Search Results for author:
Found 88 papers, 38 papers with code
A Chance-Constrained Generative Framework for Sequence Optimization
Deep generative modeling has achieved many successes for continuous data generation, such as producing realistic images and controlling their properties (e. g., styles).
DecompDiff: Diffusion Models with Decomposed Priors for Structure-Based Drug Design
Designing 3D ligands within a target binding site is a fundamental task in drug discovery.
Equivariant Neural Operator Learning with Graphon Convolution
We propose a general architecture that combines the coefficient learning scheme with a residual operator layer for learning mappings between continuous functions in the 3D Euclidean space.
InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation
Leveraging our new pipeline, we create, to the best of our knowledge, the first one-step diffusion-based text-to-image generator with SD-level image quality, achieving an FID (Frechet Inception Distance) of $23. 3$ on MS COCO 2017-5k, surpassing the previous state-of-the-art technique, progressive distillation, by a significant margin ($37. 2$ $\rightarrow$ $23. 3$ in FID).
3D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Prediction
Rich data and powerful machine learning models allow us to design drugs for a specific protein target \textit{in silico}.
Active Learning in Brain Tumor Segmentation with Uncertainty Sampling, Annotation Redundancy Restriction, and Data Initialization
We investigated uncertainty sampling, annotation redundancy restriction, and initial dataset selection techniques.
Efficient Meta Reinforcement Learning for Preference-based Fast Adaptation
To bridge this gap, we study the problem of few-shot adaptation in the context of human-in-the-loop reinforcement learning.
Dateformer: Time-modeling Transformer for Longer-term Series Forecasting
This, for fine-grained time series, leads to a bottleneck in information input and prediction output, which is mortal to long-term series forecasting.
Is Self-Supervised Learning More Robust Than Supervised Learning?
Our insight has implications in improving the downstream robustness of supervised learning.
A large-scale systematic survey reveals recurring molecular features of public antibody responses to SARS-CoV-2
Global research to combat the COVID-19 pandemic has led to the isolation and characterization of thousands of human antibodies to the SARS-CoV-2 spike protein, providing an unprecedented opportunity to study the antibody response to a single antigen.
Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pockets
Deep generative models have achieved tremendous success in designing novel drug molecules in recent years.
Imitation Learning from Observations under Transition Model Disparity
In this work, we propose an algorithm that trains an intermediary policy in the learner environment and uses it as a surrogate expert for the learner.
Equivariant Point Cloud Analysis via Learning Orientations for Message Passing
In this work, we propose a novel and simple framework to achieve equivariance for point cloud analysis based on the message passing (graph neural network) scheme.
A 3D Generative Model for Structure-Based Drug Design
In this paper, we propose a 3D generative model that generates molecules given a designated 3D protein binding site.
FastFold: Reducing AlphaFold Training Time from 11 Days to 67 Hours
In this work, we present FastFold, an efficient implementation of AlphaFold for both training and inference.
Overcome Anterograde Forgetting with Cycled Memory Networks
This work proposes a general framework named Cycled Memory Networks (CMN) to address the anterograde forgetting in neural networks for lifelong learning.
Learning Long-Term Reward Redistribution via Randomized Return Decomposition
Based on this framework, this paper proposes a novel reward redistribution algorithm, randomized return decomposition (RRD), to learn a proxy reward function for episodic reinforcement learning.
Reviewing continual learning from the perspective of human-level intelligence
Different from previous reviews that mainly focus on the catastrophic forgetting phenomenon in CL, this paper surveys CL from a more macroscopic perspective based on the Stability Versus Plasticity mechanism.
Learning by Active Forgetting for Neural Networks
This paper presents a learning model by active forgetting mechanism with artificial neural networks.
Neural Energy Minimization for Molecular Conformation Optimization
Assuming different forms of the underlying potential energy function, we can not only reinterpret and unify many of the existing models but also derive new variants of SE(3)-equivariant neural networks in a principled manner.
Hindsight Foresight Relabeling for Meta-Reinforcement Learning
Meta-reinforcement learning (meta-RL) algorithms allow for agents to learn new behaviors from small amounts of experience, mitigating the sample inefficiency problem in RL.
Pixel Contrastive-Consistent Semi-Supervised Semantic Segmentation
We leverage the pixel-level L2 loss and the pixel contrastive loss for the two purposes respectively.
Coordinate-wise Control Variates for Deep Policy Gradients
The control variates (CV) method is widely used in policy gradient estimation to reduce the variance of the gradient estimators in practice.
Off-Policy Reinforcement Learning with Delayed Rewards
We study deep reinforcement learning (RL) algorithms with delayed rewards.
DAP: Detection-Aware Pre-training with Weak Supervision
This paper presents a detection-aware pre-training (DAP) approach, which leverages only weakly-labeled classification-style datasets (e. g., ImageNet) for pre-training, but is specifically tailored to benefit object detection tasks.
Learning Neural Generative Dynamics for Molecular Conformation Generation
Inspired by the recent progress in deep generative models, in this paper, we propose a novel probabilistic framework to generate valid and diverse conformations given a molecular graph.
Harnessing Distribution Ratio Estimators for Learning Agents with Quality and Diversity
Quality-Diversity (QD) is a concept from Neuroevolution with some intriguing applications to Reinforcement Learning.
Off-Policy Interval Estimation with Lipschitz Value Iteration
Off-policy evaluation provides an essential tool for evaluating the effects of different policies or treatments using only observed data.
Hunting for Dark Matter Subhalos in Strong Gravitational Lensing with Neural Networks
Dark matter substructures are interesting since they can reveal the properties of dark matter.
Cosmology and Nongalactic Astrophysics Computational Physics
Learning Guidance Rewards with Trajectory-space Smoothing
To make credit assignment easier, recent works have proposed algorithms to learn dense "guidance" rewards that could be used in place of the sparse or delayed environmental rewards.
Efficient Competitive Self-Play Policy Optimization
Reinforcement learning from self-play has recently reported many successes.
Pre-training of Graph Neural Network for Modeling Effects of Mutations on Protein-Protein Binding Affinity
Modeling the effects of mutations on the binding affinity plays a crucial role in protein engineering and drug design.
Boosting Weakly Supervised Object Detection with Progressive Knowledge Transfer
In this paper, we propose an effective knowledge transfer framework to boost the weakly supervised object detection accuracy with the help of an external fully-annotated source dataset, whose categories may not overlap with the target domain.
Accelerating Nonconvex Learning via Replica Exchange Langevin Diffusion
To attain the advantages of both regimes, we propose to use replica exchange, which swaps between two Langevin diffusions with different temperatures.
Mutual Information Based Knowledge Transfer Under State-Action Dimension Mismatch
In this paper, we propose a new framework for transfer learning where the teacher and the student can have arbitrarily different state- and action-spaces.
DASNet: Dual attentive fully convolutional siamese networks for change detection of high resolution satellite images
However, the available methods focus mainly on the difference information between multitemporal remote sensing images and lack robustness to pseudo-change information.
Stein Variational Inference for Discrete Distributions
In addition, such transform can be straightforwardly employed in gradient-free kernelized Stein discrepancy to perform goodness-of-fit (GOF) test on discrete distributions.
State-only Imitation with Transition Dynamics Mismatch
Imitation Learning (IL) is a popular paradigm for training agents to achieve complicated goals by leveraging expert behavior, rather than dealing with the hardships of designing a correct reward function.
Disentangling Controllable Object through Video Prediction Improves Visual Reinforcement Learning
In many vision-based reinforcement learning (RL) problems, the agent controls a movable object in its visual field, e. g., the player's avatar in video games and the robotic arm in visual grasping and manipulation.
Convolution Neural Network Architecture Learning for Remote Sensing Scene Classification
The feature-learning procedure of CNN largely depends on the architecture of CNN.
cube2net: Efficient Query-Specific Network Construction with Data Cube Organization
With extensive experiments of two classic network mining tasks on different real-world large datasets, we show that our proposed cube2net pipeline is general, and much more effective and efficient in query-specific network construction, compared with other methods without the leverage of data cube or reinforcement learning.
Overcoming Long-term Catastrophic Forgetting through Adversarial Neural Pruning and Synaptic Consolidation
It is due to two facts: first, as the model learns more tasks, the intersection of the low-error parameter subspace satisfying for these tasks becomes smaller or even does not exist; second, when the model learns a new task, the cumulative error keeps increasing as the model tries to protect the parameter configuration of previous tasks from interference.
DeepMask: an algorithm for cloud and cloud shadow detection in optical satellite remote sensing images using deep residual network
The average accuracy is 93. 56%, compared with 85. 36% from CFMask.
HeteSpaceyWalk: A Heterogeneous Spacey Random Walk for Heterogeneous Information Network Embedding
Heterogeneous information network (HIN) embedding has gained increasing interests recently.
$\sqrt{n}$-Regret for Learning in Markov Decision Processes with Function Approximation and Low Bellman Rank
Our learning algorithm, Adaptive Value-function Elimination (AVE), is inspired by the policy elimination algorithm proposed in (Jiang et al., 2017), known as OLIVE.
Characterizing Attacks on Deep Reinforcement Learning
To the best of our knowledge, we are the first to apply adversarial attacks on DRL systems to physical robots.
Learning Belief Representations for Imitation Learning in POMDPs
We consider the problem of imitation learning from expert demonstrations in partially observable Markov decision processes (POMDPs).
Exploration via Hindsight Goal Generation
Goal-oriented reinforcement learning has recently been a practical framework for robotic manipulation tasks, in which an agent is required to reach a certain goal defined by a function on the state space.
A gradual, semi-discrete approach to generative network training via explicit Wasserstein minimization
This paper provides a simple procedure to fit generative networks to target distributions, with the goal of a small Wasserstein distance (or other optimal transport costs).
Sequence Modeling of Temporal Credit Assignment for Episodic Reinforcement Learning
Recent advances in deep reinforcement learning algorithms have shown great potential and success for solving many challenging real-world problems, including Go game and robotic applications.
Thresholding Bandit with Optimal Aggregate Regret
We consider the thresholding bandit problem, whose goal is to find arms of mean rewards above a given threshold $\theta$, with a fixed budget of $T$ trials.
Stochastic Variance Reduction for Deep Q-learning
Recent advances in deep reinforcement learning have achieved human-level performance on a variety of real-world applications.
Knowledge Flow: Improve Upon Your Teachers
A zoo of deep nets is available these days for almost any given task, and it is increasingly unclear which net to start with when addressing a new task, or which net to use as an initialization for fine-tuning a new model.
Understanding the Importance of Single Directions via Representative Substitution
Understanding the internal representations of deep neural networks (DNNs) is crucal to explain their behavior.
Overcoming Catastrophic Forgetting by Soft Parameter Pruning
In this paper, we proposed a Soft Parameters Pruning (SPP) strategy to reach the trade-off between short-term and long-term profit of a learning model by freeing those parameters less contributing to remember former task domain knowledge to learn future tasks, and preserving memories about previous tasks via those parameters effectively encoding knowledge about tasks at the same time.
Anchor Box Optimization for Object Detection
In this paper, we propose a general approach to optimize anchor boxes for object detection.
Understanding the Importance of Single Directions via Representative Substitution
Understanding the internal representations of deep neural networks (DNNs) is crucal to explain their behavior.
SemRegex: A Semantics-Based Approach for Generating Regular Expressions from Natural Language Specifications
Recent research proposes syntax-based approaches to address the problem of generating programs from natural language specifications.
Shrinkage-based Bias-Variance Trade-off for Deep Reinforcement Learning
Deep reinforcement learning has achieved remarkable successes in solving various challenging artificial intelligence tasks.
emrQA: A Large Corpus for Question Answering on Electronic Medical Records
We propose a novel methodology to generate domain-specific large-scale question answering (QA) datasets by re-purposing existing annotations for other NLP tasks.
Off-Policy Evaluation and Learning from Logged Bandit Feedback: Error Reduction via Surrogate Policy
Such an error reduction phenomenon is somewhat surprising as the estimated surrogate policy is less accurate than the given historical policy.
Learning to Explore via Meta-Policy Gradient
The performance of off-policy learning, including deep Q-learning and deep deterministic policy gradient (DDPG), critically depends on the choice of the exploration policy.
Large-Margin Classification in Hyperbolic Space
Representing data in hyperbolic space can effectively capture latent hierarchical relationships.
Learning Self-Imitating Diverse Policies
Improving the efficiency of RL algorithms in real-world problems with sparse or episodic rewards is therefore a pressing need.
Efficient Contextualized Representation: Language Model Pruning for Sequence Labeling
Many efforts have been made to facilitate natural language processing tasks with pre-trained language models (LMs), and brought significant improvements to various applications.
Ranked #47 on
Named Entity Recognition (NER)
on CoNLL 2003 (English)
Learning to Explore with Meta-Policy Gradient
The performance of off-policy learning, including deep Q-learning and deep deterministic policy gradient (DDPG), critically depends on the choice of the exploration policy.
The Importance of Norm Regularization in Linear Graph Embedding: Theoretical Analysis and Empirical Demonstration
Both theoretical and empirical evidence are provided to support this argument: (a) we prove that the generalization error of these methods can be bounded by limiting the norm of vectors, regardless of the embedding dimension; (b) we show that the generalization performance of linear graph embedding methods is correlated with the norm of embedding vectors, which is small due to the early stopping of SGD and the vanishing gradients.
Action-dependent Control Variates for Policy Optimization via Stein Identity
Policy gradient methods have achieved remarkable successes in solving challenging reinforcement learning problems.
Fast and Accurate Text Classification: Skimming, Rereading and Early Stopping
Recent advances in recurrent neural nets (RNNs) have shown much promise in many applications in natural language processing.
Policy Optimization by Genetic Distillation
GPO uses imitation learning for policy crossover in the state space and applies policy gradient methods for mutation.
Action-depedent Control Variates for Policy Optimization via Stein's Identity
Policy gradient methods have achieved remarkable successes in solving challenging reinforcement learning problems.
Efficient Localized Inference for Large Graphical Models
We propose a new localized inference algorithm for answering marginalization queries in large graphical models with the correlation decay property.
Stochastic Variance Reduction for Policy Gradient Estimation
Recent advances in policy gradient methods and deep learning have demonstrated their applicability for complex reinforcement learning problems.
Energy-efficient Amortized Inference with Cascaded Deep Classifiers
Deep neural networks have been remarkable successful in various AI tasks but often cast high computation and energy cost for energy-constrained applications such as mobile sensing.
Empower Sequence Labeling with Task-Aware Neural Language Model
In this study, we develop a novel neural framework to extract abundant knowledge hidden in raw texts to empower the sequence labeling task.
Ranked #13 on
Part-Of-Speech Tagging
on Penn Treebank
On the Selective and Invariant Representation of DCNN for High-Resolution Remote Sensing Image Recognition
Owing to its superiority in feature representation, DCNN has exhibited remarkable performance in scene recognition of high-resolution remote sensing (HRRS) images and classification of hyper-spectral remote sensing images.
RSI-CB: A Large Scale Remote Sensing Image Classification Benchmark via Crowdsource Data
In this paper, we propose a remote sensing image classification benchmark (RSI-CB) based on massive, scalable, and diverse crowdsource data.
What do We Learn by Semantic Scene Understanding for Remote Sensing imagery in CNN framework?
Is the DCNN recognition mechanism centered on object recognition still applicable to the scenarios of remote sensing scene understanding?
Stein Variational Policy Gradient
Policy gradient methods have been successfully applied to many complex reinforcement learning problems.
Learning to Play in a Day: Faster Deep Reinforcement Learning by Optimality Tightening
We propose a novel training algorithm for reinforcement learning which combines the strength of deep Q-learning with a constrained optimization approach to tighten optimality and encourage faster reward propagation.
DPPred: An Effective Prediction Framework with Concise Discriminative Patterns
In the literature, two series of models have been proposed to address prediction problems including classification and regression.
Meta-Path Guided Embedding for Similarity Search in Large-Scale Heterogeneous Information Networks
It models vertices as low-dimensional vectors to explore network structure-embedded similarity.
Protein secondary structure prediction using deep convolutional neural fields
Protein secondary structure (SS) prediction is important for studying protein structure and function.
Ranked #1 on
Protein Secondary Structure Prediction
on CullPDB
On the Interpretability of Conditional Probability Estimates in the Agnostic Setting
We study the interpretability of conditional probability estimates for binary classification under the agnostic setting or scenario.
Diffusion Component Analysis: Unraveling Functional Topology in Biological Networks
In this paper, we introduce diffusion component analysis (DCA), a framework that plugs in a diffusion model and learns a low-dimensional vector representation of each node to encode the topological properties of a network.
Exact Hybrid Covariance Thresholding for Joint Graphical Lasso
This paper proposes a novel hybrid covariance thresholding algorithm that can effectively identify zero entries in the precision matrices and split a large joint graphical lasso problem into small subproblems.
Variational Inference for Crowdsourcing
Crowdsourcing has become a popular paradigm for labeling large datasets.
Conditional Neural Fields
To model the nonlinear relationship between input features and outputs we propose Conditional Neural Fields (CNF), a new conditional probabilistic graphical model for sequence labeling.
