Chinese Whispers 聚类算法

Chinese Whispers 聚类算法用于当你不知道有多少个类时。他的基本算法步骤是：

1，对于所有节点v，都赋值一个初始的类class（vi）=i

2，随机选取一个节点vt，找到v所有的临接节点，对临接节点所属的类进行打分。例如一个节点1的临接节点有2,3,4,5,分别属于a,b,c,b类别，边1-2,1-3,1-4,1-5的权值都为1，那么类a的得分就是1，类b得分2，类c得分1

3，将得分最高的类别赋值给vt

4，返回2

下面上dlib的代码进行解析：

  inline unsigned long chinese_whispers (
        const std::vector<ordered_sample_pair>& edges,
        std::vector<unsigned long>& labels,
        const unsigned long num_iterations,
        dlib::rand& rnd
    )
    {
        // make sure requires clause is not broken，传进来的边集需要排好序
        DLIB_ASSERT(is_ordered_by_index(edges),
                    "\t unsigned long chinese_whispers()"
                    << "\n\t Invalid inputs were given to this function"
        );

        labels.clear();
        if (edges.size() == 0)
            return 0;

        std::vector<std::pair<unsigned long, unsigned long> > neighbors;
        find_neighbor_ranges(edges, neighbors);

        // Initialize the labels, each node gets a different label.
        
        labels.resize(neighbors.size());
        for (unsigned long i = 0; i < labels.size(); ++i)
            labels[i] = i;


        for (unsigned long iter = 0; iter < neighbors.size()*num_iterations; ++iter)
        {
            // Pick a random node.随机挑选一个节点
            const unsigned long idx = rnd.get_random_64bit_number()%neighbors.size();

            // Count how many times each label happens amongst our neighbors.对节点的临接几点所属的类别进行统计打分
            std::map<unsigned long, double> labels_to_counts;
            const unsigned long end = neighbors[idx].second;
            for (unsigned long i = neighbors[idx].first; i != end; ++i)
            {
                labels_to_counts[labels[edges[i].index2()]] += edges[i].distance();
            }

            // find the most common label.找到得分最高的类，并给该节点归类
            std::map<unsigned long, double>::iterator i;
            double best_score = -std::numeric_limits<double>::infinity();
            unsigned long best_label = labels[idx];
            for (i = labels_to_counts.begin(); i != labels_to_counts.end(); ++i)
            {
                if (i->second > best_score)
                {
                    best_score = i->second;
                    best_label = i->first;
                }
            }

            labels[idx] = best_label;
        }


        // Remap the labels into a contiguous range.  First we find the
        // mapping.因为上述找到的类别可能不是连续的0,1,2,3...,需要对类别进行重新映射为连续的编号
        std::map<unsigned long,unsigned long> label_remap;
        for (unsigned long i = 0; i < labels.size(); ++i)
        {
            const unsigned long next_id = label_remap.size();
            if (label_remap.count(labels[i]) == 0)
                label_remap[labels[i]] = next_id;
        }
        // now apply the mapping to all the labels.给所有节点赋值类别
        for (unsigned long i = 0; i < labels.size(); ++i)
        {
            labels[i] = label_remap[labels[i]];
        }

        return label_remap.size();
    }

相关参考论文

《Chinese Whispers - an Efficient Graph Clustering Algorithm and its Application to Natural Language Processing Problems》