Protein-protein interactions (PPIs) are central to understanding cellular mechanisms and disease pathogenesis. While conventional graph-based models have achieved significant success in predicting PPIs, they are limited to pairwise interactions, failing to capture higher-order relational patterns prevalent in biological systems. In this study, we propose HGNN-PPI, a novel framework that integrates hypergraph neural networks with traditional graph neural models to enhance multi-label PPI prediction. Our method combines three complementary perspectives: global graph structure, local subgraph features, and higher-order interaction motifs modeled through a hypergraph constructed from biologically meaningful feedforward and feedback loops. To address the class imbalance inherent in PPI datasets, we use an asymmetric loss function tailored for multi-label learning. Experimental results on benchmark datasets (SHS27k and SHS148k) demonstrate that HGNN-PPI consistently outperforms state-of-the-art methods, particularly in capturing rare interaction types. These findings highlight the effectiveness of incorporating higher-order biological motifs and hypergraph structures in improving PPI prediction.

Temporal Knowledge Graphs (TKGs) organize dynamic real-world facts, adding a time dimension to the multi-relational graph structure of Knowledge Graphs (KGs).We leverage the expressive power of graph convolutional networks (GCNs) for modeling TKGs, recognizing similarities with handling graph-structured data and utilizing complex geometry.Our approach emphasizes compositional interactions between relations and entities, integrating a diachronic mechanism to enhance representation with both graph structure and temporal dynamics.Experimental results on benchmark datasets, employing various composition operators, showcase the effectiveness of our model in link prediction tasks.

Knowledge graph link prediction has been researched for many years.With the steady development of data, the demand for missing link prediction in knowledge bases is growing.In this study, we propose FouriER, a model using Fourier transforms integrated into MetaFormer architecture to learn features from embeddings better but more computationally cost-effective than the self-attention mechanism in Transformer models.Furthermore, we transform embeddings to a 2D form and stack them that benefit the model in learning interactions between entities and relations more efficiently.As a result, we found that our model outperformed baseline models on two benchmark datasets in our experiments.

Identifying features to represent graphs such as social networks, protein graphs is increasingly common in both research and business communities, thanks to the fact that data has increased not only in quantity but also in complexity. This results in the graphs to be sparser because not all nodes a re fully connected. In addition, if this whole graph is used as input data for learning algorithms e.g. neural network, a lot of training time will be required. Substantial efforts have been made to convert the graphs to better yet compact representations, among of which is graph embedding. The traditional methods used to map the original graph to its embedding representation had not yielded significant results until deep learning was invented. Many good approaches in this direction, as examples, are DeepWalk, node2vec. However, their general weakness is many important connections in the original graph could be lost. In this paper, we propose another approach to retain more edge information while ensuring the embedding graph is still sufficiently small, compared to the original one. Our experiment results show that the method also increases the accuracy of latter learning models.