Spatio-temporal graph learning is a fundamental problem in the Web of Things
era, which enables a plethora of Web applications such as smart cities, human
mobility and climate analysis. Existing approaches tackle different learning
tasks independently, tailoring their models to unique task characteristics.
These methods, however, fall short of modeling intrinsic uncertainties in the
spatio-temporal data. Meanwhile, their specialized designs limit their
universality as general spatio-temporal learning solutions. In this paper, we
propose to model the learning tasks in a unified perspective, viewing them as
predictions based on conditional information with shared spatio-temporal
patterns. Based on this proposal, we introduce Unified Spatio-Temporal
Diffusion Models (USTD) to address the tasks uniformly within the
uncertainty-aware diffusion framework. USTD is holistically designed,
comprising a shared spatio-temporal encoder and attention-based denoising
networks that are task-specific. The shared encoder, optimized by a
pre-training strategy, effectively captures conditional spatio-temporal
patterns. The denoising networks, utilizing both cross- and self-attention,
integrate conditional dependencies and generate predictions. Opting for
forecasting and kriging as downstream tasks, we design Gated Attention (SGA)
and Temporal Gated Attention (TGA) for each task, with different emphases on
the spatial and temporal dimensions, respectively. By combining the advantages
of deterministic encoders and probabilistic diffusion models, USTD achieves
state-of-the-art performances compared to deterministic and probabilistic
baselines in both tasks, while also providing valuable uncertainty estimates.

在这篇论文中，我们提出了统一的时空扩散模型（USTD），以条件信息和共享的时空模式为基础，统一地处理学习任务。USTD 综合设计了共享的时空编码器和基于注意力的去噪网络，有效捕捉条件时空模式并生成预测。与确定性编码器和概率扩散模型的优点相结合，USTD 在预测和 Kriging 的下游任务中取得了最先进的性能，并提供了宝贵的不确定性估计。

融合扩散模型的概率时空图学习方法

Towards Unifying Diffusion Models for Probabilistic Spatio-Temporal  Graph Learning

Graph data structures are widely used to store relational information between
several entities. With data being generated worldwide on a large scale, we see
a significant growth in the generation of knowledge graphs. Thing in the future
is Orange's take on a knowledge graph in the domain of the Web Of Things (WoT),
where the main objective of the platform is to provide a digital representation
of the physical world and enable cross-domain applications to be built upon
this massive and highly connected graph of things. In this context, as the
knowledge graph grows in size, it is prone to have noisy and messy data. In
this paper, we explore state-of-the-art knowledge graph embedding (KGE) methods
to learn numerical representations of the graph entities and, subsequently,
explore downstream tasks like link prediction, node classification, and triple
classification. We also investigate Graph neural networks (GNN) alongside KGEs
and compare their performance on the same downstream tasks. Our evaluation
highlights the encouraging performance of both KGE and GNN-based methods on
node classification, and the superiority of GNN approaches in the link
prediction task. Overall, we show that state-of-the-art approaches are relevant
in a WoT context, and this preliminary work provides insights to implement and
evaluate them in this context.

通过对知识图谱和图神经网络的研究，我们发现在物联网领域中，采用最新技术的方法在节点分类任务中表现出色，并且图神经网络在链接预测任务方面具有优势。这项初步工作在物联网环境中实现和评估最新方法提供了有价值的见解。

关于知识图谱嵌入和图神经网络在物联网中的研究

A Study on Knowledge Graph Embeddings and Graph Neural Networks for Web  Of Things

In the past few years, the Web of Things (WOT) became a beneficial
game-changing technology within the Agriculture domain as it introduces
innovative and promising solutions to the Internet of Things (IoT) agricultural
applications problems by providing its services. WOT provides the support for
integration, interoperability for heterogeneous devices, infrastructures,
platforms, and the emergence of various other technologies. The main aim of
this study is about understanding and providing a growing and existing research
content, issues, and directions for the future regarding WOT-based agriculture.
Therefore, a systematic literature review (SLR) of research articles is
presented by categorizing the selected studies published between 2010 and 2020
into the following categories: research type, approaches, and their application
domains. Apart from reviewing the state-of-the-art articles on WOT solutions
for the agriculture field, a taxonomy of WOT-base agriculture application
domains has also been presented in this study. A model has also presented to
show the picture of WOT based Smart Agriculture. Lastly, the findings of this
SLR and the research gaps in terms of open issues have been presented to
provide suggestions on possible future directions for the researchers for
future research.

本文通过系统文献综述方法，总结了 Web of things 在农业领域的应用类型、方法和应用领域，并提出了一种基于 WOT 的智能农业模型，最后给出了研究亟需解决的问题和未来研究方向的建议。