search

yingtaoluo / Spatial-Temporal-Attention-Network-for-POI-Recommendation

Codes for a WWW'21 Paper. POI recommender system for location/trajectory prediction.
https://doi.org/10.1145/3442381.3449998
164 stars 39 forks source link

Where are the evaluation results of other methods reported in the paper from? #22

Closed yeliudev closed 1 year ago

yeliudev commented 2 years ago

Hi @yingtaoluo, may I ask that did you reproduce other methods (e.g. GeoSAN, LSTPM, etc.) on exactly the same datasets you used for STAN, or did you just copy the results from elsewhere? I notice that almost all the papers in POI recommendation use their own dataset pre-processing methods, and did not mention where are the results of other methods from. Thanks!

yeliudev commented 2 years ago

@yingtaoluo

yingtaoluo commented 1 year ago

Yes, it is indeed a problem. There are very few open source codes as well. Just hope some people may find it useful to build upon STAN's code (although awful & ugly, TBH) to write their own model, especially those that are starters in the area. We use the same preprocessing, since different preprocessing for different methods can be painfully time-costly.