scispace - formally typeset
Search or ask a question

Showing papers on "Metric (mathematics) published in 2018"


Book ChapterDOI
08 Sep 2018
TL;DR: ShuffleNet V2 as discussed by the authors proposes to evaluate the direct metric on the target platform, beyond only considering FLOPs, based on a series of controlled experiments, and derives several practical guidelines for efficient network design.
Abstract: Currently, the neural network architecture design is mostly guided by the indirect metric of computation complexity, i.e., FLOPs. However, the direct metric, e.g., speed, also depends on the other factors such as memory access cost and platform characterics. Thus, this work proposes to evaluate the direct metric on the target platform, beyond only considering FLOPs. Based on a series of controlled experiments, this work derives several practical guidelines for efficient network design. Accordingly, a new architecture is presented, called ShuffleNet V2. Comprehensive ablation experiments verify that our model is the state-of-the-art in terms of speed and accuracy tradeoff.

3,393 citations


Proceedings ArticleDOI
18 Jun 2018
TL;DR: A conceptually simple, flexible, and general framework for few-shot learning, where a classifier must learn to recognise new classes given only few examples from each, which is easily extended to zero- shot learning.
Abstract: We present a conceptually simple, flexible, and general framework for few-shot learning, where a classifier must learn to recognise new classes given only few examples from each. Our method, called the Relation Network (RN), is trained end-to-end from scratch. During meta-learning, it learns to learn a deep distance metric to compare a small number of images within episodes, each of which is designed to simulate the few-shot setting. Once trained, a RN is able to classify images of new classes by computing relation scores between query images and the few examples of each new class without further updating the network. Besides providing improved performance on few-shot learning, our framework is easily extended to zero-shot learning. Extensive experiments on five benchmarks demonstrate that our simple approach provides a unified and effective approach for both of these two tasks.

2,496 citations


Journal ArticleDOI
TL;DR: This paper proposes a simple but effective method to learn discriminative CNNs (D-CNNs) to boost the performance of remote sensing image scene classification and comprehensively evaluates the proposed method on three publicly available benchmark data sets using three off-the-shelf CNN models.
Abstract: Remote sensing image scene classification is an active and challenging task driven by many applications. More recently, with the advances of deep learning models especially convolutional neural networks (CNNs), the performance of remote sensing image scene classification has been significantly improved due to the powerful feature representations learnt through CNNs. Although great success has been obtained so far, the problems of within-class diversity and between-class similarity are still two big challenges. To address these problems, in this paper, we propose a simple but effective method to learn discriminative CNNs (D-CNNs) to boost the performance of remote sensing image scene classification. Different from the traditional CNN models that minimize only the cross entropy loss, our proposed D-CNN models are trained by optimizing a new discriminative objective function. To this end, apart from minimizing the classification error, we also explicitly impose a metric learning regularization term on the CNN features. The metric learning regularization enforces the D-CNN models to be more discriminative so that, in the new D-CNN feature spaces, the images from the same scene class are mapped closely to each other and the images of different classes are mapped as farther apart as possible. In the experiments, we comprehensively evaluate the proposed method on three publicly available benchmark data sets using three off-the-shelf CNN models. Experimental results demonstrate that our proposed D-CNN methods outperform the existing baseline methods and achieve state-of-the-art results on all three data sets.

1,001 citations


Proceedings Article
23 May 2018
TL;DR: This work identifies that metric scaling and metric task conditioning are important to improve the performance of few-shot algorithms and proposes and empirically test a practical end-to-end optimization procedure based on auxiliary task co-training to learn a task-dependent metric space.
Abstract: Few-shot learning has become essential for producing models that generalize from few examples. In this work, we identify that metric scaling and metric task conditioning are important to improve the performance of few-shot algorithms. Our analysis reveals that simple metric scaling completely changes the nature of few-shot algorithm parameter updates. Metric scaling provides improvements up to 14% in accuracy for certain metrics on the mini-Imagenet 5-way 5-shot classification task. We further propose a simple and effective way of conditioning a learner on the task sample set, resulting in learning a task-dependent metric space. Moreover, we propose and empirically test a practical end-to-end optimization procedure based on auxiliary task co-training to learn a task-dependent metric space. The resulting few-shot learning model based on the task-dependent scaled metric achieves state of the art on mini-Imagenet. We confirm these results on another few-shot dataset that we introduce in this paper based on CIFAR100.

980 citations


Proceedings Article
Hyunjik Kim1, Andriy Mnih1
16 Feb 2018
TL;DR: This article proposed FactorVAE, a method that disentangles by encouraging the distribution of representations to be factorial and hence independent across the dimensions, and showed that it improves upon β-VAE by providing a better trade-off between disentanglement and reconstruction quality.
Abstract: We define and address the problem of unsupervised learning of disentangled representations on data generated from independent factors of variation. We propose FactorVAE, a method that disentangles by encouraging the distribution of representations to be factorial and hence independent across the dimensions. We show that it improves upon $\beta$-VAE by providing a better trade-off between disentanglement and reconstruction quality. Moreover, we highlight the problems of a commonly used disentanglement metric and introduce a new metric that does not suffer from them.

660 citations


Posted Content
Hyunjik Kim1, Andriy Mnih1
TL;DR: FactorVAE, a method that disentangles by encouraging the distribution of representations to be factorial and hence independent across the dimensions, is proposed and it improves upon $\beta$-VAE by providing a better trade-off between disentanglement and reconstruction quality.
Abstract: We define and address the problem of unsupervised learning of disentangled representations on data generated from independent factors of variation. We propose FactorVAE, a method that disentangles by encouraging the distribution of representations to be factorial and hence independent across the dimensions. We show that it improves upon $\beta$-VAE by providing a better trade-off between disentanglement and reconstruction quality. Moreover, we highlight the problems of a commonly used disentanglement metric and introduce a new metric that does not suffer from them.

502 citations


Posted Content
TL;DR: New insights are provided into the Inception Score, a recently proposed and widely used evaluation metric for generative models, and it is demonstrated that it fails to provide useful guidance when comparing models.
Abstract: Deep generative models are powerful tools that have produced impressive results in recent years. These advances have been for the most part empirically driven, making it essential that we use high quality evaluation metrics. In this paper, we provide new insights into the Inception Score, a recently proposed and widely used evaluation metric for generative models, and demonstrate that it fails to provide useful guidance when comparing models. We discuss both suboptimalities of the metric itself and issues with its application. Finally, we call for researchers to be more systematic and careful when evaluating and comparing generative models, as the advancement of the field depends upon it.

459 citations


Proceedings Article
01 Jan 2018
TL;DR: The problem of Explainable AI for deep neural networks that take images as input and output a class probability is addressed and an approach called RISE that generates an importance map indicating how salient each pixel is for the model's prediction is proposed.
Abstract: Deep neural networks are being used increasingly to automate data analysis and decision making, yet their decision-making process is largely unclear and is difficult to explain to the end users. In this paper, we address the problem of Explainable AI for deep neural networks that take images as input and output a class probability. We propose an approach called RISE that generates an importance map indicating how salient each pixel is for the model's prediction. In contrast to white-box approaches that estimate pixel importance using gradients or other internal network state, RISE works on black-box models. It estimates importance empirically by probing the model with randomly masked versions of the input image and obtaining the corresponding outputs. We compare our approach to state-of-the-art importance extraction methods using both an automatic deletion/insertion metric and a pointing metric based on human-annotated object segments. Extensive experiments on several benchmark datasets show that our approach matches or exceeds the performance of other methods, including white-box approaches. Project page: this http URL

436 citations


Journal ArticleDOI
TL;DR: This work investigates notions of complexity of states in continuous many-body quantum systems by focusing on Gaussian states which include ground states of free quantum field theories and their approximations encountered in the context of the continuous version of the multiscale entanglement renormalization ansatz.
Abstract: We investigate notions of complexity of states in continuous many-body quantum systems. We focus on Gaussian states which include ground states of free quantum field theories and their approximations encountered in the context of the continuous version of the multiscale entanglement renormalization ansatz. Our proposal for quantifying state complexity is based on the Fubini-Study metric. It leads to counting the number of applications of each gate (infinitesimal generator) in the transformation, subject to a state-dependent metric. We minimize the defined complexity with respect to momentum-preserving quadratic generators which form su(1,1) algebras. On the manifold of Gaussian states generated by these operations, the Fubini-Study metric factorizes into hyperbolic planes with minimal complexity circuits reducing to known geodesics. Despite working with quantum field theories far outside the regime where Einstein gravity duals exist, we find striking similarities between our results and those of holographic complexity proposals.

427 citations


Book ChapterDOI
08 Sep 2018
TL;DR: Huang et al. as mentioned in this paper proposed a hierarchical triplet loss (HTL) to automatically collect informative training samples via a defined hierarchical tree that encodes global context information, which allows the model to learn more discriminative features from visual similar classes, leading to faster convergence and better performance.
Abstract: We present a novel hierarchical triplet loss (HTL) capable of automatically collecting informative training samples (triplets) via a defined hierarchical tree that encodes global context information. This allows us to cope with the main limitation of random sampling in training a conventional triplet loss, which is a central issue for deep metric learning. Our main contributions are two-fold. (i) we construct a hierarchical class-level tree where neighboring classes are merged recursively. The hierarchical structure naturally captures the intrinsic data distribution over the whole dataset. (ii) we formulate the problem of triplet collection by introducing a new violate margin, which is computed dynamically based on the designed hierarchical tree. This allows it to automatically select meaningful hard samples with the guide of global context. It encourages the model to learn more discriminative features from visual similar classes, leading to faster convergence and better performance. Our method is evaluated on the tasks of image retrieval and face recognition, where it outperforms the standard triplet loss substantially by 1%–18%, and achieves new state-of-the-art performance on a number of benchmarks.

319 citations


Proceedings ArticleDOI
16 Mar 2018
TL;DR: Wang et al. as discussed by the authors proposed triplet-center loss, which learns a center for each class and requires that the distances between samples and centers from the same class are closer than those from different classes.
Abstract: Most existing 3D object recognition algorithms focus on leveraging the strong discriminative power of deep learning models with softmax loss for the classification of 3D data, while learning discriminative features with deep metric learning for 3D object retrieval is more or less neglected. In the paper, we study variants of deep metric learning losses for 3D object retrieval, which did not receive enough attention from this area. First, two kinds of representative losses, triplet loss and center loss, are introduced which could learn more discriminative features than traditional classification loss. Then, we propose a novel loss named triplet-center loss, which can further enhance the discriminative power of the features. The proposed triplet-center loss learns a center for each class and requires that the distances between samples and centers from the same class are closer than those from different classes. Extensive experimental results on two popular 3D object retrieval benchmarks and two widely-adopted sketch-based 3D shape retrieval benchmarks consistently demonstrate the effectiveness of our proposed loss, and significant improvements have been achieved compared with the state-of-the-arts.

Proceedings ArticleDOI
12 Mar 2018
TL;DR: In this paper, the final classification layer can be stripped from the network to facilitate nearest neighbor queries on unseen individuals using the cosine similarity metric, which is effectively optimized through a simple re-parametrization of the conventional softmax classification regime.
Abstract: Metric learning aims to construct an embedding where two extracted features corresponding to the same identity are likely to be closer than features from different identities. This paper presents a method for learning such a feature space where the cosine similarity is effectively optimized through a simple re-parametrization of the conventional softmax classification regime. At test time, the final classification layer can be stripped from the network to facilitate nearest neighbor queries on unseen individuals using the cosine similarity metric. This approach presents a simple alternative to direct metric learning objectives such as siamese networks that have required sophisticated pair or triplet sampling strategies in the past. The method is evaluated on two large-scale pedestrian re-identification datasets where competitive results are achieved overall. In particular, we achieve better generalization on the test set compared to a network trained with triplet loss.

Journal ArticleDOI
TL;DR: The authors surveyed all articles in the Journal of Personality and Social Psychology (JPSP), Psychological Science (PS), and the Journal Experimental Psychology: General (JEP:G) that mentioned the term Likert, and found that 100% of the articles that analyzed ordinal data did so using a metric model.

Proceedings Article
03 Jul 2018
TL;DR: In this article, a task-specific learner of an EMMT-net performs gradient descent with respect to a meta-learned distance metric, which warps the activation space to be more sensitive to task identity.
Abstract: Gradient-based meta-learning methods leverage gradient descent to learn the commonalities among various tasks. While previous such methods have been successful in meta-learning tasks, they resort to simple gradient descent during meta-testing. Our primary contribution is the {\em MT-net}, which enables the meta-learner to learn on each layer's activation space a subspace that the task-specific learner performs gradient descent on. Additionally, a task-specific learner of an {\em MT-net} performs gradient descent with respect to a meta-learned distance metric, which warps the activation space to be more sensitive to task identity. We demonstrate that the dimension of this learned subspace reflects the complexity of the task-specific learner's adaptation task, and also that our model is less sensitive to the choice of initial learning rates than previous gradient-based meta-learning methods. Our method achieves state-of-the-art or comparable performance on few-shot classification and regression tasks.

Proceedings Article
27 Apr 2018
TL;DR: An improved two-stream CNN network is presented to learn the multimodality sharable feature representations and identity loss and contrastive loss are integrated to enhance the discriminability and modality-invariance with partially shared layer parameters.
Abstract: Person re-identification is widely studied in visible spectrum, where all the person images are captured by visible cameras. However, visible cameras may not capture valid appearance information under poor illumination conditions, e.g, at night. In this case, thermal camera is superior since it is less dependent on the lighting by using infrared light to capture the human body. To this end, this paper investigates a cross-modal re-identification problem, namely visible-thermal person re-identification (VT-REID). Existing cross-modal matching methods mainly focus on modeling the cross-modality discrepancy, while VT-REID also suffers from cross-view variations caused by different camera views. Therefore, we propose a hierarchical cross-modality matching model by jointly optimizing the modality-specific and modality-shared metrics. The modality-specific metrics transform two heterogenous modalities into a consistent space that modality-shared metric can be subsequently learnt. Meanwhile, the modality-specific metric compacts features of the same person within each modality to handle the large intra-modality intra-person variations (e.g. viewpoints, pose). Additionally, an improved two-stream CNN network is presented to learn the multi-modality sharable feature representations. Identity loss and contrastive loss are integrated to enhance the discriminability and modality-invariance with partially shared layer parameters. Extensive experiments illustrate the effectiveness and robustness of the proposed method.

Proceedings ArticleDOI
18 Jun 2018
TL;DR: The proposed method supports different kinds of user input such as segmentation mask in the first frame (semi-supervised scenario), or a sparse set of clicked points (interactive scenario), and reaches comparable quality to competing methods with much less interaction.
Abstract: This paper tackles the problem of video object segmentation, given some user annotation which indicates the object of interest. The problem is formulated as pixel-wise retrieval in a learned embedding space: we embed pixels of the same object instance into the vicinity of each other, using a fully convolutional network trained by a modified triplet loss as the embedding model. Then the annotated pixels are set as reference and the rest of the pixels are classified using a nearest-neighbor approach. The proposed method supports different kinds of user input such as segmentation mask in the first frame (semi-supervised scenario), or a sparse set of clicked points (interactive scenario). In the semi-supervised scenario, we achieve results competitive with the state of the art but at a fraction of computation cost (275 milliseconds per frame). In the interactive scenario where the user is able to refine their input iteratively, the proposed method provides instant response to each input, and reaches comparable quality to competing methods with much less interaction.

Journal ArticleDOI
TL;DR: The algorithm is shown to not only locate and maintain a larger number of Pareto-optimal solutions, but also to obtain good distributions in both the decision and objective spaces.
Abstract: This paper presents a new particle swarm optimizer for solving multimodal multiobjective optimization problems which may have more than one Pareto-optimal solution corresponding to the same objective function value The proposed method features an index-based ring topology to induce stable niches that allow the identification of a larger number of Pareto-optimal solutions, and adopts a special crowding distance concept as a density metric in the decision and objective spaces The algorithm is shown to not only locate and maintain a larger number of Pareto-optimal solutions, but also to obtain good distributions in both the decision and objective spaces In addition, new multimodal multiobjective optimization test functions and a novel performance indicator are designed for the purpose of assessing the performance of the proposed algorithms An effectiveness validation study is carried out comparing the proposed method with five other algorithms using the benchmark functions to prove its effectiveness

Journal ArticleDOI
TL;DR: A comprehensive mathematical framework is developed to compute circuit complexity between arbitrary fermionic Gaussian states and free Dirac field states with respect to several classes of spatially unentangled reference states.
Abstract: We study circuit complexity for free fermionic field theories and Gaussian states. Our definition of circuit complexity is based on the notion of geodesic distance on the Lie group of special orthogonal transformations equipped with a right-invariant metric. After analyzing the differences and similarities to bosonic circuit complexity, we develop a comprehensive mathematical framework to compute circuit complexity between arbitrary fermionic Gaussian states. We apply this framework to the free Dirac field in four dimensions where we compute the circuit complexity of the Dirac ground state with respect to several classes of spatially unentangled reference states. Moreover, we show that our methods can also be applied to compute the complexity of excited energy eigenstates of the free Dirac field. Finally, we discuss the relation of our results to alternative approaches based on the Fubini-Study metric, the relevance to holography and possible extensions.

Proceedings ArticleDOI
23 Apr 2018
TL;DR: Qualitative studies demonstrate evidence that the proposed model is able to infer and encode explicit sentiment, temporal and attribute information despite being only trained on implicit feedback, ascertains the ability of LRML to uncover hidden relational structure within implicit datasets.
Abstract: This paper proposes a new neural architecture for collaborative ranking with implicit feedback. Our model, LRML (Latent Relational Metric Learning) is a novel metric learning approach for recommendation. More specifically, instead of simple push-pull mechanisms between user and item pairs, we propose to learn latent relations that describe each user item interaction. This helps to alleviate the potential geometric inflexibility of existing metric learning approaches. This enables not only better performance but also a greater extent of modeling capability, allowing our model to scale to a larger number of interactions. In order to do so, we employ a augmented memory module and learn to attend over these memory blocks to construct latent relations. The memory-based attention module is controlled by the user-item interaction, making the learned relation vector specific to each user-item pair. Hence, this can be interpreted as learning an exclusive and optimal relational translation for each user-item interaction. The proposed architecture demonstrates the state-of-the-art performance across multiple recommendation benchmarks. LRML outperforms other metric learning models by 6%-7.5% in terms of Hits@10 and nDCG@10 on large datasets such as Netflix and MovieLens20M. Moreover, qualitative studies also demonstrate evidence that our proposed model is able to infer and encode explicit sentiment, temporal and attribute information despite being only trained on implicit feedback. As such, this ascertains the ability of LRML to uncover hidden relational structure within implicit datasets.

Posted Content
TL;DR: RISE as mentioned in this paper generates an importance map indicating how salient each pixel is for the model's prediction, by probing the model with randomly masked versions of the input image and obtaining the corresponding outputs.
Abstract: Deep neural networks are being used increasingly to automate data analysis and decision making, yet their decision-making process is largely unclear and is difficult to explain to the end users. In this paper, we address the problem of Explainable AI for deep neural networks that take images as input and output a class probability. We propose an approach called RISE that generates an importance map indicating how salient each pixel is for the model's prediction. In contrast to white-box approaches that estimate pixel importance using gradients or other internal network state, RISE works on black-box models. It estimates importance empirically by probing the model with randomly masked versions of the input image and obtaining the corresponding outputs. We compare our approach to state-of-the-art importance extraction methods using both an automatic deletion/insertion metric and a pointing metric based on human-annotated object segments. Extensive experiments on several benchmark datasets show that our approach matches or exceeds the performance of other methods, including white-box approaches. Project page: this http URL

Proceedings Article
01 Jan 2018
TL;DR: NASHBOT is developed, a Gaussian process based BO framework for neural architecture search which outperforms other alternatives for architecture search in several cross validation based model selection tasks on multi-layer perceptrons and convolutional neural networks.
Abstract: Bayesian Optimisation (BO) refers to a class of methods for global optimisation of a function f which is only accessible via point evaluations. It is typically used in settings where f is expensive to evaluate. A common use case for BO in machine learning is model selection, where it is not possible to analytically model the generalisation performance of a statistical model, and we resort to noisy and expensive training and validation procedures to choose the best model. Conventional BO methods have focused on Euclidean and categorical domains, which, in the context of model selection, only permits tuning scalar hyper-parameters of machine learning algorithms. However, with the surge of interest in deep learning, there is an increasing demand to tune neural network architectures. In this work, we develop NASBOT, a Gaussian process based BO framework for neural architecture search. To accomplish this, we develop a distance metric in the space of neural network architectures which can be computed efficiently via an optimal transport program. This distance might be of independent interest to the deep learning community as it may find applications outside of BO. We demonstrate that NASBOT outperforms other alternatives for architecture search in several cross validation based model selection tasks on multi-layer perceptrons and convolutional neural networks.

Proceedings ArticleDOI
Yueqi Duan, Wenzhao Zheng1, Xudong Lin1, Jiwen Lu, Jie Zhou 
18 Jun 2018
TL;DR: This paper proposes a deep adversarial metric learning (DAML) framework to generate synthetic hard negatives from the observed negative samples, which is widely applicable to supervised deep metric learning methods.
Abstract: Learning an effective distance metric between image pairs plays an important role in visual analysis, where the training procedure largely relies on hard negative samples. However, hard negatives in the training set usually account for the tiny minority, which may fail to fully describe the distribution of negative samples close to the margin. In this paper, we propose a deep adversarial metric learning (DAML) framework to generate synthetic hard negatives from the observed negative samples, which is widely applicable to supervised deep metric learning methods. Different from existing metric learning approaches which simply ignore numerous easy negatives, the proposed DAML exploits them to generate potential hard negatives adversarial to the learned metric as complements. We simultaneously train the hard negative generator and feature embedding in an adversarial manner, so that more precise distance metrics can be learned with adequate and targeted synthetic hard negatives. Extensive experimental results on three benchmark datasets including CUB-200-2011, Cars196 and Stanford Online Products show that DAML effectively boosts the performance of existing deep metric learning approaches through adversarial learning.

Journal ArticleDOI
TL;DR: An evaluation metric for generative models called Fréchet ChemNet distance (FCD) is proposed that can detect whether generated molecules are diverse and have similar chemical and biological properties as real molecules.
Abstract: The new wave of successful generative models in machine learning has increased the interest in deep learning driven de novo drug design. However, method comparison is difficult because of various flaws of the currently employed evaluation metrics. We propose an evaluation metric for generative models called Frechet ChemNet distance (FCD). The advantage of the FCD over previous metrics is that it can detect whether generated molecules are diverse and have similar chemical and biological properties as real molecules.

Journal ArticleDOI
TL;DR: A novel correlation coefficient is proposed which takes into consideration both the non-intersection and the difference among the focal elements and satisfies all the requirements for a metric.

Proceedings Article
01 Jan 2018
TL;DR: This work shows that the nonlinearity of the generator imply that the latent space gives a distorted view of the input space, and shows that this distortion can be characterized by a stochastic Riemannian metric, and demonstrates that distances and interpolants are significantly improved under this metric.
Abstract: Deep generative models provide a systematic way to learn nonlinear data distributions, through a set of latent variables and a nonlinear "generator" function that maps latent points into the input space. The nonlinearity of the generator imply that the latent space gives a distorted view of the input space. Under mild conditions, we show that this distortion can be characterized by a stochastic Riemannian metric, and demonstrate that distances and interpolants are significantly improved under this metric. This in turn improves probability distributions, sampling algorithms and clustering in the latent space. Our geometric analysis further reveals that current generators provide poor variance estimates and we propose a new generator architecture with vastly improved variance estimates. Results are demonstrated on convolutional and fully connected variational autoencoders, but the formalism easily generalize to other deep generative models.

Journal ArticleDOI
TL;DR: This work proposes a unified metric learning-based framework to jointly learn discriminative feature representation and co-salient object detector by optimizing a new objective function that explicitly embeds a metric learning regularization term into support vector machine (SVM) training.
Abstract: Co-saliency detection, which focuses on extracting commonly salient objects in a group of relevant images, has been attracting research interest because of its broad applications In practice, the relevant images in a group may have a wide range of variations, and the salient objects may also have large appearance changes Such wide variations usually bring about large intra-co-salient objects (intra-COs) diversity and high similarity between COs and background, which makes the co-saliency detection task more difficult To address these problems, we make the earliest effort to introduce metric learning to co-saliency detection Specifically, we propose a unified metric learning-based framework to jointly learn discriminative feature representation and co-salient object detector This is achieved by optimizing a new objective function that explicitly embeds a metric learning regularization term into support vector machine (SVM) training Here, the metric learning regularization term is used to learn a powerful feature representation that has small intra-COs scatter, but big separation between background and COs and the SVM classifier is used for subsequent co-saliency detection In the experiments, we comprehensively evaluate the proposed method on two commonly used benchmark data sets The state-of-the-art results are achieved in comparison with the existing co-saliency detection methods

Proceedings ArticleDOI
19 Jul 2018
TL;DR: A novel heterogenous information network embedding model PME based on the metric learning to capture both first-order and second-order proximities in a unified way is proposed and the experimental results show superiority of the proposed PME model in terms of prediction accuracy and scalability.
Abstract: Heterogenous information network embedding aims to embed heterogenous information networks (HINs) into low dimensional spaces, in which each vertex is represented as a low-dimensional vector, and both global and local network structures in the original space are preserved. However, most of existing heterogenous information network embedding models adopt the dot product to measure the proximity in the low dimensional space, and thus they can only preserve the first-order proximity and are insufficient to capture the global structure. Compared with homogenous information networks, there are multiple types of links (i.e., multiple relations) in HINs, and the link distribution w.r.t relations is highly skewed. To address the above challenging issues, we propose a novel heterogenous information network embedding model PME based on the metric learning to capture both first-order and second-order proximities in a unified way. To alleviate the potential geometrical inflexibility of existing metric learning approaches, we propose to build object and relation embeddings in separate object space and relation spaces rather than in a common space. Afterwards, we learn embeddings by firstly projecting vertices from object space to corresponding relation space and then calculate the proximity between projected vertices. To overcome the heavy skewness of the link distribution w.r.t relations and avoid "over-sampling'' or "under-sampling'' for each relation, we propose a novel loss-aware adaptive sampling approach for the model optimization. Extensive experiments have been conducted on a large-scale HIN dataset, and the experimental results show superiority of our proposed PME model in terms of prediction accuracy and scalability.

Journal ArticleDOI
TL;DR: A procedure for optimizing the sharpening of a map based on maximizing the level of detail and connectivity of the map has been developed and applied to 361 pairs of deposited cryo-EM maps and associated models.
Abstract: An algorithm for automatic map sharpening is presented that is based on optimization of the detail and connectivity of the sharpened map. The detail in the map is reflected in the surface area of an iso-contour surface that contains a fixed fraction of the volume of the map, where a map with high level of detail has a high surface area. The connectivity of the sharpened map is reflected in the number of connected regions defined by the same iso-contour surfaces, where a map with high connectivity has a small number of connected regions. By combining these two measures in a metric termed the `adjusted surface area', map quality can be evaluated in an automated fashion. This metric was used to choose optimal map-sharpening parameters without reference to a model or other interpretations of the map. Map sharpening by optimization of the adjusted surface area can be carried out for a map as a whole or it can be carried out locally, yielding a locally sharpened map. To evaluate the performance of various approaches, a simple metric based on map–model correlation that can reproduce visual choices of optimally sharpened maps was used. The map–model correlation is calculated using a model with B factors (atomic displacement factors; ADPs) set to zero. This model-based metric was used to evaluate map sharpening and to evaluate map-sharpening approaches, and it was found that optimization of the adjusted surface area can be an effective tool for map sharpening.

Journal ArticleDOI
TL;DR: A novel objective function is proposed to jointly optimize similarity metric learning, local positive mining and robust deep feature embedding for person re-id by proposing a novel sampling to mine suitable positives within a local range to improve the deep embedding in the context of large intra-class variations.

Journal ArticleDOI
TL;DR: The experimental results of this study suggest the proposed deep distance metric learning method offers a new and promising tool for intelligent fault diagnosis of rolling bearings.