List of examined papers for the analysis provided in Section 2 of the paper

Serial No.	Articles	Venue	Readme file	Code link	Code of baselines	Code of proposed model	Tuning strategy for baselines	Hyperparameters of the proposed model are present in the article	Hyperparameters of baseline models are present in the article
1	Unify Local and Global Information for Top-𝑁 Recommendation	SIGIR'22	Yes, without instructions	Yes	No	Yes	Some parameters like learning rate, dropout, and decay rate are selected using the grid search strategy while the remaining parameters such as batch size and embedding size are taken from thier original papers	Yes, mention separately for each dataset	No
2	Hypergraph Contrastive Collaborative Filtering	SIGIR'22	Yes, with instructions	Yes	No	Yes	Do not mention how to tune the hyperparameters	Yes, do not mention separately for each dataset	No
3	Self-Guided Learning to Denoise for Robust Recommendation	SIGIR'22	Yes, with instructions	Yes	No	Yes	Do not mention how to tune the hyperparameters	Yes, do not mention separately for each dataset	Yes, do not mention separately for each dataset
4	HAKG: Hierarchy-Aware Knowledge Gated Network for Recommendation	SIGIR'22	Yes, with instructions	Yes	No	Yes	Some parameters like learning rate, dropout, and decay rate are selected using the grid search strategy and they fix the values of remaining hyperparameters such as batch size and embedding size	Yes, do not mention separately for each dataset	No
5	Graph Trend Filtering Networks for Recommendation	SIGIR'22	Yes, with instructions	Yes	No	Yes	Do not mention how to tune the hyperparameters	Yes, do not mention separately for each dataset	No
6	PEVAE: A Hierarchical VAE for Personalized Explainable Recommendation	SIGIR'22	Yes, with instructions	Yes	No	Yes	Fix the hyperparameters of all models	Yes	No
7	Item Similarity Mining for Multi-Market Recommendation	SIGIR'22	No	No	No	No	Fix the hyperparameters of all models	Yes	Yes
8	EFLEC: Efficient Feature-LEakage Correction in GNN based Recommendation Systems	SIGIR'22	No	No	No	No	Fix the hyperparameters of all models	Yes, they follow the exact same settings as LightGCN model	Yes, they follow the exact same settings as LightGCN model
9	Enhancing Top-N Item Recommendations by Peer Collaboration	SIGIR'22	No	No	No	No	Grid search strategy	Yes, mention separately for each dataset	Yes, mention separately for each dataset
10	Transform Cold-Start Users into Warm via Fused Behaviors in Large-Scale Recommendation	SIGIR'22	No	No	No	No	Fix the hyperparameters of all models	Yes	Yes
11	An MLP-based Algorithm for Efficient Contrastive Graph Recommendations	SIGIR'22	No	No	No	No	Some parameters like learning rate, dropout, and decay rate are selected using the grid search strategy while they fix the values of remaining hyperparameters such as batch size and latent dimension	No	No
12	Improving Item Cold-start Recommendation via Model-agnostic Conditional Variational Autoencoder	SIGIR'22	Yes, with instructions	Yes	No	Yes	Fix the hyperparameters of all models	Yes	Yes
13	Self-Supervised Hypergraph Transformer for Recommender Systems	KDD'22	Yes, with instructions	Yes	No	Yes	Do not mention how to tune the hyperparameters	No	No
14	Learning Binarized Graph Representations with Multi-faceted Quantization Reinforcement for Top-K Recommendation	KDD'22	No	No	No	No	Select the parameters from their original papers, if parameters are not available then apply grid search to tune the parameters	No	No
15	Multi-Sparse-Domain Collaborative Recommendation via Enhanced Comprehensive Aspect Preference Learning	WSDM'22	No	No	No	No	Do not mention how to tune the hyperparameters	Yes, do not mention separately for each dataset	No
16	Contrastive Meta Learning with Behavior Multiplicity for Recommendation	WSDM'22	Yes, with instructions	Yes	No	Yes	Do not mention how to tune the hyperparameters	No	No
17	Long Short-Term Temporal Meta-learning in Online Recommendation	WSDM'22	No	No	No	No	Grid search strategy	No	No
18	BRUCE: Bundle Recommendation Using Contextualized item Embeddings	RecSys'22	Yes, with instructions	Yes	No	Yes	Select the parameters from their original papers	Yes, mention separately for each dataset	No
20	CAEN: A Hierarchically Attentive Evolution Network for Item-Attribute-Change-Aware Recommendation in the Growing E-commerce Environment	RecSys'22	Yes, without instructions	Yes	No	No	Fix the hyperparameters of all models	Yes	No
21	ProtoMF: Prototype-based Matrix Factorization for Effective and Explainable Recommendations	RecSys'22	Yes, with instructions	Yes	No	Yes	Tree-Structured Parzen Estimator	No	No