This work presents KoBigBird-large, a large size of Korean BigBird that achieves state-ofthe-art performance and allows long sequence processing for Korean language understanding. Without further pretraining, we only transform the architecture and extend the positional encoding with our proposed Tapered Absolute Positional Encoding Representations (TAPER). Figure 1: An illustration of building KoBigBird-large In experiments, KoBigBird-large shows stateof-the-art process. Based on the architecture of KoBigBird-base overall performance on Korean language and the parameters of RoBERTa-large, our proposed understanding benchmarks and the best TAPER method is applied to build KoBigBird-large.

Large medical imaging datasets can be cheaply and quickly annotated with low-confidence, weak labels (e.g., radiological scores). Access to high-confidence labels, such as histology-based diagnoses, is rare and costly. Pretraining strategies, like contrastive learning (CL) methods, can leverage unlabeled or weakly-annotated datasets. These methods typically require large batch sizes, which poses a difficulty in the case of large 3D images at full resolution, due to limited GPU memory. Nevertheless, volumetric positional information about the spatial context of each 2D slice can be very important for some medical applications. In this work, we propose an efficient weakly-supervised positional (WSP) contrastive learning strategy where we integrate both the spatial context of each 2D slice and a weak label via a generic kernel-based loss function. We illustrate our method on cirrhosis prediction using a large volume of weakly-labeled images, namely radiological low-confidence annotations, and small strongly-labeled (i.e., high-confidence) datasets. The proposed model improves the classification AUC by 5% with respect to a baseline model on our internal dataset, and by 26% on the public LIHC dataset from the Cancer Genome Atlas.

ChatGPT, as a recently launched large language model (LLM), has shown superior performance in various natural language processing (NLP) tasks. However, two major limitations hinder its potential applications: (1) the inflexibility of finetuning on downstream tasks and (2) the lack of interpretability in the decision-making process. To tackle these limitations, we propose a novel framework that leverages the power of ChatGPT for specific tasks, such as text classification, while improving its interpretability. The proposed framework conducts a knowledge graph extraction task to extract refined and structural knowledge from the raw data using ChatGPT. The rich knowledge is then converted into a graph, which is further used to train an interpretable linear classifier to make predictions. To evaluate the effectiveness of our proposed method, we conduct experiments on four datasets. The result shows that our method can significantly improve the performance compared to directly utilizing ChatGPT for text classification tasks. And our method provides a more transparent decision-making process compared with previous text classification methods.

Abstract--Network alignment (NA) is the task of discovering node correspondences across multiple networks. Although NA methods have achieved remarkable success in a myriad of scenarios, their effectiveness is not without additional information such as prior anchor links and/or node features, which may not always be available due to privacy concerns or access restrictions. To tackle this challenge, we propose Grad-Align+, a novel NA method built upon a recent state-of-the-art NA method, the so-called Grad-Align, that gradually discovers a part of node pairs until all node pairs are found. In designing Grad-Align+, we account for how to augment node features in the sense of performing the NA task and how to design our NA method by maximally exploiting the augmented node features. To achieve this goal, Grad-Align+ consists of three key components: 1) centrality-based node feature augmentation (CNFA), 2) graph neural network (GNN)-aided embedding similarity calculation alongside the augmented node features, and 3) gradual NA with similarity calculation using aligned cross-network neighbor-pairs (ACNs). Through comprehensive experiments, we demonstrate that Grad-Align+ exhibits (a) the superiority over benchmark NA methods, (b) empirical validations as well as our theoretical findings to see the effectiveness of CNFA, (c) the influence of each component, (d) the robustness to network noises, and (e) the computational efficiency.

Community detection becomes an important problem with the booming of social networks. The Medoid-Shift algorithm preserves the benefits of Mean-Shift and can be applied to problems based on distance matrix, such as community detection. One drawback of the Medoid-Shift algorithm is that there may be no data points within the neighborhood region defined by a distance parameter. To deal with the community detection problem better, a new algorithm called Revised Medoid-Shift (RMS) in this work is thus proposed. During the process of finding the next medoid, the RMS algorithm is based on a neighborhood defined by KNN, while the original Medoid-Shift is based on a neighborhood defined by a distance parameter. Since the neighborhood defined by KNN is more stable than the one defined by the distance parameter in terms of the number of data points within the neighborhood, the RMS algorithm may converge more smoothly. In the RMS method, each of the data points is shifted towards a medoid within the neighborhood defined by KNN. After the iterative process of shifting, each of the data point converges into a cluster center, and the data points converging into the same center are grouped into the same cluster. The RMS algorithm is tested on two kinds of datasets including community datasets with known ground truth partition and community datasets without ground truth partition respectively. The experiment results show sthat the proposed RMS algorithm generally produces betster results than Medoid-Shift and some state-of-the-art together with most classic community detection algorithms on different kinds of community detection datasets.

The ability of deep learning methods to perform classification and regression tasks relies heavily on their capacity to uncover manifolds in high-dimensional data spaces and project them into low-dimensional representation spaces. In this study, we investigate the structure and character of the manifolds generated by classical variational autoencoder (VAE) approaches and deep kernel learning (DKL). In the former case, the structure of the latent space is determined by the properties of the input data alone, while in the latter, the latent manifold forms as a result of an active learning process that balances the data distribution and target functionalities. We show that DKL with active learning can produce a more compact and smooth latent space which is more conducive to optimization compared to previously reported methods, such as the VAE. We demonstrate this behavior using a simple cards data set and extend it to the optimization of domain-generated trajectories in physical systems. Our findings suggest that latent manifolds constructed through active learning have a more beneficial structure for optimization problems, especially in feature-rich target-poor scenarios that are common in domain sciences, such as materials synthesis, energy storage, and molecular discovery. The jupyter notebooks that encapsulate the complete analysis accompany the article.

The progress made on the last decade in the field of artificial intelligence (AI) has supported a dramatic increase in the accuracy of most computer vision applications. Medical image analysis is one of the applications where the progress made assured human-level accuracy on the classification of different types of medical data (e.g., chest X-rays [90], corneal images [166]). However, and in spite of these advances, automated medical imaging is seldom adopted in clinical practice. According to Zachary Lipton [77], the explanation to this apparent paradox is straightforward, doctors will never trust the decision of an algorithm without understanding its decision process. This fact has raised the need for producing strategies capable of explaining the decision process of AI algorithms, leading subsequently to the creation of a novel research topic named as eXplainable Artificial Intelligence (XAI). According to DARPA [46], XAI aims to "produce more explainable models, while maintaining a high level of learning performance (prediction accuracy); and enable human users to understand, appropriately, trust, and effectively manage the emerging generation of artificially intelligent partners". In spite of its general applicability, XAI is particularly important in high-stake decisions, such as clinical workflow, where the consequences of a wrong decision could lead to human deaths. This is also evidenced by European Union's General Data Protection

In the quantitative analysis of competitive sports, a fundamental task is to estimate the skills of the different agents ('players') involved in a given competition based on the outcome of pairwise comparisons ('matches') between said players, often in an online setting. Skill estimation facilitates the prediction of various relevant outcomes of subsequent matches, which can then be applied towards high-level decision-making for the competition, including player seeding, fair team matching, and more. There are several established approaches to the task of skill estimation, including among others the Bradley-Terry model (Bradley and Terry, 1952), the Elo rating system (Elo, 1978), the Glicko rating system (Glickman, 1999), and TrueSkill (Herbrich et al., 2006) each with various levels of complexity and varying degrees of statistical motivation. Skill rating is of paramount importance in the world of competitive sports as it serves as a foundational tool for assessing and comparing the abilities of players and how they vary over time. By accurately quantifying skill levels, skill rating systems enable fair and balanced competition, inform strategic decision-making, and enhance the overall sporting level.

Birda co-founders John and Natalie White shared details of their social birding network with Fox News Digital. An AI-powered bird feeder called Bird Buddy doesn't only feed the birds -- it takes candid photos and identifies the species of each bird as it lands for a snack. Bird Buddy CEO Franci Zidar, whose company is based in Kalamazoo, Michigan, told Fox News Digital that the product uses artificial intelligence technology to take clear and "interesting" snapshots of the birds that come to feed. WHAT IS ARTIFICIAL INTELLIGENCE (AI)? The smart bird feeder then detects the type of bird species -- and sends a notification with the photo and bird info to its owner's mobile device.

With the development of pre-trained language models, many prompt-based approaches to data-efficient knowledge graph construction have been proposed and achieved impressive performance. However, existing prompt-based learning methods for knowledge graph construction are still susceptible to several potential limitations: (i) semantic gap between natural language and output structured knowledge with pre-defined schema, which means model cannot fully exploit semantic knowledge with the constrained templates; (ii) representation learning with locally individual instances limits the performance given the insufficient features, which are unable to unleash the potential analogical capability of pre-trained language models. Motivated by these observations, we propose a retrieval-augmented approach, which retrieves schema-aware Reference As Prompt (RAP), for data-efficient knowledge graph construction. It can dynamically leverage schema and knowledge inherited from human-annotated and weak-supervised data as a prompt for each sample, which is model-agnostic and can be plugged into widespread existing approaches. Experimental results demonstrate that previous methods integrated with RAP can achieve impressive performance gains in low-resource settings on five datasets of relational triple extraction and event extraction for knowledge graph construction. Code is available in https://github.com/zjunlp/RAP.