Gene　selection　is　an　attractive　and　important　task　in　cancer　survival　analysis.　Most　existing　supervised　learning　methods　can　only　use　the　labeled　biological　data,　while　the　censored　data　(weakly　labeled　data)　far　more　than　the　labeled　data　are　ignored　in　model　building.　Trying　to　utilize　such　information　in　the　censored　data,　a　semi-supervised　learning　framework　(Cox-AFT　model)　combined　with　Cox　proportional　hazard　(Cox)　and　accelerated　failure　time　(AFT)　model　was　used　in　cancer　research,　which　has　better　performance　than　the　single　Cox　or　AFT　model.　This　method,　however,　is　easily　affected　by　noise.　To　alleviate　this　problem,　in　this　paper　we　combine　the　Cox-AFT　model　with　self-paced　learning　(SPL)　method　to　more　effectively　employ　the　information　in　the　censored　data　in　a　self-learning　way.　SPL　is　a　kind　of　reliable　and　stable　learning　mechanism,　which　is　recently　proposed　for　simulating　the　human　learning　process　to　help　the　AFT　model　automatically　identify　and　include　samples　of　high　confidence　into　training,　minimizing　interference　from　high　noise.　Utilizing　the　SPL　method　produces　two　direct　advantages:　(1)　The　utilization　of　censored　data　is　further　promoted;　(2)　the　noise　delivered　to　the　model　is　greatly　decreased.　The　experimental　results　demonstrate　the　effectiveness　of　the　proposed　model　compared　to　the　traditional　Cox-AFT　model.