4 papers
GraphFM: A generalist graph transformer that learns transferable representations across diverse domains
Divyansha Lachi, Mehdi Azabou, Vinam Arora +1
Graph neural networks (GNNs) are often trained on individual datasets, requiring specialized models and significant hyperparameter tuning due to the unique structures and features…
Know Thyself by Knowing Others: Learning Neuron Identity from Population Context
Vinam Arora, Divyansha Lachi, Ian J. Knight +5
Neurons process information in ways that depend on their cell type, connectivity, and the brain region in which they are embedded. However, inferring these factors from neural acti…
Integrating Temporal and Structural Context in Graph Transformers for Relational Deep Learning
Divyansha Lachi, Mahmoud Mohammadi, Joe Meyer +3
In domains such as healthcare, finance, and e-commerce, the temporal dynamics of relational data emerge from complex interactions-such as those between patients and providers, or u…
Beyond Black Boxes: Enhancing Interpretability of Transformers Trained on Neural Data
Laurence Freeman, Philip Shamash, Vinam Arora +3
Transformer models have become state-of-the-art in decoding stimuli and behavior from neural activity, significantly advancing neuroscience research. Yet greater transparency in th…