Rank:pairwise instance weight not supported?

Hi,

I am trying to use lambdamart for pairwise rank.

Refer to here:https://github.com/dmlc/xgboost/blob/master/doc/input_format.md#instance-weight-file. I can give the instance weight in xxx.weight file

After I set the weight for some instance, I found the model, however, still look the same compared to the model trained by all instance weighted the same.

I check out the code in rank_obj.cc and I do not find the weight is used to construct or set the pair.

So...Could you tell me the if the instance weight is supported for LambdaMart?

Thanks!

Attach the code I've checked:

// get lambda weight for the pairs
        this->GetLambdaWeight(lst, &pairs);
        // rescale each gradient and hessian so that the lst have constant weighted
        float scale = 1.0f / param_.num_pairsample;
        if (param_.fix_list_weight != 0.0f) {
          scale *= param_.fix_list_weight / (gptr[k + 1] - gptr[k]);
        }
        for (size_t i = 0; i < pairs.size(); ++i) {
          const ListEntry &pos = lst[pairs[i].pos_index];
          const ListEntry &neg = lst[pairs[i].neg_index];
          const bst_float w = pairs[i].weight * scale;
          const float eps = 1e-16f;
          bst_float p = common::Sigmoid(pos.pred - neg.pred);
          bst_float g = p - 1.0f;
          bst_float h = std::max(p * (1.0f - p), eps);
          // accumulate gradient and hessian in both pid, and nid
          gpair[pos.rindex].grad += g * w;
          gpair[pos.rindex].hess += 2.0f * w * h;
          gpair[neg.rindex].grad -= g * w;
          gpair[neg.rindex].hess += 2.0f * w * h;
}
...
class PairwiseRankObj: public LambdaRankObj{
 protected:
  void GetLambdaWeight(const std::vector<ListEntry> &sorted_list,
                       std::vector<LambdaPair> *io_pairs) override {}
};

dmlc / xgboost

Rank:pairwise instance weight not supported? #2460