Search Results for author: Hongyu Guo

Found 51 papers, 13 papers with code

$f$-MICL: Understanding and Generalizing InfoNCE-based Contrastive Learning

no code implementations15 Feb 2024 Yiwei Lu, Guojun Zhang, Sun Sun, Hongyu Guo, YaoLiang Yu

In self-supervised contrastive learning, a widely-adopted objective function is InfoNCE, which uses the heuristic cosine similarity for the representation comparison, and is closely related to maximizing the Kullback-Leibler (KL)-based mutual information.

Contrastive Learning

A Multi-Grained Symmetric Differential Equation Model for Learning Protein-Ligand Binding Dynamics

no code implementations26 Jan 2024 Shengchao Liu, Weitao Du, Yanjing Li, Zhuoxinran Li, Vignesh Bhethanabotla, Nakul Rampal, Omar Yaghi, Christian Borgs, Anima Anandkumar, Hongyu Guo, Jennifer Chayes

We show the efficiency and effectiveness of NeuralMD, with a 2000$\times$ speedup over standard numerical MD simulation and outperforming all other ML approaches by up to 80% under the stability metric.

Drug Discovery

Calibration Attack: A Framework For Adversarial Attacks Targeting Calibration

no code implementations5 Jan 2024 Stephen Obadinma, Xiaodan Zhu, Hongyu Guo

We introduce a new framework of adversarial attacks, named calibration attacks, in which the attacks are generated and organized to trap victim models to be miscalibrated without altering their original accuracy, hence seriously endangering the trustworthiness of the models and any decision-making based on their confidence scores.

Decision Making

Symmetry-Informed Geometric Representation for Molecules, Proteins, and Crystalline Materials

1 code implementation NeurIPS 2023 Shengchao Liu, Weitao Du, Yanjing Li, Zhuoxinran Li, Zhiling Zheng, Chenru Duan, ZhiMing Ma, Omar Yaghi, Anima Anandkumar, Christian Borgs, Jennifer Chayes, Hongyu Guo, Jian Tang

Artificial intelligence for scientific discovery has recently generated significant interest within the machine learning and scientific communities, particularly in the domains of chemistry, biology, and material discovery.


A Group Symmetric Stochastic Differential Equation Model for Molecule Multi-modal Pretraining

1 code implementation28 May 2023 Shengchao Liu, Weitao Du, ZhiMing Ma, Hongyu Guo, Jian Tang

Meanwhile, existing molecule multi-modal pretraining approaches approximate MI based on the representation space encoded from the topology and geometry, thus resulting in the loss of critical structural information of molecules.

Drug Discovery

Wheat Head Counting by Estimating a Density Map with Convolutional Neural Networks

no code implementations19 Mar 2023 Hongyu Guo

The WHCNets are composed of two major components: a convolutional neural network (CNN) as the front-end for wheat head image feature extraction and a CNN with skip connections for the back-end to generate high-quality density maps.

Head Detection

Effectiveness of Data Augmentation for Parameter Efficient Tuning with Limited Data

no code implementations5 Mar 2023 Stephen Obadinma, Hongyu Guo, Xiaodan Zhu

In this paper, we examine the effectiveness of several popular task-agnostic data augmentation techniques, i. e., EDA, Back Translation, and Mixup, when using two general parameter efficient tuning methods, P-tuning v2 and LoRA, under data scarcity.

Data Augmentation Sentence +1

Over-training with Mixup May Hurt Generalization

no code implementations2 Mar 2023 Zixuan Liu, Ziqiao Wang, Hongyu Guo, Yongyi Mao

Mixup, which creates synthetic training instances by linearly interpolating random sample pairs, is a simple and yet effective regularization technique to boost the performance of deep models trained with SGD.

GraphVF: Controllable Protein-Specific 3D Molecule Generation with Variational Flow

1 code implementation23 Feb 2023 Fang Sun, Zhihao Zhan, Hongyu Guo, Ming Zhang, Jian Tang

In particular, GraphVF represents the first controllable geometry-aware, protein-specific molecule generation method, which can generate binding 3D molecules with tailored sub-structures and physio-chemical properties.

3D Molecule Generation Drug Discovery

Molecular Geometry Pretraining with SE(3)-Invariant Denoising Distance Matching

2 code implementations27 Jun 2022 Shengchao Liu, Hongyu Guo, Jian Tang

Further by leveraging an SE(3)-invariant score matching method, we propose GeoSSL-DDM in which the coordinate denoising proxy task is effectively boiled down to denoising the pairwise atomic distances in a molecule.

Denoising molecular representation

SoftEdge: Regularizing Graph Classification with Random Soft Edges

no code implementations21 Apr 2022 Hongyu Guo, Sun Sun

Augmented graphs play a vital role in regularizing Graph Neural Networks (GNNs), which leverage information exchange along edges in graphs, in the form of message passing, for learning.

Data Augmentation Graph Classification

ifMixup: Interpolating Graph Pair to Regularize Graph Classification

no code implementations18 Oct 2021 Hongyu Guo, Yongyi Mao

We present a simple and yet effective interpolation-based regularization technique, aiming to improve the generalization of Graph Neural Networks (GNNs) on supervised graph classification.

Graph Classification

Pre-training Molecular Graph Representation with 3D Geometry

1 code implementation ICLR 2022 Shengchao Liu, Hanchen Wang, Weiyang Liu, Joan Lasenby, Hongyu Guo, Jian Tang

However, the lack of 3D information in real-world scenarios has significantly impeded the learning of geometric graph representation.

Graph Representation Learning Self-Supervised Learning

$f$-Mutual Information Contrastive Learning

no code implementations29 Sep 2021 Guojun Zhang, Yiwei Lu, Sun Sun, Hongyu Guo, YaoLiang Yu

Self-supervised contrastive learning is an emerging field due to its power in providing good data representations.

Contrastive Learning

How Curriculum Learning Impacts Model Calibration

no code implementations29 Sep 2021 Stephen Obadinma, Xiaodan Zhu, Hongyu Guo

Our studies suggest the following: most of the time curriculum learning has a negligible effect on calibration, but in certain cases under the context of limited training time and noisy data, curriculum learning can substantially reduce calibration error in a manner that cannot be explained by dynamically sampling the dataset.

Intrusion-Free Graph Mixup

no code implementations29 Sep 2021 Hongyu Guo, Yongyi Mao

We present a simple and yet effective interpolation-based regularization technique to improve the generalization of Graph Neural Networks (GNNs).

Graph Classification

Midpoint Regularization: from High Uncertainty Training to Conservative Classification

no code implementations26 Jun 2021 Hongyu Guo

PLS first creates midpoint samples by averaging random sample pairs and then learns a smoothing distribution during training for each of these midpoint samples, resulting in midpoints with high uncertainty labels for training.

Classification Vocal Bursts Intensity Prediction

Symmetric Wasserstein Autoencoders

1 code implementation24 Jun 2021 Sun Sun, Hongyu Guo

With the symmetric treatment of the data and the latent representation, the algorithm implicitly preserves the local structure of the data in the latent space.


Non-Autoregressive Electron Redistribution Modeling for Reaction Prediction

no code implementations8 Jun 2021 Hangrui Bi, Hengyi Wang, Chence Shi, Connor Coley, Jian Tang, Hongyu Guo

Reliably predicting the products of chemical reactions presents a fundamental challenge in synthetic chemistry.

Self-supervised Graph-level Representation Learning with Local and Global Structure

1 code implementation8 Jun 2021 Minghao Xu, Hang Wang, Bingbing Ni, Hongyu Guo, Jian Tang

This paper studies unsupervised/self-supervised whole-graph representation learning, which is critical in many tasks such as molecule properties prediction in drug and material discovery.

Graph Representation Learning

Bypassing the Random Input Mixing in Mixup

no code implementations1 Jan 2021 Hongyu Guo

Mixup and its variants have promoted a surge of interest due to their capability of boosting the accuracy of deep models.


Regularization via Adaptive Pairwise Label Smoothing

no code implementations2 Dec 2020 Hongyu Guo

Label Smoothing (LS) is an effective regularizer to improve the generalization of state-of-the-art deep models.

On SkipGram Word Embedding Models with Negative Sampling: Unified Framework and Impact of Noise Distributions

no code implementations2 Sep 2020 Ziqiao Wang, Yongyi Mao, Hongyu Guo, Richong Zhang

SkipGram word embedding models with negative sampling, or SGN in short, is an elegant family of word embedding models.

Weighted graphlets and deep neural networks for protein structure classification

no code implementations7 Oct 2019 Hongyu Guo, Khalique Newaz, Scott Emrich, Tijana Milenkovic, Jun Li

We develop a weighted network that depicts the protein structures, and more importantly, we propose the first graphlet-based measure that applies to weighted networks.

Classification General Classification

Uncover the Ground-Truth Relations in Distant Supervision: A Neural Expectation-Maximization Framework

1 code implementation IJCNLP 2019 Junfan Chen, Richong Zhang, Yongyi Mao, Hongyu Guo, Jie Xu

Distant supervision for relation extraction enables one to effectively acquire structured relations out of very large text corpora with less human efforts.

Denoising Relation +1

MixUp as Directional Adversarial Training

no code implementations ICLR 2020 Guillaume P. Archambault, Yongyi Mao, Hongyu Guo, Richong Zhang

We prove that the family of Untied MixUp schemes is equivalent to the entire class of DAT schemes.

Augmenting Data with Mixup for Sentence Classification: An Empirical Study

2 code implementations22 May 2019 Hongyu Guo, Yongyi Mao, Richong Zhang

Mixup, a recent proposed data augmentation method through linearly interpolating inputs and modeling targets of random samples, has demonstrated its capability of significantly improving the predictive accuracy of the state-of-the-art networks for image classification.

Classification Data Augmentation +6

Syntax Encoding with Application in Authorship Attribution

no code implementations EMNLP 2018 Richong Zhang, Zhiyuan Hu, Hongyu Guo, Yongyi Mao

We propose a novel strategy to encode the syntax parse tree of sentence into a learnable distributed representation.

Benchmarking Feature Engineering +2

MixUp as Locally Linear Out-Of-Manifold Regularization

2 code implementations7 Sep 2018 Hongyu Guo, Yongyi Mao, Richong Zhang

To address this issue, we propose a novel adaptive version of MixUp, where the mixing policies are automatically learned from the data using an additional network and objective function designed to avoid manifold intrusion.

Data Augmentation

Parametric t-Distributed Stochastic Exemplar-centered Embedding

no code implementations14 Oct 2017 Martin Renqiang Min, Hongyu Guo, Dinghan Shen

Parametric embedding methods such as parametric t-SNE (pt-SNE) have been widely adopted for data visualization and out-of-sample data embedding without further computationally expensive optimization or approximation.

Data Visualization

A Deep Network with Visual Text Composition Behavior

no code implementations ACL 2017 Hongyu Guo

While natural languages are compositional, how state-of-the-art neural models achieve compositionality is still unclear.

General Classification Sentence +2

End-to-End Multi-View Networks for Text Classification

no code implementations19 Apr 2017 Hongyu Guo, Colin Cherry, Jiang Su

For a bag-of-words representation, each view focuses on a different subset of the text's words.

General Classification text-classification +1

Exemplar-Centered Supervised Shallow Parametric Data Embedding

no code implementations21 Feb 2017 Martin Renqiang Min, Hongyu Guo, Dongjin Song

Our strategy learns a shallow high-order parametric embedding function and compares training/test data only with learned or precomputed exemplars, resulting in a cost function with linear computational complexity for both training and testing.

Dimensionality Reduction General Classification +4

A Shallow High-Order Parametric Approach to Data Visualization and Compression

no code implementations16 Aug 2016 Martin Renqiang Min, Hongyu Guo, Dongjin Song

These exemplars in combination with the feature mapping learned by HOPE effectively capture essential data variations.

Computational Efficiency Data Visualization +5

Generating Text with Deep Reinforcement Learning

no code implementations30 Oct 2015 Hongyu Guo

The newly modified output sequence is subsequently used as the input to the DQN for the next decoding iteration.

reinforcement-learning Reinforcement Learning (RL) +1

A Deep Learning Model for Structured Outputs with High-order Interaction

no code implementations29 Apr 2015 Hongyu Guo, Xiaodan Zhu, Martin Renqiang Min

Many real-world applications are associated with structured data, where not only input but also output has interplay.

Classification General Classification +2

Long Short-Term Memory Over Tree Structures

no code implementations16 Mar 2015 Xiaodan Zhu, Parinaz Sobhani, Hongyu Guo

The chain-structured long short-term memory (LSTM) has showed to be effective in a wide range of problems such as speech recognition and machine translation.

Machine Translation Natural Language Understanding +4

Cannot find the paper you are looking for? You can Submit a new open access paper.