rjagerman / sigir2020

Accelerated Confergence for Counterfactual Learning to Rank

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Accelerated Convergence for Counterfactual Learning to Rank

ℹ️ This software uses PyTorchLTR. Check it out here!

Source code with our SIGIR2020 paper. To run all experiments, build the plots and create the tables that appear in the paper run the following:

export YAHOO_DIR=/path/to/yahoo/set1/
export ISTELLA_DIR=/path/to/istella/sample/
make -j$(nproc)

Or, if you are on macOS:

export YAHOO_DIR=/path/to/yahoo/set1/
export ISTELLA_DIR=/path/to/istella/sample/
make -j$(sysctl -n hw.logicalcpu)

This can take significant amount of time depending on the number of CPU cores available.

About

Accelerated Confergence for Counterfactual Learning to Rank


Languages

Language:Python 64.2%Language:Makefile 35.8%