Search Results for author:
Found 120 papers, 48 papers with code
Exploring the Generalization Capabilities of AID-based Bi-level Optimization
We conduct a convergence analysis for a carefully chosen step size to maintain stability.
Online Parallel Multi-Task Relationship Learning via Alternating Direction Method of Multipliers
In a classical distributed computing architecture with a central server, the proposed OMTL algorithm with the ADMM optimizer outperforms SGD-based approaches in terms of accuracy and efficiency.
Scaling Diffusion Language Models via Adaptation from Autoregressive Models
Diffusion Language Models (DLMs) have emerged as a promising new paradigm for text generative modeling, potentially addressing limitations of autoregressive (AR) models.
COME: Test-time adaption by Conservatively Minimizing Entropy
Machine learning models must continuously self-adjust themselves for novel data distribution in the open world.
Probing the Safety Response Boundary of Large Language Models via Unsafe Decoding Path Generation
Trained on external or self-generated harmful datasets, the cost value model could successfully influence the original safe LLM to output toxic content in decoding process.
Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Models
While Large Vision-Language Models (LVLMs) have rapidly advanced in recent years, the prevalent issue known as the `hallucination' problem has emerged as a significant bottleneck, hindering their real-world deployments.
MGCP: A Multi-Grained Correlation based Prediction Network for Multivariate Time Series
Multivariate time series prediction is widely used in daily life, which poses significant challenges due to the complex correlations that exist at multi-grained levels.
Variational Bayes for Federated Continual Learning
Federated continual learning (FCL) has received increasing attention due to its potential in handling real-world streaming data, characterized by evolving data distributions and varying client classes over time.
Test-Time Model Adaptation with Only Forward Passes
However, in real-world scenarios, models are usually deployed on resource-limited devices, e. g., FPGAs, and are often quantized and hard-coded with non-modifiable parameters for acceleration.
Uncertainty-Calibrated Test-Time Model Adaptation without Forgetting
To tackle this, we further propose EATA with Calibration (EATA-C) to separately exploit the reducible model uncertainty and the inherent data uncertainty for calibrated TTA.
Spurious Feature Eraser: Stabilizing Test-Time Adaptation for Vision-Language Foundation Model
Vision-language foundation models have exhibited remarkable success across a multitude of downstream tasks due to their scalability on extensive image-text paired data.
Step-On-Feet Tuning: Scaling Self-Alignment of LLMs via Bootstrapping
To further exploit the capabilities of bootstrapping, we investigate and adjust the training order of data, which yields improved performance of the model.
Enhancing Neural Subset Selection: Integrating Background Information into Set Representations
Learning neural subset selection tasks, such as compound selection in AI-aided drug discovery, have become increasingly pivotal across diverse applications.
WatME: Towards Lossless Watermarking Through Lexical Redundancy
Text watermarking has emerged as a pivotal technique for identifying machine-generated text.
LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay
This paper explores the open research problem of understanding the social behaviors of LLM-based agents.
ETDock: A Novel Equivariant Transformer for Protein-Ligand Docking
Predicting the docking between proteins and ligands is a crucial and challenging task for drug discovery.
Adapting Large Language Models for Content Moderation: Pitfalls in Data Engineering and Supervised Fine-tuning
Specifically, we discuss the differences between discriminative and generative models using content moderation as an example.
Are Large Language Models Really Robust to Word-Level Perturbations?
Notably, we are surprised to discover that robustness tends to decrease as fine-tuning (SFT and RLHF) is conducted.
SEGNO: Generalizing Equivariant Graph Neural Networks with Physical Inductive Biases
Furthermore, we offer theoretical insights into SEGNO, highlighting that it can learn a unique trajectory between adjacent states, which is crucial for model generalization.
DFWLayer: Differentiable Frank-Wolfe Optimization Layer
Differentiable optimization has received a significant amount of attention due to its foundational role in the domain of machine learning based on neural networks.
SR-R$^2$KAC: Improving Single Image Defocus Deblurring
To further alleviate the contingent effect of recursive stacking, i. e., ringing artifacts, we add identity shortcuts between atrous convolutions to simulate residual deconvolutions.
A Unified View of Deep Learning for Reaction and Retrosynthesis Prediction: Current Status and Future Challenges
Reaction and retrosynthesis prediction are fundamental tasks in computational chemistry that have recently garnered attention from both the machine learning and drug discovery communities.
GADBench: Revisiting and Benchmarking Supervised Graph Anomaly Detection
With a long history of traditional Graph Anomaly Detection (GAD) algorithms and recently popular Graph Neural Networks (GNNs), it is still not clear (1) how they perform under a standard comprehensive setting, (2) whether GNNs can outperform traditional algorithms such as tree ensembles, and (3) how about their efficiency on large-scale graphs.
PACER: A Fully Push-forward-based Distributional Reinforcement Learning Algorithm
As a result, PACER fully utilizes the modeling capability of the push-forward operator and is able to explore a broader class of the policy space, compared with limited policy classes used in existing distributional actor critic algorithms (i. e. Gaussians).
Doubly Stochastic Graph-based Non-autoregressive Reaction Prediction
However, the current non-autoregressive decoder does not satisfy two essential rules of electron redistribution modeling simultaneously: the electron-counting rule and the symmetry rule.
Attention Paper: How Generative AI Reshapes Digital Shadow Industry?
The rapid development of digital economy has led to the emergence of various black and shadow internet industries, which pose potential risks that can be identified and managed through digital risk management (DRM) that uses different techniques such as machine learning and deep learning.
SyNDock: N Rigid Protein Docking via Learnable Group Synchronization
Firstly, SyNDock formulates multimeric protein docking as a problem of learning global transformations to holistically depict the placement of chain units of a complex, enabling a learning-centric solution.
Reweighted Mixup for Subpopulation Shift
Subpopulation shift exists widely in many real-world applications, which refers to the training and test distributions that contain the same subpopulation groups but with different subpopulation proportions.
Deploying Offline Reinforcement Learning with Human Feedback
To address this issue, we propose an alternative framework that involves a human supervising the RL models and providing additional feedback in the online deployment phase.
Towards Stable Test-Time Adaptation in Dynamic Wild World
In this paper, we investigate the unstable reasons and find that the batch norm layer is a crucial factor hindering TTA stability.
Class-Conditional Sharpness-Aware Minimization for Deep Long-Tailed Recognition
It's widely acknowledged that deep learning models with flatter minima in its loss landscape tend to generalize better.
On the Pitfall of Mixup for Uncertainty Calibration
It has been recently found that models trained with mixup also perform well on uncertainty calibration.
Handling Missing Data via Max-Entropy Regularized Graph Autoencoder
In this work, we present a regularized graph autoencoder for graph attribute imputation, named MEGAE, which aims at mitigating spectral concentration problem by maximizing the graph spectral entropy.
Predicting Protein-Ligand Binding Affinity with Equivariant Line Graph Network
The proposed ELGN firstly adds a super node to the 3D complex, and then builds a line graph based on the 3D complex.
Vertical Federated Linear Contextual Bandits
In this paper, we investigate a novel problem of building contextual bandits in the vertical federated setting, i. e., contextual information is vertically distributed over different departments.
Robust Offline Reinforcement Learning with Gradient Penalty and Constraint Relaxation
A promising paradigm for offline reinforcement learning (RL) is to constrain the learned policy to stay close to the dataset behaviors, known as policy constraint offline RL.
Pareto-aware Neural Architecture Generation for Diverse Computational Budgets
More critically, these independent search processes cannot share their learned knowledge (i. e., the distribution of good architectures) with each other and thus often result in limited search results.
FusionRetro: Molecule Representation Fusion via In-Context Learning for Retrosynthetic Planning
Current strategies use a decoupled approach of single-step retrosynthesis models and search algorithms, taking only the product as the input to predict the reactants for each planning step and ignoring valuable context information along the synthetic route.
MARS: A Motif-based Autoregressive Model for Retrosynthesis Prediction
In this paper, we propose a novel end-to-end graph generation model for retrosynthesis prediction, which sequentially identifies the reaction center, generates the synthons, and adds motifs to the synthons to generate reactants.
Ranked #2 on
Single-step retrosynthesis
on USPTO-50k
UMIX: Improving Importance Weighting for Subpopulation Shift via Uncertainty-Aware Mixup
Importance reweighting is a normal way to handle the subpopulation shift issue by imposing constant or adaptive sampling weights on each sample in the training dataset.
ImDrug: A Benchmark for Deep Imbalanced Learning in AI-aided Drug Discovery
The last decade has witnessed a prosperous development of computational methods and dataset curation for AI-aided drug discovery (AIDD).
Quantized Adaptive Subgradient Algorithms and Their Applications
Therefore, a threshold quantization strategy with a relatively small error is adopted in QCMD adagrad and QRDA adagrad to improve the signal-to-noise ratio and preserve the sparsity of the model.
Pareto Invariant Risk Minimization: Towards Mitigating the Optimization Dilemma in Out-of-Distribution Generalization
Recently, there has been a growing surge of interest in enabling machine learning systems to generalize well to Out-of-Distribution (OOD) data.
ImGCL: Revisiting Graph Contrastive Learning on Imbalanced Node Classification
Motivated by this observation, we propose a principled GCL framework on Imbalanced node classification (ImGCL), which automatically and adaptively balances the representations learned from GCL without labels.
A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protection
Deep graph learning has achieved remarkable progresses in both business and scientific areas ranging from finance and e-commerce, to drug and advanced material discovery.
Multi-scale Attention Flow for Probabilistic Time Series Forecasting
The probability prediction of multivariate time series is a notoriously challenging but practical task.
GPN: A Joint Structural Learning Framework for Graph Neural Networks
To the best of our knowledge, our method is the first GNN-based bilevel optimization framework for resolving this task.
DRFLM: Distributionally Robust Federated Learning with Inter-client Noise via Local Mixup
In this paper, we propose a general framework to solve the above two challenges simultaneously.
Efficient Test-Time Model Adaptation without Forgetting
Test-time adaptation (TTA) seeks to tackle potential distribution shifts between training and testing data by adapting a given model w. r. t.
Boost Test-Time Performance with Closed-Loop Inference
Motivated by this, we propose to predict those hard-classified test samples in a looped manner to boost the model performance.
Learning Neural Set Functions Under the Optimal Subset Oracle
Learning neural set functions becomes increasingly more important in many applications like product recommendation and compound selection in AI-aided drug discovery.
Transformer for Graphs: An Overview from Architecture Perspective
In this survey, we provide a comprehensive review of various Graph Transformer models from the architectural design perspective.
Neighbour Interaction based Click-Through Rate Prediction via Graph-masked Transformer
Although these methods have made great progress, they are often limited by the recommender system's direct exposure and inactive interactions, and thus fail to mine all potential user interests.
DrugOOD: Out-of-Distribution (OOD) Dataset Curator and Benchmark for AI-aided Drug Discovery -- A Focus on Affinity Prediction Problems with Noise Annotations
AI-aided drug discovery (AIDD) is gaining increasing popularity due to its promise of making the search for new pharmaceuticals quicker, cheaper and more efficient.
RetroComposer: Composing Templates for Template-Based Retrosynthesis Prediction
To overcome this limitation, we propose an innovative retrosynthesis prediction framework that can compose novel templates beyond training templates.
Ranked #3 on
Single-step retrosynthesis
on USPTO-50k
SVIP: Sequence VerIfication for Procedures in Videos
In this paper, we propose a novel sequence verification task that aims to distinguish positive video pairs performing the same action sequence from negative ones with step-level transformations but still conducting the same task.
Graph Convolutional Module for Temporal Action Localization in Videos
To this end, we propose a general graph convolutional module (GCM) that can be easily plugged into existing action localization methods, including two-stage and one-stage paradigms.
Ranked #2 on
Temporal Action Localization
on THUMOS’14
(mAP IOU@0.1 metric)
$p$-Laplacian Based Graph Neural Networks
Graph neural networks (GNNs) have demonstrated superior performance for semi-supervised node classification on graphs, as a result of their ability to exploit node features and topological information simultaneously.
Meta-learning with an Adaptive Task Scheduler
In ATS, for the first time, we design a neural scheduler to decide which meta-training tasks to use next by predicting the probability being sampled for each candidate task, and train the scheduler to optimize the generalization capacity of the meta-model to unseen tasks.
Value Penalized Q-Learning for Recommender Systems
To alleviate the action distribution shift problem in extracting RL policy from static trajectories, we propose Value Penalized Q-learning (VPQ), an uncertainty-based offline RL algorithm.
Weakly Supervised Graph Clustering
Graph Clustering, which clusters the nodes of a graph given its collection of node features and edge connections in an unsupervised manner, has long been researched in graph learning and is essential in certain applications.
Local Augmentation for Graph Neural Networks
To address this, we propose a simple and efficient data augmentation strategy, local augmentation, to learn the distribution of the node features of the neighbors conditioned on the central node's feature and enhance GNN's expressive power with generated features.
AdaXpert: Adapting Neural Architecture for Growing Data
To address this, we present a neural architecture adaptation method, namely Adaptation eXpert (AdaXpert), to efficiently adjust previous architectures on the growing data.
Learning Graphon Autoencoders for Generative Graph Modeling
A linear graphon factorization model works as a decoder, leveraging the latent representations to reconstruct the induced graphons (and the corresponding observed graphs).
Exploring Robustness of Unsupervised Domain Adaptation in Semantic Segmentation
Recent studies imply that deep neural networks are vulnerable to adversarial examples -- inputs with a slight but intentional perturbation are incorrectly classified by the network.
Sparse online relative similarity learning
This is clearly inefficient for high dimensional tasks due to its high memory and computational complexity.
FedGraphNN: A Federated Learning System and Benchmark for Graph Neural Networks
FedGraphNN is built on a unified formulation of graph FL and contains a wide range of datasets from different domains, popular GNN models, and FL algorithms, with secure and efficient system support.
Pareto-Frontier-aware Neural Architecture Generation for Diverse Budgets
To this end, we propose a Pareto-Frontier-aware Neural Architecture Generator (NAG) which takes an arbitrary budget as input and produces the Pareto optimal architecture for the target budget.
Towards Accurate and Compact Architectures via Neural Architecture Transformer
To address this issue, we propose a Neural Architecture Transformer++ (NAT++) method which further enlarges the set of candidate transitions to improve the performance of architecture optimization.
Pareto-Frontier-aware Neural Architecture Search
To find promising architectures under different budgets, existing methods may have to perform an independent search for each budget, which is very inefficient and unnecessary.
Hierarchical Graph Capsule Network
Graph Neural Networks (GNNs) draw their strength from explicitly modeling the topological information of structured data.
Adversarial Sparse Transformer for Time Series Forecasting
Specifically, AST adopts a Sparse Transformer as the generator to learn a sparse attention map for time series forecasting, and uses a discriminator to improve the prediction performance from sequence level.
Multivariate Time Series Forecasting
Probabilistic Time Series Forecasting
+1
Supervised Learning Achieves Human-Level Performance in MOBA Games: A Case Study of Honor of Kings
Unlike prior attempts, we integrate the macro-strategy and the micromanagement of MOBA-game-playing into neural networks in a supervised and end-to-end manner.
RetroXpert: Decompose Retrosynthesis Prediction like a Chemist
Retrosynthesis is the process of recursively decomposing target molecules into available building blocks.
FedML: A Research Library and Benchmark for Federated Machine Learning
Federated learning (FL) is a rapidly growing research field in machine learning.
Inverse Graph Identification: Can We Identify Node Labels Given Graph Labels?
Upon a formal discussion of the variants of IGI, we choose a particular case study of node clustering by making use of the graph labels and node features, with an assistance of a hierarchical graph that further characterizes the connections between different graphs.
Breaking the Curse of Space Explosion: Towards Efficient NAS with Curriculum Search
With the proposed search strategy, our Curriculum Neural Architecture Search (CNAS) method significantly improves the search efficiency and finds better architectures than existing NAS methods.
Collaborative Unsupervised Domain Adaptation for Medical Image Diagnosis
Deep learning based medical image diagnosis has shown great potential in clinical medicine.
Relation-Aware Transformer for Portfolio Policy Learning
One of the key issues is how to represent the non-stationary price series of assets in a portfolio, which is important for portfolio decisions.
Towards Fast Adaptation of Neural Architectures with Meta Learning
Recently, Neural Architecture Search (NAS) has been successfully applied to multiple artificial intelligence areas and shows better performance compared with hand-designed networks.
COVID-DA: Deep Domain Adaptation from Typical Pneumonia to COVID-19
There are two main challenges: 1) the discrepancy of data distributions between domains; 2) the task difference between the diagnosis of typical pneumonia and COVID-19.
Disturbance-immune Weight Sharing for Neural Architecture Search
To alleviate the performance disturbance issue, we propose a new disturbance-immune update strategy for model updating.
Privacy Preserving Point-of-interest Recommendation Using Decentralized Matrix Factorization
However, existing MF approaches suffer from two major problems: (1) Expensive computations and storages due to the centralized model training mechanism: the centralized learners have to maintain the whole user-item rating matrix, and potentially huge low rank matrices.
Context-Aware Domain Adaptation in Semantic Segmentation
To achieve this goal, we design two cross-domain attention modules to adapt context dependencies from both spatial and channel views.
Ranked #29 on
Domain Adaptation
on SYNTHIA-to-Cityscapes
Cost-Sensitive Portfolio Selection via Deep Reinforcement Learning
This task, however, has two main difficulties: (i) the non-stationary price series and complex asset correlations make the learning of feature representation very hard; (ii) the practicality principle in financial markets requires controlling both transaction and risk costs.
Joint Wasserstein Distribution Matching
However, the resultant optimization problem is still intractable.
Rumor Detection on Social Media with Bi-Directional Graph Convolutional Networks
Meanwhile, detecting rumors from such massive information in social media is becoming an arduous challenge.
Mastering Complex Control in MOBA Games with Deep Reinforcement Learning
We study the reinforcement learning problem of complex action control in the Multi-player Online Battle Arena (MOBA) 1v1 games.
Online Adaptive Asymmetric Active Learning with Limited Budgets
In these problems, there are two key challenges: the query budget is often limited; the ratio between classes is highly imbalanced.
Collaborative Unsupervised Domain Adaptation for Medical Image Diagnosis
In this paper, we seek to exploit rich labeled data from relevant domains to help the learning in the target task with unsupervised domain adaptation (UDA).
NAT: Neural Architecture Transformer for Accurate and Compact Architectures
To verify the effectiveness of the proposed strategies, we apply NAT on both hand-crafted architectures and NAS based architectures.
Aggregated Gradient Langevin Dynamics
In this paper, we explore a general Aggregated Gradient Langevin Dynamics framework (AGLD) for the Markov Chain Monte Carlo (MCMC) sampling.
Molecular Graph Enhanced Transformer for Retrosynthesis Prediction
With massive possible synthetic routes in chemistry, retrosynthesis prediction is still a challenge for researchers.
Ranked #10 on
Single-step retrosynthesis
on USPTO-50k
Towards Interpreting Deep Neural Networks via Understanding Layer Behaviors
ii) the $W$-distance of a specific layer to the target distribution tends to decrease along training iterations.
Graph Convolutional Networks for Temporal Action Localization
Then we apply the GCNs over the graph to model the relations among different proposals and learn powerful representations for the action classification and localization.
Ranked #4 on
Temporal Action Localization
on THUMOS’14
(mAP IOU@0.1 metric)
Transferable Neural Processes for Hyperparameter Optimization
Automated machine learning aims to automate the whole process of machine learning, including model configuration.
Decentralized Online Learning: Take Benefits from Others' Data without Sharing Your Own to Track Global Trend
Decentralized Online Learning (online learning in decentralized networks) attracts more and more attention, since it is believed that Decentralized Online Learning can help the data providers cooperatively better solve their online problems without sharing their private data to a third party or other providers.
Hyperparameter Learning via Distributional Transfer
Bayesian optimisation is a popular technique for hyperparameter learning but typically requires initial exploration even in cases where similar prior tasks have been solved.
Learning Joint Wasserstein Auto-Encoders for Joint Distribution Matching
We study the joint distribution matching problem which aims at learning bidirectional mappings to match the joint distribution of two domains.
Open-Ended Question Answering
Unsupervised Image-To-Image Translation
+2
Dual Reconstruction Nets for Image Super-Resolution with Gradient Sensitive Loss
However, most deep learning methods employ feed-forward architectures, and thus the dependencies between LR and HR images are not fully exploited, leading to limited learning performance.
Towards More Efficient Stochastic Decentralized Learning: Faster Convergence and Sparse Communication
Recently, the decentralized optimization problem is attracting growing attention.
A Boosting Framework of Factorization Machine
However, to choose the rank properly, it usually needs to run the algorithm for many times using different ranks, which clearly is inefficient for some large-scale datasets.
Distributed Collaborative Hashing and Its Applications in Ant Financial
The experimental results demonstrate that, comparing with the classic and state-of-the-art (distributed) latent factor models, DCH has comparable performance in terms of recommendation accuracy but has both fast convergence speed in offline model training procedure and realtime efficiency in online recommendation procedure.
Adaptive Cost-sensitive Online Classification
Cost-Sensitive Online Classification has drawn extensive attention in recent years, where the main approach is to directly online optimize two well-known cost-sensitive metrics: (i) weighted sum of sensitivity and specificity; (ii) weighted misclassification cost.
Online Learning: A Comprehensive Survey
Online learning represents an important family of machine learning algorithms, in which a learner attempts to resolve an online prediction (or any type of decision-making) task by learning a model/hypothesis from a sequence of data instances one at a time.
Online Compact Convexified Factorization Machine
To address this subsequent challenge, we follow the general projection-free algorithmic framework of Online Conditional Gradient and propose an Online Compact Convex Factorization Machine (OCCFM) algorithm that eschews the projection operation with efficient linear optimization steps.
Projection-free Distributed Online Learning in Networks
The conditional gradient algorithm has regained a surge of research interest in recent years due to its high efficiency in handling large-scale machine learning problems.
Robust Cost-Sensitive Learning for Recommendation with Implicit Feedback
Morever, the proposed algorithm can be scaled up to large-sized datasets after a relaxation.
Robust Online Multi-Task Learning with Correlative and Personalized Structures
Multi-Task Learning (MTL) can enhance a classifier's generalization performance by learning multiple related tasks simultaneously.
Online Bayesian Collaborative Topic Regression
In this paper, we propose a novel scheme of Online Bayesian Collaborative Topic Regression (OBCTR) which is efficient and scalable for learning from data streams.
Adaptive Subgradient Methods for Online AUC Maximization
Despite their encouraging results reported, the existing online AUC maximization algorithms often adopt simple online gradient descent approaches that fail to exploit the geometrical knowledge of the data observed during the online learning process, and thus could suffer from relatively larger regret.
Budget Online Multiple Kernel Learning
To overcome this drawback, we present a novel framework of Budget Online Multiple Kernel Learning (BOMKL) and propose a new Sparse Passive Aggressive learning to perform effective budget online learning.
A Framework of Sparse Online Learning and Its Applications
Unlike some existing online data stream classification techniques that are often based on first-order online learning, we propose a framework of Sparse Online Classification (SOC) for data stream classification, which includes some state-of-the-art first-order sparse online learning algorithms as special cases and allows us to derive a new effective second-order online learning algorithm for data stream classification.
Accelerating Minibatch Stochastic Gradient Descent using Stratified Sampling
Stochastic Gradient Descent (SGD) is a popular optimization method which has been applied to many important machine learning tasks such as Support Vector Machines and Deep Neural Networks.
Stochastic Optimization with Importance Sampling
Uniform sampling of training data has been commonly used in traditional stochastic optimization algorithms such as Proximal Stochastic Gradient Descent (prox-SGD) and Proximal Stochastic Dual Coordinate Ascent (prox-SDCA).
Adaptive Stochastic Alternating Direction Method of Multipliers
The Alternating Direction Method of Multipliers (ADMM) has been studied for years.
Active Learning with Expert Advice
In this paper, we address a new problem of active learning with expert advice, where the outcome of an instance is disclosed only when it is requested by the online learner.
PAMR: Passive aggressive mean reversion strategy for portfolio selection
This article proposes a novel online portfolio selection strategy named “Passive Aggressive Mean Reversion” (PAMR).
DUOL: A Double Updating Approach for Online Learning
This is clearly insufficient since when a new misclassified example is added to the pool of support vectors, we generally expect it to affect the weights for the existing support vectors.
