With the rapidly increasing application of large language models (LLMs), their abuse has caused many undesirable societal problems such as fake news, academic dishonesty, and information pollution. This makes AI-gener...
详细信息
Decentralized online social networks such as Mastodon have emerged quickly during the past years, and offer unique opportunities to investigate user behavior, moderation strategies, and community evolution. However, t...
详细信息
ISBN:
(纸本)9798400713316
Decentralized online social networks such as Mastodon have emerged quickly during the past years, and offer unique opportunities to investigate user behavior, moderation strategies, and community evolution. However, their decentralized nature imposes challenges for data collection and preprocessing, particularly for obtaining a real-time snapshot in a timely manner. This paper introduces FediLive, a framework designed to rapidly collect and preprocess the live feeds from Mastodon, generate a comprehensive snapshot in real-time, including user-generated contents, interaction networks, and users' demographic attributes. Such a snapshot could further be leveraged for data analysis from different angles, leading to a deeper understanding of user activities on Mastodon. Using FediLive, we collected a 13-day snapshot of Mastodon, covering the publicly-visible activities of all Mastodon users. Our study demonstrates the usefulness of FediLive, and reveals its potential in facilitating data-driven analysis for decentralized online social networks.
Manually annotating anatomical landmarks in medical images requires experienced clinicians and is a labor-intensive process. However, recent AI-assisted methods for landmark detection often rely on the training and te...
详细信息
This paper explores test-agnostic long-tail recognition, a challenging long-tail task where the test label distributions are unknown and arbitrarily imbalanced. We argue that the variation in these distributions can b...
详细信息
This paper explores test-agnostic long-tail recognition, a challenging long-tail task where the test label distributions are unknown and arbitrarily imbalanced. We argue that the variation in these distributions can be broken down hierarchically into global and local levels. The global ones reflect a broad range of diversity, while the local ones typically arise from milder changes, often focused on a particular neighbor. Traditional methods predominantly use a Mixture-of-Expert (MoE) approach, targeting a few fixed test label distributions that exhibit substantial global variations. However, the local variations are left unconsidered. To address this issue, we propose a new MoE strategy, DirMixE, which assigns experts to different Dirichlet meta-distributions of the label distribution, each targeting a specific aspect of local variations. Additionally, the diversity among these Dirichlet meta-distributions inherently captures global variations. This dual-level approach also leads to a more stable objective function, allowing us to sample different test distributions better to quantify the mean and variance of performance outcomes. Theoretically, we show that our proposed objective benefits from enhanced generalization by virtue of the variance-based regularization. Comprehensive experiments across multiple benchmarks confirm the effectiveness of DirMixE. The code is available at https://***/scongl/DirMixE. Copyright 2024 by the author(s)
Multi-modal Video Object Segmentation (VOS), including RGB-Thermal, RGB-Depth, and RGB-Event, has garnered attention due to its capability to address challenging scenarios where traditional VOS methods struggle, such ...
详细信息
Personalized news headline generation, aiming at generating user-specific headlines based on readers’ preferences, burgeons a recent flourishing research direction. Existing studies generally inject a user interest e...
Personalized news headline generation, aiming at generating user-specific headlines based on readers’ preferences, burgeons a recent flourishing research direction. Existing studies generally inject a user interest embedding into an encoder-decoder headline generator to make the output personalized, while the factual consistency of headlines is inadequate to be verified. In this paper, we propose a framework Fact-Preserved Personalized News Headline Generation (short for FPG), to prompt a tradeoff between personalization and consistency. In FPG, the similarity between the candidate news to be exposed and the historical clicked news is used to give different levels of attention to key facts in the candidate news, and the similarity scores help to learn a fact-aware global user embedding. Besides, an additional training procedure based on contrastive learning is devised to further enhance the factual consistency of generated headlines. Extensive experiments conducted on a real-world benchmark PENS 1 validate the superiority of FPG, especially on the tradeoff between personalization and factual consistency. 1 https://***/***
When tracking densely distributed targets such as insects, the traditional trajectory association algorithm exhibits poor correlation performance, leading to a decline in multi-target tracking efficiency. In this pape...
详细信息
Magnetic topological semimetals have been at the forefront of condensed matter physics due to their ability to exhibit exotic transport *** the interplay between magnetic and topological orders in systems with broken ...
详细信息
Magnetic topological semimetals have been at the forefront of condensed matter physics due to their ability to exhibit exotic transport *** the interplay between magnetic and topological orders in systems with broken time-reversal symmetry is crucial for realizing non-trivial quantum *** delve into the electronic structure of the rare-earth-based antiferromagnetic Dirac semimetal EuMg_(2)Bi_(2) using first-principles calculations and angle-resolved photoemission *** calculations reveal that the spin-orbit coupling(SOC)in EuMg_(2)Bi_(2) prompts an insulator to topological semimetal transition,with the Dirac bands protected by crystal *** linearly dispersive states near the Fermi level,primarily originating from Bi 6p orbitals,are observed on both the(001)and(100)surfaces,confirming that EuMg_(2)Bi_(2) is a three-dimensional topological Dirac *** research offers pivotal insights into the interplay between magnetism,SOC and topological phase transitions in spintronics applications.
Rockfall events occur frequently in mountainous areas. To address the problems of missed detection, false detection, and trajectory interruption when using the deep learning-based online multiple object tracking metho...
详细信息
Despite the Graph Neural Networks' (GNNs) pro-ficiency in analyzing graph data, achieving high-accuracy and interpretable predictions remains challenging. Existing GNN interpreters typically provide post-hoc expla...
详细信息
ISBN:
(数字)9798350317152
ISBN:
(纸本)9798350317169
Despite the Graph Neural Networks' (GNNs) pro-ficiency in analyzing graph data, achieving high-accuracy and interpretable predictions remains challenging. Existing GNN interpreters typically provide post-hoc explanations disjointed from GNNs' predictions, resulting in misrepresentations. Self-explainable GNNs offer built-in explanations during the training process. However, they cannot exploit the explanatory outcomes to augment prediction performance, and they fail to provide high-quality explanations of node features and require additional processes to generate explainable subgraphs, which is costly. To address the aforementioned limitations, we propose a self-explained and self-supervised graph neural network (SES) to bridge the gap between explainability and prediction. SES comprises two processes: explainable training and enhanced predictive learning. During explainable training, SES employs a global mask generator co-trained with a graph encoder and directly produces crucial structure and feature masks, reducing time consumption and providing node feature and subgraph explanations. In the enhanced predictive learning phase, mask-based positive-negative pairs are constructed utilizing the ex-planations to compute a triplet loss and enhance the node representations by contrastive learning. Extensive experiments demonstrate the superiority of SES on multiple datasets and tasks. SES outperforms baselines on real-world node classification datasets by notable margins of up to 2.59% and achieves state-of-the-art (SOTA) performance in explanation tasks on synthetic datasets with improvements of up to 3.0%. Moreover, SES delivers more coherent explanations on real-world datasets, has a fourfold increase in Fidelity+ score for explanation quality, and demonstrates faster training and expla-nation generating times. To our knowledge, SES is a pioneering GNN to achieve SOTA performance on both explanation and prediction tasks.
暂无评论