Search Results for author:
Found 102 papers, 60 papers with code
Active Test-Time Adaptation: Theoretical Analyses and An Algorithm
Extensive experimental results confirm consistency with our theoretical analyses and show that the proposed ATTA method yields substantial performance improvements over TTA methods while maintaining efficiency and shares similar effectiveness to the more demanding active domain adaptation (ADA) methods.
SineNet: Learning Temporal Dynamics in Time-Dependent Partial Differential Equations
While the U-Net architecture with skip connections is commonly used by prior studies to enable multi-scale processing, our analysis shows that the need for features to evolve across layers results in temporally misaligned features in skip connections, which limits the model's performance.
Complete and Efficient Graph Transformers for Crystal Material Property Prediction
Crystal structures are characterized by atomic bases within a primitive unit cell that repeats along a regular lattice throughout 3D space.
On the Markov Property of Neural Algorithmic Reasoning: Analyses and Methods
To address challenges in training ForgetNet at early stages, we further introduce G-ForgetNet, which uses a gating mechanism to allow for the selective integration of historical embeddings.
TrustLLM: Trustworthiness in Large Language Models
This paper introduces TrustLLM, a comprehensive study of trustworthiness in LLMs, including principles for different dimensions of trustworthiness, established benchmark, evaluation, and analysis of trustworthiness for mainstream LLMs, and discussion of open challenges and future directions.
Genetic InfoMax: Exploring Mutual Information Maximization in High-Dimensional Imaging Genetics Studies
Genome-wide association studies (GWAS) are used to identify relationships between genetic variations and specific traits.
Video Timeline Modeling For News Story Understanding
In this paper, we present a novel problem, namely video timeline modeling.
Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
Advances in artificial intelligence (AI) are fueling a new paradigm of discoveries in natural sciences.
QH9: A Quantum Hamiltonian Prediction Benchmark for QM9 Molecules
Supervised machine learning approaches have been increasingly used in accelerating electronic structure prediction as surrogates of first-principle computational methods, such as density functional theory (DFT).
Graph Structure and Feature Extrapolation for Out-of-Distribution Generalization
Out-of-distribution (OOD) generalization deals with the prevalent learning scenario where test distribution shifts from training distribution.
Efficient Approximations of Complete Interatomic Potentials for Crystal Property Prediction
This is enabled by our approximations of infinite potential summations, where we extend the Ewald summation for several potential series approximations with provable error bounds.
Ranked #1 on
Band Gap
on Materials Project
Graph Mixup with Soft Alignments
We conduct systematic experiments to show that S-Mixup can improve the performance and generalization of graph neural networks (GNNs) on various graph classification tasks.
Group Equivariant Fourier Neural Operators for Partial Differential Equations
We consider solving partial differential equations (PDEs) with Fourier neural operators (FNOs), which operate in the frequency domain.
Efficient and Equivariant Graph Networks for Predicting Quantum Hamiltonian
We consider the prediction of the Hamiltonian matrix, which finds use in quantum chemistry and condensed matter physics.
Joint Learning of Label and Environment Causal Independence for Graph Out-of-Distribution Generalization
In this work, we propose to simultaneously incorporate label and environment causal independence (LECI) to fully make use of label and environment information, thereby addressing the challenges faced by prior methods on identifying causal and invariant subgraphs.
A Score-Based Model for Learning Neural Wavefunctions
Existing optimization approaches compute the energy by sampling local energy from an explicit probability distribution given by the wavefunction.
A Latent Diffusion Model for Protein Structure Generation
Proteins are complex biomolecules that perform a variety of crucial functions within living organisms.
3D Molecular Geometry Analysis with 2D Graphs
Here, we propose a novel deep learning framework to predict 3D geometries from molecular graphs.
A new perspective on building efficient and expressive 3D equivariant graph neural networks
Geometric deep learning enables the encoding of physical symmetries in modeling 3D objects.
Provably Convergent Subgraph-wise Sampling for Fast GNN Training
During the message passing (MP) in GNNs, subgraph-wise sampling methods discard messages outside the mini-batches in backward passes to avoid the well-known neighbor explosion problem, i. e., the exponentially increasing dependencies of nodes with the number of MP iterations.
Generalization in Visual Reinforcement Learning with the Reward Sequence Distribution
The appealing features of RSD-OA include that: (1) RSD-OA is invariant to visual distractions, as it is conditioned on the predefined subsequent action sequence without task-irrelevant information from transition dynamics, and (2) the reward sequence captures long-term task-relevant information in both rewards and transition dynamics.
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.
Gradient-Guided Importance Sampling for Learning Binary Energy-Based Models
the discrete data space to approximately construct the provably optimal proposal distribution, which is subsequently used by importance sampling to efficiently estimate the original ratio matching objective.
Periodic Graph Transformers for Crystal Material Property Prediction
Our Matformer is designed to be invariant to periodicity and can capture repeating patterns explicitly.
Ranked #2 on
Band Gap
on JARVIS-DFT
Learning Hierarchical Protein Representations via Complete 3D Graph Networks
In this work, we propose to develop a novel hierarchical graph network, known as ProNet, to capture the relations.
FlowX: Towards Explainable Graph Neural Networks via Message Flows
We investigate the explainability of graph neural networks (GNNs) as a step toward elucidating their working mechanisms.
ComENet: Towards Complete and Efficient Message Passing for 3D Molecular Graphs
To incorporate 3D information completely and efficiently, we propose a novel message passing scheme that operates within 1-hop neighborhood.
Ranked #4 on
Drug Discovery
on QM9
Self-Adaptive Label Augmentation for Semi-supervised Few-shot Classification
A major novelty of SALA is the task-adaptive metric, which can learn the metric adaptively for different tasks in an end-to-end fashion.
GOOD: A Graph Out-of-Distribution Benchmark
Our GOOD benchmark is a growing project and expects to expand in both quantity and variety of resources as the area develops.
Lattice Convolutional Networks for Learning Ground States of Quantum Many-Body Systems
Based on the proposed lattice convolutions, we design lattice convolutional networks (LCN) that use self-gating and attention mechanisms.
GraphFM: Improving Large-Scale GNN Training via Feature Momentum
GraphFM-IB applies FM to in-batch sampled data, while GraphFM-OB applies FM to out-of-batch data that are 1-hop neighborhood of in-batch data.
Empowering GNNs via Edge-Aware Weisfeiler-Leman Algorithm
Message passing graph neural networks (GNNs) are known to have their expressiveness upper-bounded by 1-dimensional Weisfeiler-Leman (1-WL) algorithm.
Learning Task-relevant Representations for Generalization via Characteristic Functions of Reward Sequence Distributions
Generalization across different environments with the same tasks is critical for successful applications of visual reinforcement learning (RL) in real scenarios.
Generating 3D Molecules for Target Protein Binding
Second, to preserve the desirable equivariance property, we select a local reference atom according to the designed auxiliary classifiers and then construct a local spherical coordinate system.
Duality-Induced Regularizer for Semantic Matching Knowledge Graph Embeddings
Semantic matching models -- which assume that entities with similar semantics have similar embeddings -- have shown great power in knowledge graph embeddings (KGE).
Automated Data Augmentations for Graph Classification
In this work, we propose GraphAug, a novel automated data augmentation method aiming at computing label-invariant augmentations for graph classification.
Self-Supervised Representation Learning via Latent Graph Prediction
Self-supervised learning (SSL) of graph neural networks is emerging as a promising way of leveraging unlabeled data.
Task-Agnostic Graph Explanations
They are also unable to provide explanations in cases where the GNN is trained in a self-supervised manner, and the resulting representations are used in future downstream tasks.
Neighbor2Seq: Deep Learning on Massive Graphs by Transforming Neighbors to Sequences
Therefore, our Neighbor2Seq naturally endows GNNs with the efficiency and advantages of deep learning operations on grid-like data by precomputing the Neighbor2Seq transformations.
ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs
To address this challenge, we propose a novel query embedding model, namely Cone Embeddings (ConE), which is the first geometry-based QE model that can handle all the FOL operations, including conjunction, disjunction, and negation.
Molecule3D: A Benchmark for Predicting 3D Geometries from Molecular Graphs
Here, we propose to predict the ground-state 3D geometries from molecular graphs using machine learning methods.
Ranked #1 on
3D Geometry Prediction
on Molecule3D val
GraphEBM: Towards Permutation Invariant and Multi-Objective Molecular Graph Generation
In this work, we propose GraphEBM, a molecular graph generation method via energy-based models (EBMs), as an exploratory work to perform permutation invariant and multi-objective molecule generation.
Gradient-Guided Importance Sampling for Learning Discrete Energy-Based Models
In this study, we propose ratio matching with gradient-guided importance sampling (RMwGGIS) to alleviate the above limitations.
An Autoregressive Flow Model for 3D Molecular Geometry Generation from Scratch
We consider the problem of generating 3D molecular geometries from scratch.
Task-Agnostic Graph Neural Explanations
TAGE enables the explanation of GNN embedding models without downstream tasks and allows efficient explanation of multitask models.
Group Contrastive Self-Supervised Learning on Graphs
Our framework embeds the given graph into multiple subspaces, of which each representation is prompted to encode specific characteristics of graphs.
Fast Quantum Property Prediction via Deeper 2D and 3D Graph Networks
We employ our methods to participate in the 2021 KDD Cup on OGB Large-Scale Challenge (OGB-LSC), which aims to predict the HOMO-LUMO energy gap of molecules.
AdaGNN: Graph Neural Networks with Adaptive Frequency Response Filter
Existing efforts can be mainly categorized as spectral-based and spatial-based methods.
Stochastic Optimization of Areas Under Precision-Recall Curves with Provable Convergence
Compared with AUROC, AUPRC is a more appropriate metric for highly imbalanced datasets.
DIG: A Turnkey Library for Diving into Graph Deep Learning Research
Although there exist several libraries for deep learning on graphs, they are aiming at implementing basic operations for graph deep learning.
Sent2Matrix: Folding Character Sequences in Serpentine Manifolds for Two-Dimensional Sentence
We study text representation methods using deep models.
Self-Supervised Learning of Graph Neural Networks: A Unified Review
Our unified treatment of SSL methods for GNNs sheds light on the similarities and differences of various methods, setting the stage for developing new methods and algorithms.
Spherical Message Passing for 3D Graph Networks
Based on such observations, we propose the spherical message passing (SMP) as a novel and powerful scheme for 3D molecular learning.
Ranked #3 on
Drug Discovery
on QM9
On Explainability of Graph Neural Networks via Subgraph Explorations
To make the tree search more effective, we propose to use Shapley values as a measure of subgraph importance, which can also capture the interactions among different subgraphs.
GraphDF: A Discrete Flow Model for Molecular Graph Generation
We consider the problem of molecular graph generation using deep models.
GraphEBM: Molecular Graph Generation with Energy-Based Models
We note that most existing approaches for molecular graph generation fail to guarantee the intrinsic property of permutation invariance, resulting in unexpected bias in generative models.
A Multi-Stage Attentive Transfer Learning Framework for Improving COVID-19 Diagnosis
The method is then integrated to the last stage of the proposed transfer learning framework to reuse the complex patterns learned from the same CT images.
CleftNet: Augmented Deep Learning for Synaptic Cleft Detection from Brain Electron Microscopy
The effectiveness of our methods is evaluated on both online and offline tasks.
Node2Seq: Towards Trainable Convolutions in Graph Neural Networks
Several graph neural network approaches are proposed for node feature learning and they generally follow a neighboring information aggregation scheme to learn node features.
Weighted Line Graph Convolutional Networks
Line graphs have shown to be effective in improving feature learning in graph neural networks.
Teleport Graph Convolutional Networks
To address these limitations, we propose a teleport graph convolution layer (TeleGCL) that uses teleport functions to enable each node to aggregate information from a much larger neighborhood.
Explainability in Graph Neural Networks: A Taxonomic Survey
To facilitate evaluations, we generate a set of benchmark graph datasets specifically for GNN explainability.
Advanced Graph and Sequence Neural Networks for Molecular Property Prediction and Drug Discovery
Here we develop a suite of comprehensive machine learning methods and tools spanning different computational models, molecular representations, and loss functions for molecular property prediction and drug discovery.
Towards Improved and Interpretable Deep Metric Learning via Attentive Grouping
Grouping has been commonly used in deep metric learning for computing diverse features.
Augmented Equivariant Attention Networks for Microscopy Image Reconstruction
Advances in deep learning enable us to perform image-to-image transformation tasks for various types of microscopy image reconstruction, computationally producing high-quality images from the physically acquired low-quality ones.
Noise2Same: Optimizing A Self-Supervised Bound for Image Denoising
Self-supervised frameworks that learn denoising models with merely individual noisy images have shown strong capability and promising performance in various image denoising tasks.
Line Graph Neural Networks for Link Prediction
In this formalism, a link prediction problem is converted to a graph classification task.
Deep Low-Shot Learning for Biological Image Classification and Visualization from Limited Training Samples
In our task, saliency maps are used to assist the identification and visualization of developmental landmarks.
Topology-Aware Graph Pooling Networks
In addition, graph topology is incorporated in global voting to compute the importance score of each node globally in the entire graph.
CorDEL: A Contrastive Deep Learning Approach for Entity Linkage
We evaluate CorDEL with extensive experiments conducted on both public benchmark datasets and a real-world dataset.
Ranked #7 on
Entity Resolution
on Amazon-Google
Global Voxel Transformer Networks for Augmented Microscopy
In this work, we introduce global voxel transformer networks (GVTNets), an advanced deep learning tool for augmented microscopy that overcomes intrinsic limitations of the current U-Net based models and achieves improved performance.
Machine Learning Explanations to Prevent Overtrust in Fake News Detection
Combating fake news and misinformation propagation is a challenging task in the post-truth era.
Second-Order Pooling for Graph Neural Networks
In addition, compared to existing graph pooling methods, second-order pooling is able to use information from all nodes and collect second-order statistics, making it more powerful.
Towards Deeper Graph Neural Networks
Based on our theoretical and empirical analysis, we propose Deep Adaptive Graph Neural Network (DAGNN) to adaptively incorporate information from large receptive fields.
Ranked #2 on
Node Classification
on AMZ Computers
Deep Learning of High-Order Interactions for Protein Interface Prediction
However, these methods do not incorporate the important sequential information from amino acid chains and the high-order pairwise interactions.
Protein Interface Prediction
Vocal Bursts Intensity Prediction
Kronecker Attention Networks
Use of attention operators on high-order data requires flattening of the spatial or spatial-temporal dimensions into a vector, which is assumed to follow a multivariate normal distribution.
XGNN: Towards Model-Level Explanations of Graph Neural Networks
Furthermore, our experimental results indicate that the generated graphs can provide guidance on how to improve the trained GNNs.
Non-Local Graph Neural Networks
Modern graph neural networks (GNNs) learn node embeddings through multilayer local aggregation and achieve great success in applications on assortative graphs.
iCapsNets: Towards Interpretable Capsule Networks for Text Classification
On the other hand, iCapsNets explore a novel way to explain the model's general behavior, achieving global interpretability.
StructPool: Structured Graph Pooling via Conditional Random Fields
Learning high-level representations for graphs is of great importance for graph analysis tasks.
Adversarial Attacks and Defenses on Graphs: A Review, A Tool and Empirical Studies
As the extensions of DNNs to graphs, Graph Neural Networks (GNNs) have been demonstrated to inherit this vulnerability.
Topology-Aware Pooling via Graph Attention
Previous studies used global ranking methods to sample some of the important nodes, but most of them are not able to incorporate graph topology information in computing ranking scores.
Dense Transformer Networks for Brain Electron Microscopy Image Segmentation
The proposed dense transformer modules are differentiable, thus the entire network can be trained.
Ranked #1 on
Electron Microscopy Image Segmentation
on SNEMI3D
Electron Microscopy Image Segmentation
Image Segmentation
+1
XFake: Explainable Fake News Detector with Visualizations
In this demo paper, we present the XFake system, an explainable fake news detector that assists end-users to identify news credibility.
Graph Representation Learning via Hard and Channel-Wise Attention Networks
To further reduce the requirements on computational resources, we propose the cGAO that performs attention operations along channels.
Ranked #8 on
Graph Classification
on D&D
(using extra training data)
Global Pixel Transformers for Virtual Staining of Microscopy Images
It is also shown that our proposed global pixel transformer layer is useful to improve the fluorescence image prediction results.
Graph U-Nets
We further propose the gUnpool layer as the inverse operation of the gPool layer.
Ranked #4 on
Graph Classification
on D&D
On Attribution of Recurrent Neural Network Predictions via Additive Decomposition
REAT decomposes the final prediction of a RNN into additive contribution of each word in the input text.
Learning Graph Pooling and Hybrid Convolutional Operations for Text Representations
Another limitation of GCN when used on graph-based text representation tasks is that, GCNs do not consider the order information of nodes in graph.
Non-local U-Net for Biomedical Image Segmentation
In this work, we propose the non-local U-Nets, which are equipped with flexible global aggregation blocks, for biomedical image segmentation.
ChannelNets: Compact and Efficient Convolutional Neural Networks via Channel-Wise Convolutions
Compared to prior CNNs designed for mobile devices, ChannelNets achieve a significant reduction in terms of the number of parameters and computational cost without loss in accuracy.
Smoothed Dilated Convolutions for Improved Dense Prediction
Unlike existing models, which explore solutions by focusing on a block of cascaded dilated convolutional layers, our methods address the gridding artifacts by smoothing the dilated convolution itself.
Large-Scale Learnable Graph Convolutional Networks
However, the number of neighboring units is neither fixed nor are they ordered in generic graphs, thereby hindering the applications of convolutional operations.
Ranked #2 on
Document Classification
on Cora
Efficient and Invariant Convolutional Neural Networks for Dense Prediction
In this paper, we propose a set of methods based on kernel rotation and flip to enable rotation and flip invariance in convolutional neural networks.
Dense Transformer Networks
The proposed dense transformer modules are differentiable, thus the entire network can be trained.
Multi-Stage Variational Auto-Encoders for Coarse-to-Fine Image Generation
In the simplest case, the proposed multi-stage VAE divides the decoder into two components in which the second component generates refined images based on the course images generated by the first component.
Pixel Deconvolutional Networks
When used in image generation tasks, our PixelDCL can largely overcome the checkerboard problem suffered by regular deconvolution operations.
Spatial Variational Auto-Encoding via Matrix-Variate Normal Distributions
In this work, we propose spatial VAEs that use feature maps of larger size as latent variables to explicitly capture spatial information.
Learning Convolutional Text Representations for Visual Question Answering
We also show that the text representation requirement in visual question answering is more complicated and comprehensive than that in conventional natural language processing tasks, making it a better task to evaluate textual representation methods.
Multi-label Multiple Kernel Learning
We present a multi-label multiple kernel learning (MKL) formulation, in which the data are embedded into a low-dimensional space directed by the instance-label correlations encoded into a hypergraph.
