Knowledge Graphs (KGs) and heterogeneous graphs (HGs) offer a principled way to represent multi-entity, multi-relational systems, while also revealing a persistent tension between expressive modeling, scalable learning, and faithful reasoning.Two trends are rapidly reshaping the field: graph foundation models (GFMs), which seek transfer across graphs, tasks, and domains via large-scale pretraining, and the growing integration of large language models (LLMs) with graph-structured knowledge to improve grounding, interaction, and reasoning.Temporal settings add further challenges, as evolving facts and interactions demand time-consistent modeling and evaluation.This tutorial provides a structured survey of these directions: we introduce a unified background and notation for typed heterogeneous graphs, (temporal) KGs, and event-based temporal heterogeneous graphs; we then formalize the main task families (KG completion, query answering, node/graph prediction, and temporal variants), emphasizing evaluation protocols and leakage pitfalls.Finally, we review recent advances in GFMs and LLM-graph integration, and summarize the state of the art in learning over temporal heterogeneous graphs and temporal KGs.

Abstract Modeling the temporal evolution of biological systems is fundamental for understanding cellular dynamics and anticipating future functional states. While temporal graph neural networks (TGNNs) have achieved remarkable success in social and financial domains, their evaluation on dynamic biological systems remains largely unexplored. In this work, we provide the first systematic benchmark of discrete-time temporal graph neural networks on dynamic protein-protein interaction (PPI) networks, considering both future link prediction and future gene expression forecasting as complementary structure- and node-level tasks. To capture the recurring and synchronized nature of biological dynamics, we introduce State-Memory Temporal Graph Neural Networks (SM-TGNN), a novel architecture that augments message passing with a compact state-memory mechanism designed to model recurrent structural regimes without relying on sequential recurrent units. Across multiple yeast PPI datasets, SM-TGNN achieves consistently competitive performance in predicting future protein interactions and gene expression profiles, matching or exceeding existing neural approaches across most evaluation settings. At the same time, the strong results obtained by memory-based baselines indicate that temporal link prediction in dynamic biological networks remains a particularly challenging task, requiring models capable of capturing recurrent interaction regimes and long-term temporal dependencies. Notably, a model pre-trained on one PPI network achieves competitive performance when transferred to a distinct yeast cell-cycle dataset, suggesting that the learned state representations capture recurring temporal structures that can partially generalize across related biological settings. Furthermore, SM-TGNN offers competitive inference-time and memory efficiency compared to standard TGNN architectures. Our results demonstrate that state-based temporal modeling provides an effective and scalable inductive bias for learning from dynamic biological networks, opening new directions for temporal graph learning as an AI-driven simulation of cellular processes.

Temporal Heterogeneous Networks (THNs) are evolving networks that characterize many real-world applications such as citation and events networks, recommender systems, and knowledge graphs. Forecasting THNs involves predicting future connections within a network that evolves over time and comprises diverse types of nodes and interactions with varying temporal dynamics. Although some Graph Neural Networks (GNNs) models have been successfully applied to forecast THNs, there is a lack of a general overview of how the message-passing computation could be extended to treat THNs. Moreover, most of the current solutions exhibit pitfalls in their training and evaluation strategies. Hence, in this work, we propose a graph deep learning framework for THN forecasting. Our framework decomposes the computation of a GNN layer into multiple components and introduces two different schemes to update embedding representations for THNs. This design allows the classification of existing solutions into special instances of our framework and highlights their potential limitations. We also extend the set of benchmarks for THNs by introducing two novel high-resolution temporal heterogeneous graph datasets derived from an emerging Web3 platform and a well-established e-commerce website. Overall, we conducted the first massive evaluation of THNs solutions over four temporal heterogeneous network datasets on two different future link prediction tasks using a fair newly introduced evaluation setting that considers the evolving nature of the data. Based on the limitations of existing solutions, we develop a new model that combines working techniques from previous models and leverages a new embedding update scheme. Experiments show the prediction power of our model compared to current solutions for link prediction in temporal graphs. Moreover, the experimental evaluation highlights the strengths and weaknesses of the different solutions and shows the effectiveness of our framework design.

The problem of link prediction in temporal knowledge graphs (TKGs) consists of finding missing links in the knowledge base under temporal constraints.Recently, [4] and [8] proposed a solution to the problem inspired by the canonical decomposition of 4-order tensors, where they regularise the representations of time steps by learning similar transformation for adjacent timestamps.However, the impact of the choice of temporal regularisation terms is still poorly understood.In this work, we systematically analyse several choices of temporal regularisers using linear functions and recurrent architectures.In our experiments, we show that by carefully selecting the temporal regulariser and regularisation weight, a simple method like TNTComplEx [4] can produce comparable results with state-of-the-art methods and enhance its original performance.Specifically, we observe that linear regularisers for temporal smoothing based on specific nuclear norms can significantly improve the predictive accuracy of the base temporal link prediction methods.

The convergence of network science and artificial intelligence (AI) represents a rich area of research, where both fields can mutually enhance one another.Network science offers a comprehensive framework to analyze and model complex relationships, while machine learning (ML) and AI provide powerful tools for recognizing patterns and making predictions from large datasets.Combining these two disciplines can advance the study of complex systems and lead to new innovations in data-driven research.This tutorial paper reviews fundamental concepts of network science, describes the current and promising research direction for bridging network science and AI, and summarizes the contributions that have been accepted for publication in the ESANN 2025 special session on the topic.

User migration (i.e., the movement of large sets of users from one online social platform to another one) is one of the main phenomena occurring in modern online social networks and even involves the most recent alternative paradigms of online social networks, such as blockchain-based online social networks. In these platforms, user migration mainly occurs through hard forks of the supporting blockchain (i.e., a split of the original blockchain and the creation of an alternative blockchain), to which users may decide to migrate. However, our understanding of user migration and its mechanisms is still limited, particularly regarding the role of densely connected user groups (communities) during migration and fork events. Are there differences between users who stay and those who decide to leave, in terms of network structure and discussion topics? In this work, we show, through network-based analysis centered on the identification of communities on multilayer networks and text mining that (a) the “position” of a group within the network of social and economic interactions is connected to the likelihood of a group to migrate (i.e., marginal groups are more likely to leave); (b) group network structure is also important, as users in densely connected groups interacting through monetary transactions are more likely to stay; (c) users who leave are characterized by different discussion topics; and (d) user groups interacting through monetary transactions show interest in migration-related content if they are going to leave. These findings highlight the importance of social and economic relationships between users during a user migration caused by fork events In general, in the larger context of online social media, it motivates the need to investigate user migration through a network-inspired approach based on groups and specific subgraphs while leveraging user-generated content, at the same time.

Abstract User migration in online social networks represents a critical phenomenon that can reshape platform dynamics and lead to abrupt structural changes, often triggered by technical, social, or competitive factors. In the context of blockchain-based online social networks, migration events can be particularly disruptive when triggered by hard forks - fundamental splits in the underlying blockchain protocol that create two incompatible versions of the platform. However, understanding how users adapt their behavior before, during, and after such events remains a challenging research question. To address this challenge, we rely on the framework of graph representation learning, with a particular focus on Temporal Graph Neural Networks (TGNNs). In particular, we analyze how node representations returned by TGNNs evolve during the migration event and examine how representation shifts can mirror changes in users’ behavioral patterns and platform interactions. Our study focuses on Steemit, a blockchain-based social network that experienced a significant user migration following a hard fork in its supporting blockchain infrastructure. Our findings highlight that both the prediction performance and node representation are influenced by the occurrence of the migration event. We detect shifts in node representations that correspond to changes in individual user behavior throughout the event. Furthermore, group-centric analysis reveals changes in behavior and memberships among similar users during different transition periods. Additionally, we find a level of polarization in node representations caused by the migration event, which gradually diminishes over time, resulting in more evenly distributed dimensions of node representations months after the first migration. We compare our approach against two baselines based on network statistics and pre-trained LLM embeddings, showing that TGNNs better capture the distribution shift derived by the migration. To summarize, this work offers valuable insights into user behavior dynamics during platform migrations, demonstrating the effectiveness of temporal graph learning approaches in analyzing such transitions in an automated manner.

Link prediction is one of the most well-known and studied problems in graph machine learning, successfully applied in different settings, such as predicting network evolution in online social networks, protein-to-protein interactions, or completing links in knowledge graphs.In recent years, we have witnessed several solutions based on deep learning methods for solving this task in the context of temporal networks.However, despite their effectiveness on static graphs, traditional heuristic-based approaches from network science research have never been considered potential benchmarks' baselines.For this reason, in this work, we tested four of the most well-known and simple heuristics for link prediction on the most adopted temporal graph benchmark (TGB).Our results show that simple link prediction heuristics can reach comparable results with state-of-the-art deep learning techniques and, thanks to their interpretability, give insights into the network being studied.We believe considering heuristic-based baselines will push the temporal graph learning community toward better models for link prediction.

Abstract 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.

Abstract Link prediction in Online Social Networks—OSNs—has been the focus of numerous studies in the machine learning community. A successful machine learning-based solution for this task needs to (i) leverage global and local properties of the graph structure surrounding links; (ii) leverage the content produced by OSN users; and (iii) allow their representations to change over time, as thousands of new links between users and new content like textual posts, comments, images and videos are created/uploaded every month. Current works have successfully leveraged the structural information but only a few have also taken into account the textual content and/or the dynamicity of network structure and node attributes. In this paper, we propose a methodology based on temporal graph neural networks to handle the challenges described above. To understand the impact of textual content on this task, we provide a novel pipeline to include textual information alongside the structural one with the usage of BERT language models, dense preprocessing layers, and an effective post-processing decoder. We conducted the evaluation on a novel dataset gathered from an emerging blockchain-based online social network, using a live-update setting that takes into account the evolving nature of data and models. The dataset serves as a useful testing ground for link prediction evaluation because it provides high-resolution temporal information on link creation and textual content, characteristics hard to find in current benchmark datasets. Our results show that temporal graph learning is a promising solution for dynamic link prediction with text. Indeed, combining textual features and dynamic Graph Neural Networks—GNNs—leads to the best performances over time. On average, the textual content can enhance the performance of a dynamic GNN by 3.1% and, as the collection of documents increases in size over time, help even models that do not consider the structural information of the network.