Ultra-dense networking is widely accepted as a promising enabling technology to realize high power and spectrum efficient communications in future 5G communication systems. Although joint resource allocation schemes promise huge performance improvement at the cost of cooperation among base stations,the large numbers of user equipment and base station make jointly optimizing the available resource very challenging and even prohibitive. How to decompose the resource allocation problem is a critical issue. In this paper,we exploit factor graphs to design a distributed resource allocation algorithm for ultra dense networks,which consists of power allocation,subcarrier allocation and cell association. The proposed factor graph based distributed algorithm can decompose the joint optimization problem of resource allocation into a series of low complexity subproblems with much lower dimensionality,and the original optimization problem can be efficiently solved via solving these subproblems iteratively. In addition,based on the proposed algorithm the amounts of exchanging information overhead between the resulting subprob-lems are also reduced. The proposed distributed algorithm can be understood as solving largely dimensional optimization problem in a soft manner,which is much preferred in practical scenarios. Finally,the performance of the proposed low complexity distributed algorithm is evaluated by several numerical results. Ultra-dense networking is widely accepted as a promising enabling technology to realize high power and spectrum efficient communications in future 5G communication systems. and base station make jointly optimizing the available resource very challenging and even prohibitive. How to decompose the resource allocation problem is a critical issue. In this paper, we exploit factor graphs to design a distributed resource allocation algorithm for ultra dense networks, which consists of power allocation, subcarrier allocation and cell association. The proposed factor graph based distributed algorithm can decompose the joint optimization problem of resource allocation into a series of low complexity subproblems with much lower dimensionality, and the original optimization problem can be for solved solved via these subproblems ite ratively. In addition, based on the proposed algorithm the amounts of exchanging information overhead between the resulting subprob-lems are also reduced. The proposed distributed algorithm can be understood as drastically optimizing problem in a soft manner, which is much preferred in practical Finally, the performance of the proposed low complexity distributed algorithm is evaluated by several numerical results.