Identifying robust survival subgroups of hepatocellular carcinoma (HCC) will significantly improve patient care. Currently, endeavor of integrating multi-omics data to explicitly predict HCC survival from multiple patient cohorts is lacking. To fill in this gap, we present a deep learning (DL) based model on HCC that robustly differentiates survival subpopulations of patients in six cohorts. We build the DL based, survival-sensitive model on 360 HCC patients' data using RNA-seq, miRNA-seq and methylation data from TCGA, which predicts prognosis as good as an alternative model where genomics and clinical data are both considered. This DL based model provides two optimal subgroups of patients with significant survival differences (P=7.13e-6) and good model fitness (C-index=0.68). More aggressive subtype is associated with frequent TP53 inactivation mutations, higher expression of stemness markers (KRT19, EPCAM) and tumor marker BIRC5, and activated Wnt and Akt signaling pathways. We validated this multi-omics model on five external datasets of various omics types: LIRI-JP cohort (n=230, C-index=0.75), NCI cohort (n=221, C-index=0.67), Chinese cohort (n=166, C-index=0.69), E-TABM-36 cohort (n=40, C-index=0.77), and Hawaiian cohort (n=27, C-index=0.82). This is the first study to employ deep learning to identify multi-omics features linked to the differential survival of HCC patients. Given its robustness over multiple cohorts, we expect this workflow to be useful at predicting HCC prognosis prediction.