RESEARCH

→ View original post on X — @aibreakfast

3D-aware Conditional Image Synthesis from Carnegie Mellon

By

@aibreakfast

–

19 February 2023 23h23

"3D-aware Conditional Image Synthesis" Authors: Kangle Deng, Gengshan Yang, Deva Ramanan, Jun-Yan Zhu from @CarnegieMellon Read more about their project here: https://
cs.cmu.edu/~pix2pix3D/

Learnable Prompts Emerge as Key GNN Pre-training Architecture

By

–

19 February 2023 21h48

In conclusion, it looks like a neat architecture to pre-train GNNs. Learnable prompts are a handy addition and might re-appear in future architectures. Can't wait to become a graph prompt engineer.

Learnable Prompt Vectors Reduce Parameters for Downstream Tasks

By

–

19 February 2023 21h40

It only uses the learnable prompt vector and not the GNN weights, which are frozen for downstream tasks. This reduces the number of parameters that need to be updated, improves the computational efficiency of task learning/inference, and reduces the reliance on labeled data.

Prompt Tuning Optimizes Downstream Task Efficiency and Accuracy

By

–

19 February 2023 21h39

Prompt tuning involves optimizing the learnable prompt to improve the computational efficiency and accuracy of downstream tasks. It is based on the similarity of subgraphs and is formulated using prompt-assisted task-specific subgraph representations.

Learnable Prompts Enable Better Task-Specific Knowledge Extraction

By

–

19 February 2023 21h34

Learnable prompts provide a better alternative to handcrafted prompts, and enable the extraction of the most relevant prior knowledge for each task. The prompts are a dimension-wise reweighting (or a linear transformation) of the node representations.

Graph Neural Networks Pre-training with Link Prediction Task

By

–

19 February 2023 21h26

During pre-training, the GNN is trained on a link prediction task. By sampling nodes and forming triplets, a pre-training loss is constructed that improves the similarity between the contextual subgraphs of two candidate nodes.

GraphPrompt: Unified Pre-Training Framework for Graph Neural Networks

By

–

19 February 2023 21h21

GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networks Interesting pre-training training framework for GNNs, based on learnable prompts. It reduces labeling needs and boosts downstream task performance. https://
arxiv.org/abs/2302.08043