Graph neural networks (GNNs) provide an effective mechanism for enhancing transformer representations by modeling relational structures that sequence-based models cannot directly capture. In this study, a multiview graph neural network enhanced transformer architecture is proposed for cell-type annotation in single-cell RNA sequencing (scRNA-seq) data. The proposed approach models complementary relationships between cells using multiple graph views constructed from the training expression matrix, allowing the GNN component to refine transformer-derived embeddings through neighborhood-based information propagation. By combining transformer-based contextual representations with relational information from multiple graph structures, the framework exploits both structural and feature-level patterns in scRNA-seq data. Experimental results show that the proposed method improves cell-type annotation performance compared with existing approaches.
Y. Ekiz, E. Koç, Aykut Koç· Signal Processing and Commun...· 0 citations
Spatio-temporal time series forecasting is an important task in many areas such as traffic networks, environmental monitoring, and social networks. The goal is to predict future values of signals on the nodes of a graph using past observations. Current temporal encoding methods assume that temporal patterns are the same for all nodes. In practice, however, different nodes can show different temporal behavior depending on where they are in the graph and what their neighbors look like. In this work, we propose Graph-Enhanced Embeddings, a method that produces temporal embeddings based on the node's own signal and its neighbors' signals. The method uses learnable sinusoidal bases and a linear trend term together with a gating mechanism that controls which temporal bases are active for each node. We test the method on three benchmark datasets and show that it consistently outperforms standard baselines including fixed positional encodings, linear features, and Time2Vec.
Hasan Özekin, E. Koç, Aykut Koç· Signal Processing and Commun...· 0 citations