Numerous　significant　temporal　graph　tasks,　such　as　graph　similarity　ranking,　trend　analysis　and　anomaly　detection,　necessitate　low-dimensional　and　high-order　graph-level　embedding　in　terms　of　the　evolving　nodes　and　topologies　over　time.　However,　most　existing　graph　embedding　methods　focus　on　extracting　node-level　embeddings,　while　ignoring　these　evolutions.　Therefore,　these　methods　inadequately　consider　the　impact　of　trends　on　the　overall　graph.　Moreover,　there　are　a　large　number　of　nodes　in　temporal　graphs,　which　make　it　difficult　to　generate　effective　graph　embeddings　directly　by　aggregating　dynamic　node　embeddings.　In　this　study,　we　propose　a　novel　temporal　attention　network　for　learning　graph-level　embedding　learning　called　GraphTAN.　Specifically,　the　proposed　model　employs　pooling　attention　to　select　crucial　nodes　and　filter　out　noisy　ones　for　each　snapshot,　thereby　enhancing　the　quality　of　aggregated　graph　embeddings.　Furthermore,　we　design　a　graph-level　temporal　attention　mechanism　to　effectively　extract　temporal　graph　embeddings,　capturing　trends　and　patterns　across　snapshots.　The　proposed　model　is　evaluated　on　three　downstream　tasks.　Experimental　results　demonstrate　that　GraphTAN　captures　both　the　topology　structure　and　fine-grained　trend　effectively,　outperforming　the　state-of-the-art　methods　with　big　margins　on　multiple　tasks　over　several　real　networks.