Search Results for author:
Found 63 papers, 37 papers with code
Learning to Model Graph Structural Information on MLPs via Graph Structure Self-Contrasting
In this paper, we rethink the roles played by graph structural information in graph data training and identify that message passing is not the only path to modeling structural information.
Teach Harder, Learn Poorer: Rethinking Hard Sample Distillation for GNN-to-MLP Knowledge Distillation
To bridge the gaps between powerful Graph Neural Networks (GNNs) and lightweight Multi-Layer Perceptron (MLPs), GNN-to-MLP Knowledge Distillation (KD) proposes to distill knowledge from a well-trained teacher GNN into a student MLP.
The Heterophilic Graph Learning Handbook: Benchmarks, Models, Theoretical Analysis, Applications and Challenges
In this survey, we provide a comprehensive review of the latest progress on heterophilic graph learning, including an extensive summary of benchmark datasets and evaluation of homophily metrics on synthetic graphs, meticulous classification of the most updated supervised and unsupervised learning methods, thorough digestion of the theoretical analysis on homophily/heterophily, and broad exploration of the heterophily-related applications.
CBGBench: Fill in the Blank of Protein-Molecule Complex Binding Graph
To broaden the scope, we have adapted these models to a range of tasks essential in drug design, which are considered sub-tasks within the graph fill-in-the-blank tasks.
UniIF: Unified Molecule Inverse Folding
We do such unification in two levels: 1) Data-Level: We propose a unified block graph data form for all molecules, including the local frame building and geometric feature initialization.
Learning to Predict Mutation Effects of Protein-Protein Interactions by Microenvironment-aware Hierarchical Prompt Learning
Protein-protein bindings play a key role in a variety of fundamental biological processes, and thus predicting the effects of amino acid mutations on protein-protein binding is crucial.
Advances of Deep Learning in Protein Science: A Comprehensive Survey
Protein representation learning plays a crucial role in understanding the structure and function of proteins, which are essential biomolecules involved in various biological processes.
A Teacher-Free Graph Knowledge Distillation Framework with Dual Self-Distillation
As a result, TGS enjoys the benefits of graph topology awareness in training but is free from data dependency in inference.
PPFlow: Target-aware Peptide Design with Torsional Flow Matching
Therapeutic peptides have proven to have great pharmaceutical value and potential in recent decades.
Decoupling Weighing and Selecting for Integrating Multiple Graph Pre-training Tasks
In this paper, we identify two important collaborative processes for this topic: (1) select: how to select an optimal task combination from a given task pool based on their compatibility, and (2) weigh: how to weigh the selected tasks based on their importance.
Enhancing Protein Predictive Models via Proteins Data Augmentation: A Benchmark and New Directions
Augmentation is an effective alternative to utilize the small amount of labeled protein data.
MAPE-PPI: Towards Effective and Efficient Protein-Protein Interaction Prediction via Microenvironment-Aware Protein Embedding
In addition, microenvironments defined in previous work are largely based on experimentally assayed physicochemical properties, for which the "vocabulary" is usually extremely small.
Re-Dock: Towards Flexible and Realistic Molecular Docking with Diffusion Bridge
Accurate prediction of protein-ligand binding structures, a task known as molecular docking is crucial for drug design but remains challenging.
PSC-CPI: Multi-Scale Protein Sequence-Structure Contrasting for Efficient and Generalizable Compound-Protein Interaction Prediction
Compound-Protein Interaction (CPI) prediction aims to predict the pattern and strength of compound-protein interactions for rational drug discovery.
FoldToken: Learning Protein Language via Vector Quantization and Beyond
Is there a foreign language describing protein sequences and structures simultaneously?
Deep Manifold Graph Auto-Encoder for Attributed Graph Embedding
Representing graph data in a low-dimensional space for subsequent tasks is the purpose of attributed graph embedding.
Masked Modeling for Self-supervised Representation Learning on Vision and Beyond
As the deep learning revolution marches on, self-supervised learning has garnered increasing attention in recent years thanks to its remarkable representation learning ability and the low dependence on labeled data.
Protein 3D Graph Structure Learning for Robust Structure-based Protein Property Prediction
To study this problem, we identify a Protein 3D Graph Structure Learning Problem for Robust Protein Property Prediction (PGSL-RP3), collect benchmark datasets, and present a protein Structure embedding Alignment Optimization framework (SAO) to mitigate the problem of structure embedding bias between the predicted and experimental protein structures.
Revisiting the Temporal Modeling in Spatio-Temporal Predictive Learning under A Unified View
In this paper, we re-examine the two dominant temporal modeling approaches within the realm of spatio-temporal predictive learning, offering a unified perspective.
OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning
Spatio-temporal predictive learning is a learning paradigm that enables models to learn spatial and temporal patterns by predicting future frames from given past frames in an unsupervised manner.
Quantifying the Knowledge in GNNs for Reliable Distillation into MLPs
To bridge the gaps between topology-aware Graph Neural Networks (GNNs) and inference-efficient Multi-Layer Perceptron (MLPs), GLNN proposes to distill knowledge from a well-trained teacher GNN into a student MLP.
Functional-Group-Based Diffusion for Pocket-Specific Molecule Generation and Elaboration
In this way, however, it is hard to generate realistic fragments with complicated structures.
Extracting Low-/High- Frequency Knowledge from Graph Neural Networks and Injecting it into MLPs: An Effective GNN-to-MLP Distillation Framework
Furthermore, we identified a potential information drowning problem for existing GNN-to-MLP distillation, i. e., the high-frequency knowledge of the pre-trained GNNs may be overwhelmed by the low-frequency knowledge during distillation; we have described in detail what it represents, how it arises, what impact it has, and how to deal with it.
Cross-Gate MLP with Protein Complex Invariant Embedding is A One-Shot Antibody Designer
In this paper, we propose a \textit{simple yet effective} model that can co-design 1D sequences and 3D structures of CDRs in a one-shot manner.
Towards Reasonable Budget Allocation in Untargeted Graph Structure Attacks via Gradient Debias
It has become cognitive inertia to employ cross-entropy loss function in classification related tasks.
Data-Efficient Protein 3D Geometric Pretraining via Refinement of Diffused Protein Structure Decoy
Learning meaningful protein representation is important for a variety of biological downstream tasks such as structure-based drug design.
A Survey on Protein Representation Learning: Retrospect and Prospect
To pave the way for AI researchers with little bioinformatics background, we present a timely and comprehensive review of PRL formulations and existing PRL methods from the perspective of model architectures, pretext tasks, and downstream applications.
Integration of Pre-trained Protein Language Models into Geometric Deep Learning Networks
Geometric deep learning has recently achieved great success in non-Euclidean domains, and learning on 3D structures of large biomolecules is emerging as a distinct research area.
Deciphering RNA Secondary Structure Prediction: A Probabilistic K-Rook Matching Perspective
In this work, we reformulate the RNA secondary structure prediction as a K-Rook problem, thereby simplifying the prediction process into probabilistic matching within a finite solution space.
DiffBP: Generative Diffusion of 3D Molecules for Target Protein Binding
Previous works usually generate atoms in an auto-regressive way, where element types and 3D coordinates of atoms are generated one by one.
Teaching Yourself: Graph Self-Distillation on Neighborhood for Node Classification
Despite their great academic success, Multi-Layer Perceptrons (MLPs) remain the primary workhorse for practical industrial applications.
Automated Graph Self-supervised Learning via Multi-teacher Knowledge Distillation
Self-supervised learning on graphs has recently achieved remarkable success in graph representation learning.
Are Gradients on Graph Structure Reliable in Gray-box Attacks?
These errors arise from rough gradient usage due to the discreteness of the graph structure and from the unreliability in the meta-gradient on the graph structure.
Exploring Generative Neural Temporal Point Process
While lots of previous works have focused on `goodness-of-fit' of TPP models by maximizing the likelihood, their predictive performance is unsatisfactory, which means the timestamps generated by models are far apart from true observations.
Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning
Spatiotemporal predictive learning aims to generate future frames by learning from historical frames.
Ranked #12 on
Video Prediction
on Moving MNIST
CoSP: Co-supervised pretraining of pocket and ligand
Can we inject the pocket-ligand interaction knowledge into the pre-trained model and jointly learn their chemical space?
SimVP: Simpler yet Better Video Prediction
From CNN, RNN, to ViT, we have witnessed remarkable advancements in video prediction, incorporating auxiliary inputs, elaborate neural architectures, and sophisticated training strategies.
Ranked #4 on
Video Prediction
on Human3.6M
Hyperspherical Consistency Regularization
Though it benefits from taking advantage of both feature-dependent information from self-supervised learning and label-dependent information from supervised learning, this scheme remains suffering from bias of the classifier.
Discovering and Explaining the Representation Bottleneck of Graph Neural Networks from Multi-order Interactions
Graph neural networks (GNNs) mainly rely on the message-passing paradigm to propagate node features and build interactions, and different graph learning tasks require different ranges of node interactions.
STONet: A Neural-Operator-Driven Spatio-temporal Network
Graph-based spatio-temporal neural networks are effective to model the spatial dependency among discrete points sampled irregularly from unstructured grids, thanks to the great expressiveness of graph neural networks.
Harnessing Hard Mixed Samples with Decoupled Regularizer
However, we found that the extra optimizing step may be redundant because label-mismatched mixed samples are informative hard mixed samples for deep models to localize discriminative features.
SemiRetro: Semi-template framework boosts deep retrosynthesis prediction
Experimental results show that SemiRetro significantly outperforms both existing TB and TF methods.
Ranked #4 on
Single-step retrosynthesis
on USPTO-50k
SimGRACE: A Simple Framework for Graph Contrastive Learning without Data Augmentation
Furthermore, we devise adversarial training scheme, dubbed \textbf{AT-SimGRACE}, to enhance the robustness of graph contrastive learning and theoretically explain the reasons.
An Empirical Study: Extensive Deep Temporal Point Process
In this paper, we first review recent research emphasis and difficulties in modeling asynchronous event sequences with deep temporal point process, which can be concluded into four fields: encoding of history sequence, formulation of conditional intensity function, relational discovery of events and learning approaches for optimization.
ProGCL: Rethinking Hard Negative Mining in Graph Contrastive Learning
Contrastive Learning (CL) has emerged as a dominant technique for unsupervised representation learning which embeds augmented versions of the anchor close to each other (positive samples) and pushes the embeddings of other samples (negatives) apart.
Git: Clustering Based on Graph of Intensity Topology
\textbf{A}ccuracy, \textbf{R}obustness to noises and scales, \textbf{I}nterpretability, \textbf{S}peed, and \textbf{E}asy to use (ARISE) are crucial requirements of a good clustering algorithm.
Ranked #1 on
Clustering Algorithms Evaluation
on Fashion-MNIST
Beyond Message Passing Paradigm: Training Graph Data with Consistency Constraints
Specifically, the GCL framework is optimized with three well-designed consistency constraints: neighborhood consistency, label consistency, and class-center consistency.
Co-learning: Learning from Noisy Labels with Self-supervision
Noisy labels, resulting from mistakes in manual labeling or webly data collecting for supervised learning, can cause neural networks to overfit the misleading information and degrade the generalization performance.
GraphMixup: Improving Class-Imbalanced Node Classification on Graphs by Self-supervised Context Prediction
Recent years have witnessed great success in handling node classification tasks with Graph Neural Networks (GNNs).
Self-supervised Learning on Graphs: Contrastive, Generative,or Predictive
In this survey, we extend the concept of SSL, which first emerged in the fields of computer vision and natural language processing, to present a timely and comprehensive review of existing SSL techniques for graph data.
AutoMix: Unveiling the Power of Mixup for Stronger Classifiers
Specifically, AutoMix reformulates the mixup classification into two sub-tasks (i. e., mixed sample generation and mixup classification) with corresponding sub-networks and solves them in a bi-level optimization framework.
Ranked #8 on
Image Classification
on Places205
Conditional Local Convolution for Spatio-temporal Meteorological Forecasting
We further propose the distance and orientation scaling terms to reduce the impacts of irregular spatial distribution.
Deep Manifold Computing and Visualization Using Elastic Locally Isometric Smoothness
The ability to preserve local geometry of highly nonlinear manifolds in high dimensional spaces and properly unfold them into lower dimensional hyperplanes is the key to the success of manifold computing, nonlinear dimensionality reduction (NLDR) and visualization.
Towards Robust Graph Neural Networks against Label Noise
A pseudo label is computed from the neighboring labels for each node in the training set using LP; meta learning is utilized to learn a proper aggregation of the original and pseudo label as the final label.
Consistent Representation Learning for High Dimensional Data Analysis
In this paper, we propose a novel neural network-based method, called Consistent Representation Learning (CRL), to accomplish the three associated tasks end-to-end and improve the consistencies.
Deep Manifold Transformation for Nonlinear Dimensionality Reduction
The LGP constraints constitute the loss for deep manifold learning and serve as geometric regularizers for NLDR network training.
Invertible Manifold Learning for Dimension Reduction
Dimension reduction (DR) aims to learn low-dimensional representations of high-dimensional data with the preservation of essential information.
Deep Clustering and Representation Learning that Preserves Geometric Structures
To overcome the problem that clusteringoriented losses may deteriorate the geometric structure of embeddings in the latent space, an isometric loss is proposed for preserving intra-manifold structure locally and a ranking loss for inter-manifold structure globally.
Generalized Clustering and Multi-Manifold Learning with Geometric Structure Preservation
Though manifold-based clustering has become a popular research topic, we observe that one important factor has been omitted by these works, namely that the defined clustering loss may corrupt the local and global structure of the latent space.
Markov-Lipschitz Deep Learning
We propose a novel framework, called Markov-Lipschitz deep learning (MLDL), to tackle geometric deterioration caused by collapse, twisting, or crossing in vector-based neural network transformations for manifold-based representation learning and manifold data generation.
A GAN-based Tunable Image Compression System
The method of importance map has been widely adopted in DNN-based lossy image compression to achieve bit allocation according to the importance of image contents.
A Foreground-background Parallel Compression with Residual Encoding for Surveillance Video
In this paper, we propose a video compression method that extracts and compresses the foreground and background of the video separately.
