model for arbitrary style transfer, including a regularization for matching the content semantics between inputs and outputs. Extensive experiments have demonstrated the effectiveness and efficiency of the proposed method in terms of qualitative analysis, quantitative evaluation, and user study. |
| Tasks | Style Transfer |
| Published | 2020-03-17 |
| URL | https://arxiv.org/abs/2003.07694v1 |
| https://arxiv.org/pdf/2003.07694v1.pdf | |
| PWC | https://paperswithcode.com/paper/parameter-free-style-projection-for-arbitrary |
| Repo | |
| Framework | |
Minimax optimal goodness-of-fit testing for densities under a local differential privacy constraint
| Title | Minimax optimal goodness-of-fit testing for densities under a local differential privacy constraint |
| Authors | Joseph Lam-Weil, Béatrice Laurent, Jean-Michel Loubes |
| Abstract | Finding anonymization mechanisms to protect personal data is at the heart of machine learning research. Here we consider the consequences of local differential privacy constraints on goodness-of-fit testing, i.e. the statistical problem assessing whether sample points are generated from a fixed density $f_0$, or not. The observations are hidden and replaced by a stochastic transformation satisfying the local differential privacy constraint. In this setting, we propose a new testing procedure which is based on an estimation of the quadratic distance between the density $f$ of the unobserved sample and $f_0$. We establish minimax separation rates for our test over Besov balls. We also provide a lower bound, proving the optimality of our result. To the best of our knowledge, we provide the first minimax optimal test and associated private transformation under a local differential privacy constraint, quantifying the price to pay for data privacy. |
| Tasks | |
| Published | 2020-02-11 |
| URL | https://arxiv.org/abs/2002.04254v1 |
| https://arxiv.org/pdf/2002.04254v1.pdf | |
| PWC | https://paperswithcode.com/paper/minimax-optimal-goodness-of-fit-testing-for |
| Repo | |
| Framework | |
Training Deep Energy-Based Models with f-Divergence Minimization
| Title | Training Deep Energy-Based Models with f-Divergence Minimization |
| Authors | Lantao Yu, Yang Song, Jiaming Song, Stefano Ermon |
| Abstract | Deep energy-based models (EBMs) are very flexible in distribution parametrization but computationally challenging because of the intractable partition function. They are typically trained via maximum likelihood, using contrastive divergence to approximate the gradient of the KL divergence between data and model distribution. While KL divergence has many desirable properties, other f-divergences have shown advantages in training implicit density generative models such as generative adversarial networks. In this paper, we propose a general variational framework termed f-EBM to train EBMs using any desired f-divergence. We introduce a corresponding optimization algorithm and prove its local convergence property with non-linear dynamical systems theory. Experimental results demonstrate the superiority of f-EBM over contrastive divergence, as well as the benefits of training EBMs using f-divergences other than KL. |
| Tasks | |
| Published | 2020-03-06 |
| URL | https://arxiv.org/abs/2003.03463v1 |
| https://arxiv.org/pdf/2003.03463v1.pdf | |
| PWC | https://paperswithcode.com/paper/training-deep-energy-based-models-with-f |
| Repo | |
| Framework | |
A Pebble in the AI Race
| Title | A Pebble in the AI Race |
| Authors | Toby Walsh |
| Abstract | Bhutan is sometimes described as \a pebble between two boulders”, a small country caught between the two most populous nations on earth: India and China. This pebble is, however, about to be caught up in a vortex: the transformation of our economic, political and social orders by new technologies like Artificial Intelligence. What can a small nation like Bhutan hope to do in the face of such change? What should the nation do, not just to weather this storm, but to become a better place in which to live? |
| Tasks | |
| Published | 2020-03-30 |
| URL | https://arxiv.org/abs/2003.13861v1 |
| https://arxiv.org/pdf/2003.13861v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-pebble-in-the-ai-race |
| Repo | |
| Framework | |
Best Practices for Implementing FAIR Vocabularies and Ontologies on the Web
| Title | Best Practices for Implementing FAIR Vocabularies and Ontologies on the Web |
| Authors | Daniel Garijo, María Poveda-Villalón |
| Abstract | With the adoption of Semantic Web technologies, an increasing number of vocabularies and ontologies have been developed in different domains, ranging from Biology to Agronomy or Geosciences. However, many of these ontologies are still difficult to find, access and understand by researchers due to a lack of documentation, URI resolving issues, versioning problems, etc. In this chapter we describe guidelines and best practices for creating accessible, understandable and reusable ontologies on the Web, using standard practices and pointing to existing tools and frameworks developed by the Semantic Web community. We illustrate our guidelines with concrete examples, in order to help researchers implement these practices in their future vocabularies. |
| Tasks | |
| Published | 2020-03-29 |
| URL | https://arxiv.org/abs/2003.13084v1 |
| https://arxiv.org/pdf/2003.13084v1.pdf | |
| PWC | https://paperswithcode.com/paper/best-practices-for-implementing-fair |
| Repo | |
| Framework | |
Deep Neural Review Text Interaction for Recommendation Systems
| Title | Deep Neural Review Text Interaction for Recommendation Systems |
| Authors | Parisa Abolfath Beygi Dezfouli, Saeedeh Momtazi, Mehdi Dehghan |
| Abstract | Users’ reviews contain valuable information which are not taken into account in most recommender systems. According to the latest studies in this field, using review texts could not only improve the performance of recommendation, but it can also alleviate the impact of data sparsity and help to tackle the cold start problem. In this paper, we present a neural recommender model which recommends items by leveraging user reviews. In order to predict user rating for each item, our proposed model, named MatchPyramid Recommender System (MPRS), represents each user and item with their corresponding review texts. Thus, the problem of recommendation is viewed as a text matching problem such that the matching score obtained from matching user and item texts could be considered as a good representative of their joint extent of similarity. To solve the text matching problem, inspired by MatchPyramid (Pang, 2016), we employed an interaction-based approach according to which a matching matrix is constructed given a pair of input texts. The matching matrix, which has the property of hierarchical matching patterns, is then fed into a Convolutional Neural Network (CNN) to compute the matching score for the given user-item pair. Our experiments on the small data categories of Amazon review dataset show that our proposed model gains from 1.76% to 21.72% relative improvement compared to DeepCoNN model, and from 0.83% to 3.15% relative improvement compared to TransNets model. Also, on two large categories, namely AZ-CSJ and AZ-Mov, our model achieves relative improvements of 8.08% and 7.56% compared to the DeepCoNN model, and relative improvements of 1.74% and 0.86% compared to the TransNets model, respectively. |
| Tasks | Recommendation Systems, Text Matching |
| Published | 2020-03-16 |
| URL | https://arxiv.org/abs/2003.07051v1 |
| https://arxiv.org/pdf/2003.07051v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-neural-review-text-interaction-for |
| Repo | |
| Framework | |
On the effectiveness of convolutional autoencoders on image-based personalized recommender systems
| Title | On the effectiveness of convolutional autoencoders on image-based personalized recommender systems |
| Authors | E. Blanco-Mallo, B. Remeseiro, V. Bolón-Canedo, A. Alonso-Betanzos |
| Abstract | Recommender systems (RS) are increasingly present in our daily lives, especially since the advent of Big Data, which allows for storing all kinds of information about users’ preferences. Personalized RS are successfully applied in platforms such as Netflix, Amazon or YouTube. However, they are missing in gastronomic platforms such as TripAdvisor, where moreover we can find millions of images tagged with users’ tastes. This paper explores the potential of using those images as sources of information for modeling users’ tastes and proposes an image-based classification system to obtain personalized recommendations, using a convolutional autoencoder as feature extractor. The proposed architecture will be applied to TripAdvisor data, using users’ reviews that can be defined as a triad composed by a user, a restaurant, and an image of it taken by the user. Since the dataset is highly unbalanced, the use of data augmentation on the minority class is also considered in the experimentation. Results on data from three cities of different sizes (Santiago de Compostela, Barcelona and New York) demonstrate the effectiveness of using a convolutional autoencoder as feature extractor, instead of the standard deep features computed with convolutional neural networks. |
| Tasks | Data Augmentation, Recommendation Systems |
| Published | 2020-03-13 |
| URL | https://arxiv.org/abs/2003.06205v1 |
| https://arxiv.org/pdf/2003.06205v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-effectiveness-of-convolutional |
| Repo | |
| Framework | |
Universal consistency of the $k$-NN rule in metric spaces and Nagata dimension
| Title | Universal consistency of the $k$-NN rule in metric spaces and Nagata dimension |
| Authors | Benoît Collins, Sushma Kumari, Vladimir G. Pestov |
| Abstract | The $k$ nearest neighbour learning rule (under the uniform distance tie breaking) is universally consistent in every metric space $X$ that is sigma-finite dimensional in the sense of Nagata. This was pointed out by C'erou and Guyader (2006) as a consequence of the main result by those authors, combined with a theorem in real analysis sketched by D. Preiss (1971) (and elaborated in detail by Assouad and Quentin de Gromard (2006)). We show that it is possible to give a direct proof along the same lines as the original theorem of Charles J. Stone (1977) about the universal consistency of the $k$-NN classifier in the finite dimensional Euclidean space. The generalization is non-trivial because of the distance ties being more prevalent in the non-euclidean setting, and on the way we investigate the relevant geometric properties of the metrics and the limitations of the Stone argument, by constructing various examples. |
| Tasks | |
| Published | 2020-02-28 |
| URL | https://arxiv.org/abs/2003.00894v1 |
| https://arxiv.org/pdf/2003.00894v1.pdf | |
| PWC | https://paperswithcode.com/paper/universal-consistency-of-the-k-nn-rule-in |
| Repo | |
| Framework | |
