SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2002.02126 · 2020

LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 7 functions out of this paper's own repositories and ran 6 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
PreferredAI/cornac pwc_unofficial 4 of 5
lucapantea/LightGCN reimplementation 1 of 1
copy not recorded — 1 of 1
FunctionStatusWhere it lives
calc_A_hat Ran lucapantea/LightGCN/code/models/LightGCN.py
pointer only (licence: NONE) · get_code("1e0bdab65a021d83")
ranking_eval Ran PreferredAI/cornac/cornac/eval_methods/base_method.py
code served (permissive licence) · get_code("c04f4ee170bc2ef2")
ranking_eval Ran PreferredAI/cornac/cornac/eval_methods/next_basket_evaluation.py
code served (permissive licence) · get_code("403165dad04c951c")
ranking_eval Ran PreferredAI/cornac/cornac/eval_methods/propensity_stratified_evaluation.py
code served (permissive licence) · get_code("068d454afc7e35d8")
rating_eval Ran PreferredAI/cornac/cornac/eval_methods/base_method.py
code served (permissive licence) · get_code("ea27fcd78e800f26")
sparse_matrix_to_torch Ran this paper's copy was not recorded; identical code first harvested from alge24/ADA-UGNN
pointer only · get_code("27f355e24ef27c9b")
ranking_eval Not yet run PreferredAI/cornac/cornac/eval_methods/next_item_evaluation.py
code served (permissive licence) · get_code("41729017320882a2")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Graph Convolution Network (GCN) has become new state-of-the-art for collaborative filtering. Nevertheless, the reasons of its effectiveness for recommendation are not well understood. Existing work that adapts GCN to recommendation lacks thorough ablation analyses on GCN, which is originally designed for graph classification tasks and equipped with many neural network operations. However, we empirically find that the two most common designs in GCNs -- feature transformation and nonlinear activation -- contribute little to the performance of collaborative filtering. Even worse, including them adds to the difficulty of training and degrades recommendation performance. In this work, we aim to simplify the design of GCN to make it more concise and appropriate for recommendation. We propose a new model named LightGCN, including only the most essential component in GCN -- neighborhood aggregation -- for collaborative filtering. Specifically, LightGCN learns user and item embeddings by linearly propagating them on the user-item interaction graph, and uses the weighted sum of the embeddings learned at all layers as the final embedding. Such simple, linear, and neat model is much easier to implement and train, exhibiting substantial improvements (about 16.0\% relative improvement on average) over Neural Graph Collaborative Filtering (NGCF) -- a state-of-the-art GCN-based recommender model -- under exactly the same experimental setting. Further analyses are provided towards the rationality of the simple LightGCN from both analytical and empirical perspectives.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2002.02126")
get_code_for_paper("2002.02126")
have("2002.02126")

Connect an agent — have() is free.