Structural roles define sets of structurally similar nodes that are more similar to nodes inside the set than outside, whereas communities define sets of nodes with more connections inside the set ...than outside. Roles based on structural similarity and communities based on proximity are fundamentally different but important complementary notions. Recently, the notion of structural roles has become increasingly important and has gained a lot of attention due to the proliferation of work on learning representations (node/edge embeddings) from graphs that preserve the notion of roles. Unfortunately, recent work has sometimes confused the notion of structural roles and communities (based on proximity) leading to misleading or incorrect claims about the capabilities of network embedding methods. As such, this article seeks to clarify the misconceptions and key differences between structural roles and communities, and formalize the general mechanisms (e.g., random walks and feature diffusion) that give rise to community- or role-based structural embeddings. We theoretically prove that embedding methods based on these mechanisms result in either community- or role-based structural embeddings. These mechanisms are typically easy to identify and can help researchers quickly determine whether a method preserves community- or role-based embeddings. Furthermore, they also serve as a basis for developing new and improved methods for community- or role-based structural embeddings. Finally, we analyze and discuss applications and data characteristics where community- or role-based embeddings are most appropriate.
We describe wild embeddings of polyhedra into RN which show that the answer to the question of B.J. Baker–M. Laidacker (1989) concerning uncountable families of pairwise disjoint compacta can be ...twofold. The central idea of our construction is the use of specific wild Cantor sets, namely, Antoine–Blankinship–Ivanov necklaces and Krushkal sticky sets. Our basic tools are Antoine's methods and Shtan'ko demension theory.
Display omitted
•We survey methods of representing clinical text using neural networks.•We provide a “how-to” guide for training these representations on clinical text.•We describe word models, ...corpora, evaluation methods, and applications.
Representing words as numerical vectors based on the contexts in which they appear has become the de facto method of analyzing text with machine learning. In this paper, we provide a guide for training these representations on clinical text data, using a survey of relevant research. Specifically, we discuss different types of word representations, clinical text corpora, available pre-trained clinical word vector embeddings, intrinsic and extrinsic evaluation, applications, and limitations of these approaches. This work can be used as a blueprint for clinicians and healthcare workers who may want to incorporate clinical text features in their own models and applications.
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 a rank that is 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.
Recently, the widespread application of pre-trained language models (PLMs) such as BERT and RoBERTa has significantly enhanced the performance of tasks related to text semantic similarity. However, ...methods solely based on PLMs inadequately account for the differential information between sentence pairs, thus underestimating the importance of this information in sentence matching. In this paper, we propose the enriching Differential information with External Knowledge framework (DEK), an approach that explicitly extracts differential information and enriches semantics using external knowledge. Specifically, we devise a module for extracting differential words from sentence pairs, obtain synonyms of differential words from WordNet, and construct a differential information graph. We employ Graph Convolutional Networks (GCNs) to extract features from this graph and subsequently integrate this information into sentence embeddings. In this work, we demonstrate that incorporating differential information enables PLMs-based methods to better focus on the differing aspects of sentences. Moreover, DEK seamlessly adapts to contrastive learning of sentence embeddings models, including SimCSE and PromptBert, among others. Comparing to baseline, our method has improved spearman correlation between 0.22 and 0.64, yielding competitive results in the experiments.
•Information fusion of features and class labels in a common representation space.•Novel contrastive learning architectures and loss functions.•Samples form clusters around their label prototypes in ...embedding space.•Significant reduction in number of pairwise comparisons (avoids negative sampling).•Novel classifiers suitable for noisy and unbalanced datasets (intrusion detection).
Contrastive learning makes it possible to establish similarities between samples by comparing their distances in an intermediate representation space (embedding space) and using loss functions designed to attract/repel similar/dissimilar samples. The distance comparison is based exclusively on the sample features. We propose a novel contrastive learning scheme by including the labels in the same embedding space as the features and performing the distance comparison between features and labels in this shared embedding space. Following this idea, the sample features should be close to its ground-truth (positive) label and away from the other labels (negative labels). This scheme allows to implement a supervised classification based on contrastive learning. Each embedded label will assume the role of a class prototype in embedding space, with sample features that share the label gathering around it. The aim is to separate the label prototypes while minimizing the distance between each prototype and its same-class samples. A novel set of loss functions is proposed with this objective. Loss minimization will drive the allocation of sample features and labels in embedding space. Loss functions and their associated training and prediction architectures are analyzed in detail, along with different strategies for label separation. The proposed scheme drastically reduces the number of pair-wise comparisons, thus improving model performance. In order to further reduce the number of pair-wise comparisons, this initial scheme is extended by replacing the set of negative labels by its best single representative: either the negative label nearest to the sample features or the centroid of the cluster of negative labels. This idea creates a new subset of models which are analyzed in detail.
The outputs of the proposed models are the distances (in embedding space) between each sample and the label prototypes. These distances can be used to perform classification (minimum distance label), features dimensionality reduction (using the distances and the embeddings instead of the original features) and data visualization (with 2 or 3D embeddings).
Although the proposed models are generic, their application and performance evaluation is done here for network intrusion detection, characterized by noisy and unbalanced labels and a challenging classification of the various types of attacks. Empirical results of the model applied to intrusion detection are presented in detail for two well-known intrusion detection datasets, and a thorough set of classification and clustering performance evaluation metrics are included.
Display omitted
•High performance clinical information extraction supports pertinent clinical research.•Multi-site hospital natural language processing models scale across settings.•Flexible informatics empowers ...fast clinician lead research and analysis.•Fast, scalable, flexible electronic health record information extraction.
Electronic health records (EHR) contain large volumes of unstructured text, requiring the application of information extraction (IE) technologies to enable clinical analysis. We present the open source Medical Concept Annotation Toolkit (MedCAT) that provides: (a) a novel self-supervised machine learning algorithm for extracting concepts using any concept vocabulary including UMLS/SNOMED-CT; (b) a feature-rich annotation interface for customizing and training IE models; and (c) integrations to the broader CogStack ecosystem for vendor-agnostic health system deployment. We show improved performance in extracting UMLS concepts from open datasets (F1:0.448–0.738 vs 0.429–0.650). Further real-world validation demonstrates SNOMED-CT extraction at 3 large London hospitals with self-supervised training over ∼8.8B words from ∼17M clinical records and further fine-tuning with ∼6K clinician annotated examples. We show strong transferability (F1 > 0.94) between hospitals, datasets and concept types indicating cross-domain EHR-agnostic utility for accelerated clinical and research use cases.