Fresh Picks from Arxiv
The past week on GraphML arXiv: Hypergraph NNs, GNNs are dynamic programmers, latent graph learning, 3D equivariant molecule generation, and a new GNN library for Keras.

△ Hypergraph Neural Networks:
- Message Passing Neural Networks for Hypergraphs
- Hypergraph Convolutional Networks via Equivalency between Hypergraphs and Undirected Graphs ft. Yu Rong.
- Preventing Over-Smoothing for Hypergraph Neural Networks

⅀ Theory:
- Graph Neural Networks are Dynamic Programmers ft. Petar Veličković.
- OrphicX: A Causality-Inspired Latent Variable Model for Interpreting Graph Neural Networks
- Shift-Robust Node Classification via Graph Adversarial Clustering ft. Jiawei Han.
- Mutual information estimation for graph convolutional neural networks
- Graph-in-Graph (GiG): Learning interpretable latent graphs in non-Euclidean domain for biological and healthcare applications ft. Michael Bronstein.

🏐 Equivariance and 3D Graphs:
- Equivariant Diffusion for Molecule Generation in 3D ft. Max Welling.
- 3D Equivariant Graph Implicit Functions

📚 Libraries and Surveys:
- GNNkeras: A Keras-based library for Graph Neural Networks and homogeneous and heterogeneous graph processing ft. Franco Scarselli.
- Graph Neural Networks in IoT: A Survey

🔨 Applications:
- Graph similarity learning for change-point detection in dynamic networks ft. Xiowen Dong.
- Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment ft. Yizhou Sun.
- A Simple Yet Effective Pretraining Strategy for Graph Few-shot Learning
- Pretraining Graph Neural Networks for few-shot Analog Circuit Modeling and Design ft. Pieter Abbeel.

(If I forgot to mention your paper, please shoot me a message and I will update the post.)