**K3M** is a multi-modal pretraining method for e-commerce product data that introduces knowledge modality to correct the noise and supplement the missing of image and text modalities. The modal-encoding layer extracts the features of each modality. The modal-interaction layer is capable of effectively modeling the interaction of multiple modalities, where an initial-interactive feature fusion model is designed to maintain the independence of image modality and text modality, and a structure aggregation module is designed to fuse the information of image, text, and knowledge modalities. K3M is pre-trained with three pretraining tasks, including masked object modeling (MOM), masked language modeling (MLM), and link prediction modeling ([LPM](https://paperswithcode.com/method/local-prior-matching)).

**MeshGraphNet** is a framework for learning mesh-based simulations using [graph neural networks](https://paperswithcode.com/methods/category/graph-models). The model can be trained to pass messages on a mesh graph and to adapt the mesh discretization during forward simulation. The model uses an Encode-Process-Decode architecture trained with one-step supervision, and can be applied iteratively to generate long trajectories at inference time. The encoder transforms the input mesh $M^{t}$ into a graph, adding extra world-space edges. The processor performs several rounds of message passing along mesh edges and world edges, updating all node and edge embeddings. The decoder extracts the acceleration for each node, which is used to update the mesh to produce $M^{t+1}$.

MeshGraphNet

Learning Mesh-Based Simulation with Graph Networks

Knowledge Perceived Multi-modal Pretraining in E-commerce

**PatchGAN** is a type of discriminator for generative adversarial networks which only penalizes structure at the scale of local image patches. The PatchGAN discriminator tries to classify if each $N \times N$ patch in an image is real or fake. This discriminator is run convolutionally across the image, averaging all responses to provide the ultimate output of $D$. Such a discriminator effectively models the image as a Markov random field, assuming independence between pixels separated by more than a patch diameter. It can be understood as a type of texture/style loss.

Source	Knowledge Perceived Multi-modal Pretraining in E-commerce
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com