Graph Neural Networks for temporal graphs: State of the art, open challenges, and opportunities

Longa, Antonio; Lachi, Veronica; Santin, Gabriele; Bianchini, Monica; Lepri, Bruno; Lió, Píetro; Scarselli, Franco; Passerini, Andrea

doi:10.48550/arxiv.2302.01018

Cited by 2 publications

(2 citation statements)

References 43 publications

(70 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These include univariate time series models [24,25], similarity-based methods [26], probabilistic generative models [27][28][29][30], and matrix and tensor factorization [31]. Nevertheless, with the success of deep learning and representation learning on static graphs, recent approaches have shifted towards using neural networks, as surveyed by Kazemi et al [9] and Longa et al [10]. Notably, memory-based dynamic graph neural networks (DGNNs) such as TGN [21] and DyRep [32], use an encoder-decoder architecture.…”

Section: Methods For Dlp (Dynamic) Linkmentioning

confidence: 99%

“…The resulting types of data are commonly referred to as Continuous-Time Dynamic Graphs (CTDGs) [8]. Modeling and forecasting CTDGs have recently become very active fields of research, as suggested by recent surveys [9,10]. A crucial task of interest is Dynamic Link Prediction (DLP), where the goal is to predict future links from a history of observed ones.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Exploring the Performance of Continuous-Time Dynamic Link Prediction Algorithms

Romero,

Buyl,

De Bie

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

Dynamic Link Prediction (DLP) addresses the prediction of future links in evolving networks. However, accurately portraying the performance of DLP algorithms poses challenges that might impede progress in the field. Importantly, common evaluation pipelines usually calculate ranking or binary classification metrics, where the scores of observed interactions (positives) are compared with those of randomly generated ones (negatives). However, a single metric is not sufficient to fully capture the differences between DLP algorithms, and is prone to overly optimistic performance evaluation. Instead, an in-depth evaluation should reflect performance variations across different nodes, edges, and time segments. In this work, we contribute tools to perform such a comprehensive evaluation. (1) We propose Birth–Death diagrams, a simple but powerful visualization technique that illustrates the effect of time-based train–test splitting on the difficulty of DLP on a given dataset. (2) We describe an exhaustive taxonomy of negative sampling methods that can be used at evaluation time. (3) We carry out an empirical study of the effect of the different negative sampling strategies. Our comparison between heuristics and state-of-the-art memory-based methods on various real-world datasets confirms a strong effect of using different negative sampling strategies on the test area under the curve (AUC). Moreover, we conduct a visual exploration of the prediction, with additional insights on which different types of errors are prominent over time.

show abstract

Section: Methods For Dlp (Dynamic) Linkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Exploring the Performance of Continuous-Time Dynamic Link Prediction Algorithms

Romero,

Buyl,

De Bie

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

Discrete-time graph neural networks for transaction prediction in Web3 social platforms

Dileo,

Zignani

2024

Mach Learn

View full text Add to dashboard Cite

In Web3 social platforms, i.e. social web applications that rely on blockchain technology to support their functionalities, interactions among users are usually multimodal, from common social interactions such as following, liking, or posting, to specific relations given by crypto-token transfers facilitated by the blockchain. In this dynamic and intertwined networked context, modeled as a financial network, our main goals are (i) to predict whether a pair of users will be involved in a financial transaction, i.e. the transaction prediction task, even using textual information produced by users, and (ii) to verify whether performances may be enhanced by textual content. To address the above issues, we compared current snapshot-based temporal graph learning methods and developed T3GNN, a solution based on state-of-the-art temporal graph neural networks’ design, which integrates fine-tuned sentence embeddings and a simple yet effective graph-augmentation strategy for representing content, and historical negative sampling. We evaluated models in a Web3 context by leveraging a novel high-resolution temporal dataset, collected from one of the most used Web3 social platforms, which spans more than one year of financial interactions as well as published textual content. The experimental evaluation has shown that T3GNN consistently achieved the best performance over time and for most of the snapshots. Furthermore, through an extensive analysis of the performance of our model, we show that, despite the graph structure being crucial for making predictions, textual content contains useful information for forecasting transactions, highlighting an interplay between users’ interests and economic relationships in Web3 platforms. Finally, the evaluation has also highlighted the importance of adopting sampling methods alternative to random negative sampling when dealing with prediction tasks on temporal networks.

show abstract

Graph Neural Networks for temporal graphs: State of the art, open challenges, and opportunities

Cited by 2 publications

References 43 publications

Exploring the Performance of Continuous-Time Dynamic Link Prediction Algorithms

Exploring the Performance of Continuous-Time Dynamic Link Prediction Algorithms

Discrete-time graph neural networks for transaction prediction in Web3 social platforms

Contact Info

Product

Resources

About