Interpretable brain decoding from sensations to cognition to action: graph neural networks reveal the representational hierarchy of human cognition

Inter-subject modeling of cognitive processes has been a challenging task due to large individual variability in brain structure and function. Graph neural networks (GNNs) provide a potential way to project subject-specific neural responses onto a common representational space by effectively combining local and distributed brain activity through connectome-based constraints. Here we provide in-depth interpretations of biologically-constrained GNNs (BGNNs) that reach state-of-the-art performance in several decoding tasks and reveal inter-subject aligned neural representations underpinning cognitive processes. Specifically, the model not only segregates brain responses at different stages of cognitive tasks, e.g. motor preparation and motor execution, but also uncovers functional gradients in neural representations, e.g. a gradual progression of visual working memory (VWM) from sensory processing to cognitive control and towards behavioral abstraction. Moreover, the multilevel representations of VWM exhibit better inter-subject alignment in brain responses, higher decoding of cognitive states, and strong phenotypic and genetic correlations with individual behavioral performance. Our work demonstrates that biologically constrained deep-learning models have the potential towards both cognitive and biological fidelity in cognitive modeling, and open new avenues to interpretable functional gradients of brain cognition in a wide range of cognitive neuroscience questions. HighlightsO_LIBGNN improves inter-subject alignment in task-evoked responses and promotes brain decoding C_LIO_LIBGNN captures functional gradients of brain cognition, transforming from sensory processing to cognition to representational abstraction. C_LIO_LIBGNNs with diffusion or functional connectome constraints better predict human behaviors compared to other graph architectures C_LI Graphic Abstract O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=181 SRC="FIGDIR/small/510241v1_ufig1.gif" ALT="Figure 1"> View larger version (71K): org.highwire.dtl.DTLVardef@1b34a13org.highwire.dtl.DTLVardef@1c45ca2org.highwire.dtl.DTLVardef@9db47dorg.highwire.dtl.DTLVardef@1b4916d_HPS_FORMAT_FIGEXP M_FIG C_FIG Multilevel representational learning of cognitive processes using BGNN