Clustering of publication networks is an efficient way to obtain classifications of large collections of research publications. Such classifications can be used to, e.g., detect research topics, normalize citation relations, or explore the publication output of a unit. Citation networks can be created using a variety of approaches. Best practices to obtain classifications using clustering have been investigated, in particular the performance of different publication-publication relatedness measures. However, evaluation of different approaches to normalization of citation relations have not been explored to the same extent. In this paper, we evaluate five approaches to normalization of direct citation relations with respect to clustering solution quality in four data sets. A sixth approach is evaluated using no normalization. To assess the quality of clustering solutions, we use three measures. (1) We compare the clustering solution to the reference lists of a set of publications using the Adjusted Rand Index. (2) Using the Sihouette width measure, we quantity to which extent the publications have relations to other clusters than the one they have been assigned to. (3) We propose a measure that captures publications that have probably been inaccurately assigned. The results clearly show that normalization is preferred over unnormalized direct citation relations. Furthermore, the results indicate that the fractional normalization approach, which can be considered the standard approach, causes inaccurate assignments. The geometric normalization approach has a similar performance as the fractional approach regarding Adjusted Rand Index and Silhouette width but leads to fewer inaccurate assignments. We therefore believe that the geometric approach may be preferred over the fractional approach.
相關內容
An explosion of work in language is leading to ever-increasing numbers of available natural language processing models, with little understanding of how new models compare to better-understood models. One major reason for this difficulty is saturating benchmark datasets, which may not reflect well differences in model performance in the wild. In this work, we propose a novel framework for comparing two natural language processing models by revealing their shared invariance to interpretable input perturbations that are designed to target a specific linguistic capability (e.g., Synonym-Invariance, Typo-Invariance). Via experiments on models from within the same and across different architecture families, this framework offers a number of insights about how changes in models (e.g., distillation, increase in size, amount of pre-training) affect multiple well-defined linguistic capabilities. Furthermore, we also demonstrate how our framework can enable evaluation of the invariances shared between models that are available as commercial black-box APIs (e.g., InstructGPT family) and models that are relatively better understood (e.g., GPT-2). Across several experiments, we observe that large language models share many of the invariances encoded by models of various sizes, whereas the invariances encoded by large language models are only shared by other large models. Possessing a wide variety of invariances may be a key reason for the recent successes of large language models, and our framework can shed light on the types of invariances that are retained by or emerge in new models.
Within network data analysis, bipartite networks represent a particular type of network where relationships occur between two disjoint sets of nodes, formally called sending and receiving nodes. In this context, sending nodes may be organized into layers on the basis of some defined characteristics, resulting in a special case of multilayer bipartite network, where each layer includes a specific set of sending nodes. To perform a clustering of sending nodes in multi-layer bipartite network, we extend the Mixture of Latent Trait Analyzers (MLTA), also taking into account the influence of concomitant variables on clustering formation and the multi-layer structure of the data. To this aim, a multilevel approach offers a useful methodological tool to properly account for the hierarchical structure of the data and for the unobserved sources of heterogeneity at multiple levels. A simulation study is conducted to test the performance of the proposal in terms of parameters' and clustering recovery. Furthermore, the model is applied to the European Social Survey data (ESS) to i) perform a clustering of individuals (sending nodes) based on their digital skills (receiving nodes); ii) understand how socio-economic and demographic characteristics influence the individual digitalization level; iii) account for the multilevel structure of the data; iv) obtain a clustering of countries in terms of the base-line attitude to digital technologies of their residents.
Percolation theory investigates systems of interconnected units, their resilience to damage and their propensity to propagation. For random networks we can solve the percolation problems analytically using the generating function formalism. Yet, with the introduction of higher order networks, the generating function calculations are becoming difficult to perform and harder to validate. Here, I illustrate the mapping of percolation in higher order networks to percolation in chygraphs. Chygraphs are defined as a set of complexes where complexes are hypergraphs with vertex sets in the set of complexes. In a previous work I reported the generating function formalism to percolation in chygraphs and obtained an analytical equation for the order parameter. Taking advantage of this result, I recapitulate analytical results for percolation problems in higher order networks and report extensions to more complex scenarios using symbolic calculations. The code for symbolic calculations can be found at //github.com/av2atgh/chygraph.
In this paper, neural network approximation methods are developed for elliptic partial differential equations with multi-frequency solutions. Neural network work approximation methods have advantages over classical approaches in that they can be applied without much concerns on the form of the differential equations or the shape or dimension of the problem domain. When applied to problems with multi-frequency solutions, the performance and accuracy of neural network approximation methods are strongly affected by the contrast of the high- and low-frequency parts in the solutions. To address this issue, domain scaling and residual correction methods are proposed. The efficiency and accuracy of the proposed methods are demonstrated for multi-frequency model problems.
Two-level stochastic optimization formulations have become instrumental in a number of machine learning contexts such as continual learning, neural architecture search, adversarial learning, and hyperparameter tuning. Practical stochastic bilevel optimization problems become challenging in optimization or learning scenarios where the number of variables is high or there are constraints. In this paper, we introduce a bilevel stochastic gradient method for bilevel problems with nonlinear and possibly nonconvex lower-level constraints. We also present a comprehensive convergence theory that addresses both the lower-level unconstrained and constrained cases and covers all inexact calculations of the adjoint gradient (also called hypergradient), such as the inexact solution of the lower-level problem, inexact computation of the adjoint formula (due to the inexact solution of the adjoint equation or use of a truncated Neumann series), and noisy estimates of the gradients, Hessians, and Jacobians involved. To promote the use of bilevel optimization in large-scale learning, we have developed new low-rank practical bilevel stochastic gradient methods (BSG-N-FD and~BSG-1) that do not require second-order derivatives and, in the lower-level unconstrained case, dismiss any matrix-vector products.
Scale-free dynamics, formalized by selfsimilarity, provides a versatile paradigm massively and ubiquitously used to model temporal dynamics in real-world data. However, its practical use has mostly remained univariate so far. By contrast, modern applications often demand multivariate data analysis. Accordingly, models for multivariate selfsimilarity were recently proposed. Nevertheless, they have remained rarely used in practice because of a lack of available robust estimation procedures for the vector of selfsimilarity parameters. Building upon recent mathematical developments, the present work puts forth an efficient estimation procedure based on the theoretical study of the multiscale eigenstructure of the wavelet spectrum of multivariate selfsimilar processes. The estimation performance is studied theoretically in the asymptotic limits of large scale and sample sizes, and computationally for finite-size samples. As a practical outcome, a fully operational and documented multivariate signal processing estimation toolbox is made freely available and is ready for practical use on real-world data. Its potential benefits are illustrated in epileptic seizure prediction from multi-channel EEG data.
The synthesis of information deriving from complex networks is a topic receiving increasing relevance in ecology and environmental sciences. In particular, the aggregation of multilayer networks, i.e. network structures formed by multiple interacting networks (the layers), constitutes a fast-growing field. In several environmental applications, the layers of a multilayer network are modelled as a collection of similarity matrices describing how similar pairs of biological entities are, based on different types of features (e.g. biological traits). The present paper first discusses two main techniques for combining the multi-layered information into a single network (the so-called monoplex), i.e. Similarity Network Fusion (SNF) and Similarity Matrix Average (SMA). Then, the effectiveness of the two methods is tested on a real-world dataset of the relative abundance of microbial species in the ecosystems of nine glaciers (four glaciers in the Alps and five in the Andes). A preliminary clustering analysis on the monoplexes obtained with different methods shows the emergence of a tightly connected community formed by species that are typical of cryoconite holes worldwide. Moreover, the weights assigned to different layers by the SMA algorithm suggest that two large South American glaciers (Exploradores and Perito Moreno) are structurally different from the smaller glaciers in both Europe and South America. Overall, these results highlight the importance of integration methods in the discovery of the underlying organizational structure of biological entities in multilayer ecological networks.
This paper investigates the multiple testing problem for high-dimensional sparse binary sequences, motivated by the crowdsourcing problem in machine learning. We study the empirical Bayes approach for multiple testing on the high-dimensional Bernoulli model with a conjugate spike and uniform slab prior. We first show that the hard thresholding rule deduced from the posterior distribution is suboptimal. Consequently, the $\ell$-value procedure constructed using this posterior tends to be overly conservative in estimating the false discovery rate (FDR). We then propose two new procedures based on $\adj\ell$-values and $q$-values to correct this issue. Sharp frequentist theoretical results are obtained, demonstrating that both procedures can effectively control the FDR under sparsity. Numerical experiments are conducted to validate our theory in finite samples. To our best knowledge, this work provides the first uniform FDR control result in multiple testing for high-dimensional sparse binary data.
Graph representation learning for hypergraphs can be used to extract patterns among higher-order interactions that are critically important in many real world problems. Current approaches designed for hypergraphs, however, are unable to handle different types of hypergraphs and are typically not generic for various learning tasks. Indeed, models that can predict variable-sized heterogeneous hyperedges have not been available. Here we develop a new self-attention based graph neural network called Hyper-SAGNN applicable to homogeneous and heterogeneous hypergraphs with variable hyperedge sizes. We perform extensive evaluations on multiple datasets, including four benchmark network datasets and two single-cell Hi-C datasets in genomics. We demonstrate that Hyper-SAGNN significantly outperforms the state-of-the-art methods on traditional tasks while also achieving great performance on a new task called outsider identification. Hyper-SAGNN will be useful for graph representation learning to uncover complex higher-order interactions in different applications.
Recent advances in 3D fully convolutional networks (FCN) have made it feasible to produce dense voxel-wise predictions of volumetric images. In this work, we show that a multi-class 3D FCN trained on manually labeled CT scans of several anatomical structures (ranging from the large organs to thin vessels) can achieve competitive segmentation results, while avoiding the need for handcrafting features or training class-specific models. To this end, we propose a two-stage, coarse-to-fine approach that will first use a 3D FCN to roughly define a candidate region, which will then be used as input to a second 3D FCN. This reduces the number of voxels the second FCN has to classify to ~10% and allows it to focus on more detailed segmentation of the organs and vessels. We utilize training and validation sets consisting of 331 clinical CT images and test our models on a completely unseen data collection acquired at a different hospital that includes 150 CT scans, targeting three anatomical organs (liver, spleen, and pancreas). In challenging organs such as the pancreas, our cascaded approach improves the mean Dice score from 68.5 to 82.2%, achieving the highest reported average score on this dataset. We compare with a 2D FCN method on a separate dataset of 240 CT scans with 18 classes and achieve a significantly higher performance in small organs and vessels. Furthermore, we explore fine-tuning our models to different datasets. Our experiments illustrate the promise and robustness of current 3D FCN based semantic segmentation of medical images, achieving state-of-the-art results. Our code and trained models are available for download: //github.com/holgerroth/3Dunet_abdomen_cascade.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191