paper-with-me

홈 › Papers

Gaussian Embedding of Temporal Networks

2024-05-27 · Raphaël Romero, Jefrey Lijffijt, Riccardo Rastelli, Marco Corneli, Tijl De Bie

Representing the nodes of continuous-time temporal graphs in a low-dimensional latent space has wide-ranging applications, from prediction to visualization. Yet, analyzing continuous-time relational data with timestamped interactions introduces unique challenges due to its sparsity. Merely embedding nodes as trajectories in the latent space overlooks this sparsity, emphasizing the need to quantify uncertainty around the latent positions. In this paper, we propose TGNE (\textbf{T}emporal \textbf{G}aussian \textbf{N}etwork \textbf{E}mbedding), an innovative method that bridges two distinct strands of literature: the statistical analysis of networks via Latent Space Models (LSM)\cite{Hoff2002} and temporal graph machine learning. TGNE embeds nodes as piece-wise linear trajectories of Gaussian distributions in the latent space, capturing both structural information and uncertainty around the trajectories. We evaluate TGNE's effectiveness in reconstructing the original graph and modelling uncertainty. The results demonstrate that TGNE generates competitive time-varying embedding locations compared to common baselines for reconstructing unobserved edge interactions based on observed edges. Furthermore, the uncertainty estimates align with the time-varying degree distribution in the network, providing valuable insights into the temporal dynamics of the graph. To facilitate reproducibility, we provide an open-source implementation of TGNE at \url{https://github.com/aida-ugent/tgne}.

📄 PDF Abstract BibTeX arXiv:2405.17253

Code (1)

aida-ugent/tgne 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

GM-CTSC at SemEval-2020 Task 1: Gaussian Mixtures Cross Temporal Similarity Clustering

2020-05-20 · SEMEVAL 2020 · Pierluigi Cassotti, Annalina Caputo, Marco Polignano, Pierpaolo Basile

This paper describes the system proposed for the SemEval-2020 Task 1: Unsupervised Lexical Semantic Change Detection. We focused our approach on the detection problem. Given the semantics of words captured by temporal wo…

Change DetectionClusteringWord Embeddings

Temporal Knowledge Graph Embedding based on Multivariate Gaussian Process

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Recently, reasoning over Temporal Knowledge Graph (TKG), such as link prediction, has become an attractive research topic. Numerous Temporal Knowledge Graph Embedding (TKGE) methods have been proposed to map the entitie…

Gaussian ProcessesGraph EmbeddingKnowledge Graph EmbeddingLink Prediction

Per-Gaussian Embedding-Based Deformation for Deformable 3D Gaussian Splatting

2024-04-04 · Jeongmin Bae, Seoha Kim, Youngsik Yun, Hahyun Lee 외

As 3D Gaussian Splatting (3DGS) provides fast and high-quality novel view synthesis, it is a natural extension to deform a canonical 3DGS to multiple frames for representing a dynamic scene. However, previous works fail …

3DGSAttributeNovel View Synthesis

Director: Instance-aware Gaussian Splatting for Dynamic Scene Modeling and Understanding

2026-04-02 · Yuheng Jiang, Yiwen Cai, Zihao Wang, Yize Wu 외 arxiv

Volumetric video seeks to model dynamic scenes as temporally coherent 4D representations. While recent Gaussian-based approaches achieve impressive rendering fidelity, they primarily emphasize appearance but are largely …

Instance SegmentationScene Understanding

Temporal Knowledge Graph Embedding Model based on Additive Time Series Decomposition

2019-11-18 · Chengjin Xu, Mojtaba Nayyeri, Fouad Alkhoury, Hamed Shariat Yazdi 외

Knowledge Graph (KG) embedding has attracted more attention in recent years. Most KG embedding models learn from time-unaware triples. However, the inclusion of temporal information beside triples would further improve t…

Graph EmbeddingKnowledge Graph CompletionKnowledge Graph EmbeddingLink Prediction+4