Recently there has been an increasing interest in applying random walk based methods to recommender systems. We employ a Gaussian random field to model the top-N recommendation task as a semi-supervised learning problem, taking into account the degree of each node on the user-item bipartite graph, and induce an effective absorbing random walk (ARW) algorithm for the top-N recommendation task. Our random walk approach directly generates the top-N recommendations for individuals, rather than predicting the ratings of the recommendations. Experimental results on the two real data sets show that our random walk algorithm significantly outperforms the state-of-the-art random walk based personalized ranking algorithm as well as the popular item-based collaborative filtering method. Recently there has been an increasing interest in applying random walk based methods to recommender systems. We employ a Gaussian random field to model the top-N recommendation task as a semi-supervised learning problem, taking into account the degree of each node on the user -item bipartite graph, and induce an effective absorbing random walk (ARW) algorithm for the top-N recommendation task. Our random walk approach directly generate the top-N recommendations for individuals, rather than predicting the ratings of the recommendations. Experimental results on the two real data sets show that our random walk algorithm significantly outperforms the state-of-the-art random walk based solutions ranking algorithm as well as the popular item-based collaborative filtering method.