47 citations · 83 across the 15 of their papers we have counts for
8 papers · 1 filter
Switch EMA: A Free Lunch for Better Flatness and Sharpness
Siyuan Li, Zicheng Liu, Juanxi Tian +9
Exponential Moving Average (EMA) is a widely used weight averaging (WA) regularization to learn flat optima for better generalizations without extra cost in deep neural network (DN…
Graph-level Protein Representation Learning by Structure Knowledge Refinement
Ge Wang, Zelin Zang, Jiangbin Zheng +2
This paper focuses on learning representation on the whole graph level in an unsupervised manner. Learning graph-level representation plays an important role in a variety of real-w…
Co-modeling the Sequential and Graphical Routes for Peptide Representation Learning
Zihan Liu, Ge Wang, Jiaqi Wang +2
Peptides are formed by the dehydration condensation of multiple amino acids. The primary structure of a peptide can be represented either as an amino acid sequence or as a molecula…
Data-Efficient Protein 3D Geometric Pretraining via Refinement of Diffused Protein Structure Decoy
Yufei Huang, Lirong Wu, Haitao Lin +3
Learning meaningful protein representation is important for a variety of biological downstream tasks such as structure-based drug design. Having witnessed the success of protein se…
What Does the Gradient Tell When Attacking the Graph Structure
Zihan Liu, Ge Wang, Yun Luo +1
Recent research has revealed that Graph Neural Networks (GNNs) are susceptible to adversarial attacks targeting the graph structure. A malicious attacker can manipulate a limited n…
DLME: Deep Local-flatness Manifold Embedding
Zelin Zang, Siyuan Li, Di Wu +5
Manifold learning (ML) aims to seek low-dimensional embedding from high-dimensional data. The problem is challenging on real-world datasets, especially with under-sampling data, an…
HOME: High-Order Mixed-Moment-based Embedding for Representation Learning
Chuang Niu, Ge Wang
Minimum redundancy among different elements of an embedding in a latent space is a fundamental requirement or major preference in representation learning to capture intrinsic infor…
Harnessing Hard Mixed Samples with Decoupled Regularizer
Zicheng Liu, Siyuan Li, Ge Wang +3
Mixup is an efficient data augmentation approach that improves the generalization of neural networks by smoothing the decision boundary with mixed data. Recently, dynamic mixup met…