Merge branch 'main' of https://github.com/AKSW/frankgraphbench into main

Author: paulorvdc

config_files/test_entity2rec.yml

@@ -1,5 +1,21 @@
 experiment:
-  dataset:
+  # dataset:
+  #   name: ml-100k
+  #   item: # infos related to item dataset (mandatory, at least item_id)
+  #     path: datasets/ml-100k/processed/item.csv
+  #     extra_features: [movie_year, movie_title] # features(columns) beside item_id to be used
+  #   user: # mandatory (at least user_id)
+  #     path: datasets/ml-100k/processed/user.csv
+  #     extra_features: [gender, occupation] # features beside user_id
+  #   ratings: # mandatory (at least [user_id, item_id, rating])
+  #     path: datasets/ml-100k/processed/rating.csv
+  #     timestamp: True
+  #   enrich:
+  #     map_path: datasets/ml-100k/processed/map.csv
+  #     enrich_path: datasets/ml-100k/processed/enriched.csv
+  #     remove_unmatched: False
+  #     properties: [subject, director, abstract]
+  # dataset:
     # name: ml-100k
     # item: # infos related to item dataset (mandatory, at least item_id)
     #   path: datasets/ml-100k/processed/item.csv
@@ -15,6 +31,23 @@ experiment:
     #   enrich_path: datasets/ml-100k/processed/enriched.csv
     #   remove_unmatched: False
     #   properties: [subject, director, abstract]
+  # dataset:
+  #   name: douban-movie
+  #   item: # infos related to item dataset (mandatory, at least item_id)
+  #     path: datasets/douban-movie/processed/item.csv
+  #     extra_features: [name_EN, name_CN] # features(columns) beside item_id to be used
+  #   user: # mandatory (at least user_id)
+  #     path: datasets/douban-movie/processed/user.csv
+  #     extra_features: [name]
+  #   ratings: # mandatory (at least [user_id, item_id, rating])
+  #     path: datasets/douban-movie/processed/rating.csv
+  #     timestamp: False
+  #   enrich:
+  #     map_path: datasets/douban-movie/processed/map.csv
+  #     enrich_path: datasets/douban-movie/processed/enriched.csv
+  #     remove_unmatched: False
+  #     properties: [subject, director, abstract]
+  dataset:
     name: ml-1m
     item: # infos related to item dataset (mandatory, at least item_id)
       path: datasets/ml-1m/processed/item.csv

docs/source/benchmark_results/results.md

@@ -262,6 +262,7 @@ Experiment ran using the Douban Movie dataset with the following presented model
 |RotatE based model + cosine similarity;embedding_dim=200;epochs=25;seed=42;triples=all|.4091 ± .0024|.4882 ± .0066|
 |EPHEN based model + cosine similarity;embedding_model=sentence-transformers/all-roberta-large-v1;embed_with=abstract;iterations=30;mi=0.5|.4517 ± .0078|.5284 ± .0045|
 |EPHEN based model + cosine similarity;embedding_model=deepwalk_based;embedding_model_kwargs={'walk_len': 10, 'p': 1.0, 'q': 1.0, 'n_walks': 50, 'embedding_size': 64, 'epochs': 1};embed_with=graph;iterations=30;mi=0.5|.5833 ± .0043|.6755 ± .0059|
+|Entity2Rec;embedding_model=deepwalk_based;embedding_model_kwargs={'config': {'save_weights': True}, 'parameters': {'walk_len': 10, 'p': 1.0, 'q': 1.0, 'n_walks': 50, 'embedding_size': 64, 'epochs': 1}};run_all=False;workers=6;iterations=1;collab_only=False;content_only=False|.4142 ± .0084|.4971 ± .0120|
 
 - Summarized execution time results from `experiment_results/douban-movie_times.csv` (configuration: CPU: AMD EPYC 7502P 32-Core Processor; RAM: 94GB; GPUs: ['NVIDIA A2']):
 
@@ -280,6 +281,7 @@ Experiment ran using the Douban Movie dataset with the following presented model
 |RotatE based model + cosine similarity;embedding_dim=200;epochs=25;seed=42;triples=all|51.02 ± 1.804|
 |EPHEN based model + cosine similarity;embedding_model=sentence-transformers/all-roberta-large-v1;embed_with=abstract;iterations=30;mi=0.5|47.73 ± .6584|
 |EPHEN based model + cosine similarity;embedding_model=deepwalk_based;embedding_model_kwargs={'walk_len': 10, 'p': 1.0, 'q': 1.0, 'n_walks': 50, 'embedding_size': 64, 'epochs': 1};embed_with=graph;iterations=30;mi=0.5|41.90 ± .5456|
+|Entity2Rec;embedding_model=deepwalk_based;embedding_model_kwargs={'config': {'save_weights': True}, 'parameters': {'walk_len': 10, 'p': 1.0, 'q': 1.0, 'n_walks': 50, 'embedding_size': 64, 'epochs': 1}};run_all=False;workers=6;iterations=1;collab_only=False;content_only=False|9479. ± 301.5|
 
 ## douban-movie_enriched
 
@@ -302,6 +304,7 @@ Experiment ran using the Douban Movie dataset with DBpedia enrichement and the f
 |RotatE based model + cosine similarity;embedding_dim=200;epochs=25;seed=42;triples=all|.4086 ± .0016|.4895 ± .0028|
 |EPHEN based model + cosine similarity;embedding_model=sentence-transformers/all-roberta-large-v1;embed_with=abstract;iterations=30;mi=0.5|.3876 ± .0038|.4601 ± .0036|
 |EPHEN based model + cosine similarity;embedding_model=deepwalk_based;embedding_model_kwargs={'walk_len': 10, 'p': 1.0, 'q': 1.0, 'n_walks': 50, 'embedding_size': 64, 'epochs': 1};embed_with=graph;iterations=30;mi=0.5|.5736 ± .0018|.6617 ± .0061|
+|Entity2Rec;embedding_model=deepwalk_based;embedding_model_kwargs={'config': {'save_weights': True}, 'parameters': {'walk_len': 10, 'p': 1.0, 'q': 1.0, 'n_walks': 50, 'embedding_size': 64, 'epochs': 1}};run_all=False;workers=6;iterations=1;collab_only=False;content_only=False|.4184 ± .0137|.5016 ± .0119|
 
 - Summarized execution time results from `experiment_results/douban-movie_times_enriched.csv` (configuration: CPU: AMD Ryzen 5 7600 6-Core Processor; RAM: 31GB; GPUs: ['NVIDIA GeForce RTX 4060']):
 
@@ -320,6 +323,7 @@ Experiment ran using the Douban Movie dataset with DBpedia enrichement and the f
 |RotatE based model + cosine similarity;embedding_dim=200;epochs=25;seed=42;triples=all|56.15 ± 2.132|
 |EPHEN based model + cosine similarity;embedding_model=sentence-transformers/all-roberta-large-v1;embed_with=abstract;iterations=30;mi=0.5|51.79 ± 43.51|
 |EPHEN based model + cosine similarity;embedding_model=deepwalk_based;embedding_model_kwargs={'walk_len': 10, 'p': 1.0, 'q': 1.0, 'n_walks': 50, 'embedding_size': 64, 'epochs': 1};embed_with=graph;iterations=30;mi=0.5|22.54 ± 1.364|
+|Entity2Rec;embedding_model=deepwalk_based;embedding_model_kwargs={'config': {'save_weights': True}, 'parameters': {'walk_len': 10, 'p': 1.0, 'q': 1.0, 'n_walks': 50, 'embedding_size': 64, 'epochs': 1}};run_all=False;workers=6;iterations=1;collab_only=False;content_only=False|9266. ± 104.2|
 
 ## yelp
 

experiment_results/e2rec_runs/douban-movie_e2rec.csv

@@ -0,0 +1,2 @@
+model,fold-1_MAP@5,fold-1_nDCG@5,fold-2_MAP@5,fold-2_nDCG@5,fold-3_MAP@5,fold-3_nDCG@5,fold-4_MAP@5,fold-4_nDCG@5,fold-5_MAP@5,fold-5_nDCG@5,MAP@5_mean,MAP@5_std,nDCG@5_mean,nDCG@5_std
+"Entity2Rec;embedding_model=deepwalk_based;embedding_model_kwargs={'config': {'save_weights': True}, 'parameters': {'walk_len': 10, 'p': 1.0, 'q': 1.0, 'n_walks': 50, 'embedding_size': 64, 'epochs': 1}};run_all=False;workers=6;iterations=1;collab_only=False;content_only=False",0.4105331517980636,0.48672990839951147,0.40854317946058083,0.4868725010055903,0.42564185684647304,0.5129007103252039,0.40384055152143844,0.4885086054859211,0.42257196576763484,0.5106693610587183,0.41422614107883815,0.008411492724372147,0.497136217254989,0.011997800157152056

experiment_results/e2rec_runs/douban-movie_e2rec_enriched.csv

@@ -0,0 +1,2 @@
+model,fold-1_MAP@5,fold-1_nDCG@5,fold-2_MAP@5,fold-2_nDCG@5,fold-3_MAP@5,fold-3_nDCG@5,fold-4_MAP@5,fold-4_nDCG@5,fold-5_MAP@5,fold-5_nDCG@5,MAP@5_mean,MAP@5_std,nDCG@5_mean,nDCG@5_std
+"Entity2Rec;embedding_model=deepwalk_based;embedding_model_kwargs={'config': {'save_weights': True}, 'parameters': {'walk_len': 10, 'p': 1.0, 'q': 1.0, 'n_walks': 50, 'embedding_size': 64, 'epochs': 1}};run_all=False;workers=6;iterations=1;collab_only=False;content_only=False",0.44417098893499307,0.5217049886360081,0.4078887880359613,0.48562344447310024,0.4211730636237898,0.505050238433362,0.41000907676348547,0.49645125155499237,0.4089944242738589,0.4992771363263755,0.4184472683264177,0.01371991694967513,0.5016214118847676,0.01185974749863876

experiment_results/e2rec_runs/douban-movie_e2rec_enriched_times.csv

@@ -0,0 +1,2 @@
+model,fold-1_execution_time,fold-2_execution_time,fold-3_execution_time,fold-4_execution_time,fold-5_execution_time,execution_time_mean,execution_time_std
+"Entity2Rec;embedding_model=deepwalk_based;embedding_model_kwargs={'config': {'save_weights': True}, 'parameters': {'walk_len': 10, 'p': 1.0, 'q': 1.0, 'n_walks': 50, 'embedding_size': 64, 'epochs': 1}};run_all=False;workers=6;iterations=1;collab_only=False;content_only=False (CPU: AMD Ryzen 5 7600 6-Core Processor; RAM: 31GB; GPUs: ['NVIDIA GeForce RTX 4060'])",9063.20707321167,9327.364871501923,9309.03156709671,9280.02916932106,9351.780993938446,9266.282735013961,104.20857085104781

experiment_results/e2rec_runs/douban-movie_e2rec_times.csv

@@ -0,0 +1,2 @@
+model,fold-1_execution_time,fold-2_execution_time,fold-3_execution_time,fold-4_execution_time,fold-5_execution_time,execution_time_mean,execution_time_std
+"Entity2Rec;embedding_model=deepwalk_based;embedding_model_kwargs={'config': {'save_weights': True}, 'parameters': {'walk_len': 10, 'p': 1.0, 'q': 1.0, 'n_walks': 50, 'embedding_size': 64, 'epochs': 1}};run_all=False;workers=6;iterations=1;collab_only=False;content_only=False (CPU: AMD Ryzen 5 7600 6-Core Processor; RAM: 31GB; GPUs: ['NVIDIA GeForce RTX 4060'])",9145.090147972107,9306.440263032913,9279.517577409744,9941.106299877167,9723.67473769188,9479.165805196762,301.48754906956157