社会&信息网络学术速递[1.10]
Update!H5支持摘要折叠,体验更佳!点击阅读原文访问arxivdaily.com,涵盖CS|物理|数学|经济|统计|金融|生物|电气领域,更有搜索、收藏等功能!
cs.SI社会&信息网络,共计3篇
【1】 Project IRL: Playful Co-Located Interactions with Mobile Augmented Reality
标题:IRL项目:与移动增强现实进行有趣的协同交互
链接:https://arxiv.org/abs/2201.02558
摘要:We present Project IRL (In Real Life), a suite of five mobile apps we created
to explore novel ways of supporting in-person social interactions with
augmented reality. In recent years, the tone of public discourse surrounding
digital technology has become increasingly critical, and technology's influence
on the way people relate to each other has been blamed for making people feel
"alone together," diverting their attention from truly engaging with one
another when they interact in person. Motivated by this challenge, we focus on
an under-explored design space: playful co-located interactions. We evaluated
the apps through a deployment study that involved interviews and participant
observations with 101 people. We synthesized the results into a series of
design guidelines that focus on four themes: (1) device arrangement (e.g., are
people sharing one phone, or does each person have their own?), (2) enablers
(e.g., should the activity focus on an object, body part, or pet?), (3)
affordances of modifying reality (i.e., features of the technology that enhance
its potential to encourage various aspects of social interaction), and (4)
co-located play (i.e., using technology to make in-person play engaging and
inviting). We conclude by presenting our design guidelines for future work on
embodied social AR.
【2】 MGAE: Masked Autoencoders for Self-Supervised Learning on Graphs
标题:MGAE:用于图的自监督学习的屏蔽自动编码器
链接:https://arxiv.org/abs/2201.02534
摘要:We introduce a novel masked graph autoencoder (MGAE) framework to perform
effective learning on graph structure data. Taking insights from
self-supervised learning, we randomly mask a large proportion of edges and try
to reconstruct these missing edges during training. MGAE has two core designs.
First, we find that masking a high ratio of the input graph structure, e.g.,
$70\%$, yields a nontrivial and meaningful self-supervisory task that benefits
downstream applications. Second, we employ a graph neural network (GNN) as an
encoder to perform message propagation on the partially-masked graph. To
reconstruct the large number of masked edges, a tailored cross-correlation
decoder is proposed. It could capture the cross-correlation between the head
and tail nodes of anchor edge in multi-granularity. Coupling these two designs
enables MGAE to be trained efficiently and effectively. Extensive experiments
on multiple open datasets (Planetoid and OGB benchmarks) demonstrate that MGAE
generally performs better than state-of-the-art unsupervised learning
competitors on link prediction and node classification.
【3】 Modeling International Mobility using Roaming Cell Phone Traces during COVID-19 Pandemic
标题:利用冠状病毒大流行期间漫游手机痕迹模拟国际流动性
链接:https://arxiv.org/abs/2201.02470
摘要:Most of the studies related to human mobility are focused on intra-country
mobility. However, there are many scenarios (e.g., spreading diseases,
migration) in which timely data on international commuters are vital. Mobile
phones represent a unique opportunity to monitor international mobility flows
in a timely manner and with proper spatial aggregation. This work proposes
using roaming data generated by mobile phones to model incoming and outgoing
international mobility. We use the gravity and radiation models to capture
mobility flows before and during the introduction of non-pharmaceutical
interventions. However, traditional models have some limitations: for instance,
mobility restrictions are not explicitly captured and may play a crucial role.
To overtake such limitations, we propose the COVID Gravity Model (CGM), namely
an extension of the traditional gravity model that is tailored for the pandemic
scenario. This proposed approach overtakes, in terms of accuracy, the
traditional models by 126.9% for incoming mobility and by 63.9% when modeling
outgoing mobility flows.
机器翻译,仅供参考
点击“阅读原文”获取带摘要的学术速递