Masked graph modeling (MGM) is a promising approach for molecular representation learning (MRL). However, extending the success of re-mask decoding from 2D to 3DMGM is non-trivial, primarily due to two conflicting challenges: avoiding 2D structure leakage to the decoder, while still providing sufficient 2D context for reconstructing re-masked atoms. To address these challenges, we propose 3D-GSRD: a 3DMolecular Graph Auto-Encoder with Selective Re-mask Decoding.

Thus, we propose LLaMo: L arge La nguage Model-based Mo lecular graph assistant, which is an end-to-end trained large molecular graph language model.

This work focuses on protein interface prediction, which aims to determine whether a pair of residues from different proteins interact.

Learning (GCL) frameworks are hampered by the specificity, complexity, and incompleteness of their GA techniques.

Our thorough evaluations indicate the new method canachievethestate-of-the-art performance compared with other scene graphpredictionmethods.

InCM-GCL, we can either takethe textfeaturexT orthe image featurexI asthe content feature, and consider the corresponding text encoderfT or image encoderfI as the content encoder. In this section, we discuss the settings of baseline models for imbalanced node classification over fourgraphs. G1: We convert the rich text content into the bag-of-words feature vectors, and further feed the feature vectors with different imbalance ratios to a two-layer MLP [7] classifier to get the classification results. For AMiner, YelpChi, and GitHub graph datasets, we implement CHI-Square [11]toselect useful feature words. G2: We implement three graph neural network based representation learning models including GCN [5], GAT [9], and GraphSAGE [2] to learn the node embeddings by leveraging both node feature (bag-of-words feature vector) andgraph structure information.

In Appendix A, we describe each of the components in GA T A in detail. In Appendix B, we provide detailed information on how we pre-train GA T A's graph updater GA T A. Since the action scorer module is the same as in GA T A, this appendix elaborates on In Appendix D, we provide additional results and discussions. In Appendix F, we show examples of graphs in TextWorld games. As briefly mentioned in Section 3.3, GA T A utilizes a graph encoder which is based on R-GCN [ The number of bases we use is 3. 14 A.2 T ext Encoder In the block, each convolutional layer has 64 filters, each kernel's size is 5. Following standard transformer training, we add positional encodings into each block's The representation aggregator aims to combine the text observation representations and graph representations together. The scorer consists of a self-attention layer, a masked mean pooling layer, and a two-layer MLP .