RESUMEN
Knowledge graph reasoning, vital for addressing incompleteness and supporting applications, faces challenges with the continuous growth of graphs. To address this challenge, several inductive reasoning models for encoding emerging entities have been proposed. However, they do not consider the multi-batch emergence scenario, where new entities and new facts are usually added to knowledge graphs (KGs) in multiple batches in the order of their emergence. To simulate the continuous growth of knowledge graphs, a novel multi-batch emergence (MBE) scenario has recently been proposed. We propose a path-based inductive model to handle multi-batch entity growth, enhancing entity encoding with type information. Specifically, we observe a noteworthy pattern in which entity types at the head and tail of the same relation exhibit relative regularity. To utilize this regularity, we introduce a pair of learnable parameters for each relation, representing entity type features linked to the relation. The type features are dedicated to encoding and updating the features of entities. Meanwhile, our model incorporates a novel attention mechanism, combining statistical co-occurrence and semantic similarity of relations effectively for contextual information capture. After generating embeddings, we employ reinforcement learning for path reasoning. To reduce sparsity and expand the action space, our model generates soft candidate facts by grounding a set of soft path rules. Meanwhile, we incorporate the confidence scores of these facts in the action space to facilitate the agent to better distinguish between original facts and rule-generated soft facts. Performances on three multi-batch entity growth datasets demonstrate robust performance, consistently outperforming state-of-the-art models.
RESUMEN
Epilepsies are a group of neurological disorders characterized by abnormal spontaneous brain activity, involving multiscale changes in brain functional organizations. However, it is not clear to what extent the epilepsy-related perturbations of spontaneous brain activity affect macroscale intrinsic dynamics and microcircuit organizations, that supports their pathological relevance. We collect a sample of patients with temporal lobe epilepsy (TLE) and genetic generalized epilepsy with tonic-clonic seizure (GTCS), as well as healthy controls. We extract massive temporal features of fMRI BOLD time-series to characterize macroscale intrinsic dynamics, and simulate microcircuit neuronal dynamics used a large-scale biological model. Here we show whether macroscale intrinsic dynamics and microcircuit dysfunction are differed in epilepsies, and how these changes are linked. Differences in macroscale gradient of time-series features are prominent in the primary network and default mode network in TLE and GTCS. Biophysical simulations indicate reduced recurrent connection within somatomotor microcircuits in both subtypes, and even more reduced in GTCS. We further demonstrate strong spatial correlations between differences in the gradient of macroscale intrinsic dynamics and microcircuit dysfunction in epilepsies. These results emphasize the impact of abnormal neuronal activity on primary network and high-order networks, suggesting a systematic abnormality of brain hierarchical organization.