Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
Maximum Common Subgraph Guided Graph Retrieval: Late and Early Interaction Networks
Authors: Indradyumna Roy, Soumen Chakrabarti, Abir De
NeurIPS 2022 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments with seven data sets show that our proposals are superior among late interaction models in terms of both accuracy and speed. Our early interaction models provide accuracy competitive with the state of the art, at substantially greater speeds. |
| Researcher Affiliation | Academia | Indradyumna Roy Soumen Chakrabarti Abir De Indian Institute of Technology Bombay EMAIL |
| Pseudocode | Yes | Algorithm 1 GOSSIP(B) 1: X(0) = I # identity 2: for t = 1, . . . T 1 do 3: X(t + 1) X(t)(B + I) 4: Return maxu V ||X(T)[ , u]||0 |
| Open Source Code | Yes | Our code is in https://tinyurl.com/mccsxmcs. |
| Open Datasets | Yes | We experiment with seven datasets, viz., MSRC-21 (MSRC), PTC-MM (MM), PTC-FR (FR), PTC-MR (MR), PTC-FM (FM), COX2 (COX) and DD. The details about them are described in Appendix C. |
| Dataset Splits | Yes | We partition the query set into 60% training, 20% validation and 20% test folds. |
| Hardware Specification | No | The paper does not explicitly describe the specific hardware used to run its experiments in the provided text. |
| Software Dependencies | No | The paper does not provide specific ancillary software details with version numbers (e.g., library or solver names with version numbers) in the provided text. |
| Experiment Setup | No | The paper mentions that hyperparameters were tuned using the validation split and that models were trained by minimizing MSE loss, but it does not provide specific values for hyperparameters like learning rate, batch size, or number of epochs in the main text. |