Search Results for author:
Found 56 papers, 17 papers with code
OBELiX: A Curated Dataset of Crystal Structures and Experimentally Measured Ionic Conductivities for Lithium Solid-State Electrolytes
The goal of this work is to facilitate the use of machine learning for solid-state electrolyte materials discovery.
Baichuan-Omni-1.5 Technical Report
We introduce Baichuan-Omni-1. 5, an omni-modal model that not only has omni-modal understanding capabilities but also provides end-to-end audio generation capabilities.
A High Energy-Efficiency Multi-core Neuromorphic Architecture for Deep SNN Training
There is a growing necessity for edge training to adapt to dynamically changing environment.
Structure Language Models for Protein Conformation Generation
In this paper, we introduce Structure Language Modeling (SLM) as a novel framework for efficient protein conformation generation.
Manifold-Constrained Nucleus-Level Denoising Diffusion Model for Structure-Based Drug Design
Artificial intelligence models have shown great potential in structure-based drug design, generating ligands with high binding affinities.
$f$-MICL: Understanding and Generalizing InfoNCE-based Contrastive Learning
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.
A Multi-Grained Symmetric Differential Equation Model for Learning Protein-Ligand Binding Dynamics
We demonstrate the efficiency and effectiveness of NeuralMD, achieving over 1K$\times$ speedup compared to standard numerical MD simulations.
Calibration Attacks: A Comprehensive Study of Adversarial Attacks on Model Confidence
In this work, we highlight and perform a comprehensive study on calibration attacks, a form of adversarial attacks that aim to trap victim models to be heavily miscalibrated without altering their predicted labels, hence endangering the trustworthiness of the models and follow-up decision making based on their confidence.
Symmetry-Informed Geometric Representation for Molecules, Proteins, and Crystalline Materials
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.
ChatGPT-powered Conversational Drug Editing Using Retrieval and Domain Feedback
This research sheds light on the potential of ChatGPT and conversational LLMs for drug editing.
A Group Symmetric Stochastic Differential Equation Model for Molecule Multi-modal Pretraining
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.
Wheat Head Counting by Estimating a Density Map with Convolutional Neural Networks
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.
Effectiveness of Data Augmentation for Parameter Efficient Tuning with Limited Data
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.
T-Cell Receptor Optimization with Reinforcement Learning and Mutation Policies for Precesion Immunotherapy
This process is known as TCR recognition and constitutes a key step for immune response.
Over-training with Mixup May Hurt Generalization
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
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.
A Text-guided Protein Design Framework
Current AI-assisted protein design mainly utilizes protein sequential and structural information.
Modeling driver's evasive behavior during safety-critical lane changes:Two-dimensional time-to-collision and deep reinforcement learning
Lane changes are complex driving behaviors and frequently involve safety-critical situations.
Molecular Geometry Pretraining with SE(3)-Invariant Denoising Distance Matching
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.
SoftEdge: Regularizing Graph Classification with Random Soft Edges
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.
ifMixup: Interpolating Graph Pair to Regularize Graph Classification
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.
Pre-training Molecular Graph Representation with 3D Geometry
However, the lack of 3D information in real-world scenarios has significantly impeded the learning of geometric graph representation.
Intrusion-Free Graph Mixup
We present a simple and yet effective interpolation-based regularization technique to improve the generalization of Graph Neural Networks (GNNs).
$f$-Mutual Information Contrastive Learning
Self-supervised contrastive learning is an emerging field due to its power in providing good data representations.
How Curriculum Learning Impacts Model Calibration
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.
Midpoint Regularization: from High Uncertainty Training to Conservative Classification
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.
Symmetric Wasserstein Autoencoders
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
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
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.
Bypassing the Random Input Mixing in Mixup
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
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
SkipGram word embedding models with negative sampling, or SGN in short, is an elegant family of word embedding models.
A Graph to Graphs Framework for Retrosynthesis Prediction
A fundamental problem in computational chemistry is to find a set of reactants to synthesize a target molecule, a. k. a.
Ranked #29 on
Single-step retrosynthesis
on USPTO-50k
Aggregated Learning: A Vector-Quantization Approach to Learning Neural Network Classifiers
We show that IB learning is, in fact, equivalent to a special class of the quantization problem.
Weighted graphlets and deep neural networks for protein structure classification
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.
MixUp as Directional Adversarial Training
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
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.
Syntax Encoding with Application in Authorship Attribution
We propose a novel strategy to encode the syntax parse tree of sentence into a learnable distributed representation.
MixUp as Locally Linear Out-Of-Manifold Regularization
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.
Aggregated Learning: A Deep Learning Framework Based on Information-Bottleneck Vector Quantization
Based on the notion of information bottleneck (IB), we formulate a quantization problem called "IB quantization".
Parametric t-Distributed Stochastic Exemplar-centered Embedding
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.
A Deep Network with Visual Text Composition Behavior
While natural languages are compositional, how state-of-the-art neural models achieve compositionality is still unclear.
End-to-End Multi-View Networks for Text Classification
For a bag-of-words representation, each view focuses on a different subset of the text's words.
Exemplar-Centered Supervised Shallow Parametric Data Embedding
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.
A Shallow High-Order Parametric Approach to Data Visualization and Compression
These exemplars in combination with the feature mapping learned by HOPE effectively capture essential data variations.
Generating Text with Deep Reinforcement Learning
The newly modified output sequence is subsequently used as the input to the DQN for the next decoding iteration.
A Deep Learning Model for Structured Outputs with High-order Interaction
Many real-world applications are associated with structured data, where not only input but also output has interplay.
Long Short-Term Memory Over Tree Structures
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.
