{"id":25215606,"url":"https://github.com/deezer/recsys21-hlr","last_synced_at":"2025-10-25T14:31:23.605Z","repository":{"id":48435672,"uuid":"386650703","full_name":"deezer/recsys21-hlr","owner":"deezer","description":"Hierarchical Latent Relation Modeling for Collaborative Metric Learning","archived":false,"fork":false,"pushed_at":"2021-09-24T09:37:55.000Z","size":57,"stargazers_count":6,"open_issues_count":1,"forks_count":3,"subscribers_count":7,"default_branch":"main","last_synced_at":"2024-04-16T11:27:18.185Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/deezer.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2021-07-16T13:42:03.000Z","updated_at":"2024-04-16T11:27:18.186Z","dependencies_parsed_at":"2022-08-31T15:31:51.430Z","dependency_job_id":null,"html_url":"https://github.com/deezer/recsys21-hlr","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/deezer%2Frecsys21-hlr","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/deezer%2Frecsys21-hlr/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/deezer%2Frecsys21-hlr/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/deezer%2Frecsys21-hlr/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/deezer","download_url":"https://codeload.github.com/deezer/recsys21-hlr/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":238161490,"owners_count":19426669,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-02-10T18:15:07.717Z","updated_at":"2025-10-25T14:31:18.173Z","avatar_url":"https://github.com/deezer.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Hierarchical Latent Relation Modeling for Collaborative Metric Learning\n\nThis repository provides Python code to reproduce experiments from our paper:\n\n\u003e V-A. Tran, G. Salha-Galvan, R. Hennequin and M. Moussallam. Hierarchical Latent Relation Modeling for Collaborative Metric Learning. In: *Proceedings of the 15th ACM Conference on Recommender Systems (RecSys 2021)*, September 2021.\n\n\n## Environment\n- python 3.6.9\n- tensorflow 1.15\n- numpy 1.18.1\n- scipy 1.6.2\n- sklearn 0.22.2\n- pandas 1.0.1\n- toolz 0.11.1\n- implicit 0.4.4\n\n## Datasets\nThe following datasets are considered in our work that could be easily downloaded from Internet and put in `exp/data` directory \n- Movielens 20M (https://grouplens.org/datasets/movielens/20m/)\n- Echonest (http://millionsongdataset.com/sites/default/files/challenge/train_triplets.txt.zip)\n- Yelp (https://www.kaggle.com/yelp-dataset/yelp-dataset)\n- Amazon Book (https://jmcauley.ucsd.edu/data/amazon/)\n\n## Hyperparameters\nBest hyperparameters that we found through grid-search for each model on each dataset are reported in the corresponding configuration file in `configs` directory\n\n## Experiments\nAll experiment scripts for train / evaluation of our models and other baselines described in the paper could be found in `scripts` directory.\n\nYou could do the following steps to run experiment:\n1. Download data and put it into `exp/data` directory. For example `exp/data/ml-20m` for Movielens 20M.\n2. Change data path and interaction file name in configuration file (for example `configs/mvlens/10-core/cml/*.json`).\n3. Run experiment script (that contains both train and evaluation commands) in `scripts` directory\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdeezer%2Frecsys21-hlr","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdeezer%2Frecsys21-hlr","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdeezer%2Frecsys21-hlr/lists"}