Tracking students' historical interactions to predict their future performance is a critical research focus in the field of Knowledge Tracing （KT）. Recent KT methods aim to explore students' learning patterns and evolving knowledge states to provide personalized learning guidance， but ignore the richness of exercises themselves. Additionally， with the emergence of new disciplines and interdisciplinary fields， Graph Neural Network （GNN） -based KT methods face challenges in the issues such as broadening the scope of concept associations and modeling students' learning behaviors. To address these challenges， a novel Knowledge Tracing （KT） model was proposed， termed the Knowledge Tracking model based on concept association Memory network with Graph Attention （GAMKT）. The GAMKT is capable of modeling students' exercise interaction sequences， tracking their knowledge states， and capturing global features of related concepts from the exercise-concept graph. Moreover， a forgetting gate and higher-order information extraction were incorporated into the model to realistically simulate students' exercise-solving processes. Experimental results on the Junyi， ASSIST09， and Static2011 datasets demonstrate that， compared with seven baseline models including Graph-based Knowledge Tracing （GKT）， GAMKT achieves average improvements of approximately 2.1% in Area Under the Curve （AUC） and 2.4% in Accuracy， indicating that GAMKT outperforms the baseline methods on datasets with well-structured knowledge.