Search Results for author:
Found 39 papers, 11 papers with code
FinTSBridge: A New Evaluation Suite for Real-world Financial Prediction with Advanced Time Series Models
Despite the growing attention to time series forecasting in recent years, many studies have proposed various solutions to address the challenges encountered in time series prediction, aiming to improve forecasting performance.
Assessing Uncertainty in Stock Returns: A Gaussian Mixture Distribution-Based Method
We introduce a novel deep learning model that utilizes a Gaussian mixture distribution to capture the complex, time-varying nature of asset return distributions in the Chinese stock market.
A Theoretical Framework for Data Efficient Multi-Source Transfer Learning Based on Cramér-Rao Bound
Additionally, we develop an architecture-agnostic and data-efficient algorithm OTQMS to implement our theoretical results for training deep multi-source transfer learning models.
PSformer: Parameter-efficient Transformer with Segment Attention for Time Series Forecasting
Time series forecasting remains a critical challenge across various domains, often complicated by high-dimensional data and long-term dependencies.
Task Oriented In-Domain Data Augmentation
On average, TRAIT improves LLM performance by 8% in the advertisement domain and 7. 5% in the math domain.
NAC: Mitigating Noisy Correspondence in Cross-Modal Matching Via Neighbor Auxiliary Corrector
The presence of noisy correspondence within cross-modal matching has significantly undermined the performance of existing matching methods.
Exploring Iterative Refinement with Diffusion Models for Video Grounding
In this paper, we propose DiffusionVG, a novel framework with diffusion models that formulates video grounding as a conditional generation task, where the target span is generated from Gaussian noise inputs and interatively refined in the reverse diffusion process.
SSLCL: An Efficient Model-Agnostic Supervised Contrastive Learning Framework for Emotion Recognition in Conversations
To address these challenges, we propose an efficient and model-agnostic SCL framework named Supervised Sample-Label Contrastive Learning with Soft-HGR Maximal Correlation (SSLCL), which eliminates the need for a large batch size and can be seamlessly integrated with existing ERC models without introducing any model-specific assumptions.
Personalized Federated Learning with Feature Alignment and Classifier Collaboration
Data heterogeneity is one of the most challenging issues in federated learning, which motivates a variety of approaches to learn personalized models for participating clients.
Stabilizing and Improving Federated Learning with Non-IID Data and Client Dropout
The label distribution skew induced data heterogeniety has been shown to be a significant obstacle that limits the model performance in federated learning, which is particularly developed for collaborative model training over decentralized data sources while preserving user privacy.
An Information-Theoretic Approach to Transferability in Task Transfer Learning
Task transfer learning is a popular technique in image processing applications that uses pre-trained models to reduce the supervision cost of related tasks.
Revisiting Sparse Convolutional Model for Visual Recognition
We show that such models have equally strong empirical performance on CIFAR-10, CIFAR-100, and ImageNet datasets when compared to conventional neural networks.
Transferability-Guided Cross-Domain Cross-Task Transfer Learning
We propose two novel transferability metrics F-OTCE (Fast Optimal Transport based Conditional Entropy) and JC-OTCE (Joint Correspondence OTCE) to evaluate how much the source model (task) can benefit the learning of the target task and to learn more transferable representations for cross-domain cross-task transfer learning.
Generalizing to Unseen Domains with Wasserstein Distributional Robustness under Limited Source Knowledge
Domain generalization aims at learning a universal model that performs well on unseen target domains, incorporating knowledge from multiple source domains.
Regularization Penalty Optimization for Addressing Data Quality Variance in OoD Algorithms
Due to the poor generalization performance of traditional empirical risk minimization (ERM) in the case of distributional shift, Out-of-Distribution (OoD) generalization algorithms receive increasing attention.
A Mathematical Framework for Quantifying Transferability in Multi-source Transfer Learning
Current transfer learning algorithm designs mainly focus on the similarities between source and target tasks, while the impacts of the sample sizes of these tasks are often not sufficiently addressed.
Transferability Estimation for Semantic Segmentation Task
Recent analytical transferability metrics are mainly designed for image classification problem, and currently there is no specific investigation for the transferability estimation of semantic segmentation task, which is an essential problem in autonomous driving, medical image analysis, etc.
PAC-Bayes Information Bottleneck
Then, we build an IIW-based information bottleneck on the trade-off between accuracy and information complexity of NNs, namely PIB.
Performance-Guaranteed ODE Solvers with Complexity-Informed Neural Networks
Traditionally, we provide technical parameters for ODE solvers, such as the order, the stepsize and the local error threshold.
On Distributed Learning with Constant Communication Bits
Specifically, we consider the distributed hypothesis testing (DHT) problem where two distributed nodes are constrained to transmit a constant number of bits to a central decoder.
Byzantine-robust Federated Learning through Collaborative Malicious Gradient Filtering
To this end, previous work either makes use of auxiliary data at parameter server to verify the received gradients (e. g., by computing validation error rate) or leverages statistic-based methods (e. g. median and Krum) to identify and remove malicious gradients from Byzantine clients.
Maximum Likelihood Estimation for Multimodal Learning with Missing Modality
Moreover, we develop a generalized form of the softmax function to effectively implement maximum likelihood estimation in an end-to-end manner.
DQ-SGD: Dynamic Quantization in SGD for Communication-Efficient Distributed Learning
Gradient quantization is an emerging technique in reducing communication costs in distributed learning.
Practical Transferability Estimation for Image Classification Tasks
Transferability estimation is an essential problem in transfer learning to predict how good the performance is when transferring a source model (or source task) to a target task.
OTCE: A Transferability Metric for Cross-Domain Cross-Task Representations
Specifically, we use optimal transport to estimate domain difference and the optimal coupling between source and target distributions, which is then used to derive the conditional entropy of the target task (task difference).
Lifelong Learning based Disease Diagnosis on Clinical Notes
Current deep learning based disease diagnosis systems usually fall short in catastrophic forgetting, i. e., directly fine-tuning the disease diagnosis model on new tasks usually leads to abrupt decay of performance on previous tasks.
DQSGD: DYNAMIC QUANTIZED STOCHASTIC GRADIENT DESCENT FOR COMMUNICATION-EFFICIENT DISTRIBUTED LEARNING
This paper addresses this issue by proposing a novel dynamic quantized SGD (DQSGD) framework, which enables us to optimize the quantization strategy for each gradient descent step by exploring the trade-off between communication cost and modeling error.
Predicting Events in MOBA Games: Prediction, Attribution, and Evaluation
The multiplayer online battle arena (MOBA) games have become increasingly popular in recent years.
Finding Influential Instances for Distantly Supervised Relation Extraction
Distant supervision (DS) is a strong way to expand the datasets for enhancing relation extraction (RE) models but often suffers from high label noise.
Information Theoretic Counterfactual Learning from Missing-Not-At-Random Feedback
Counterfactual learning for dealing with missing-not-at-random data (MNAR) is an intriguing topic in the recommendation literature since MNAR data are ubiquitous in modern recommender systems.
Online Disease Self-diagnosis with Inductive Heterogeneous Graph Convolutional Networks
We propose a Healthcare Graph Convolutional Network (HealGCN) to offer disease self-diagnosis service for online users based on Electronic Healthcare Records (EHRs).
Interpretable Real-Time Win Prediction for Honor of Kings, a Popular Mobile MOBA Esport
With the rapid prevalence and explosive development of MOBA esports (Multiplayer Online Battle Arena electronic sports), much research effort has been devoted to automatically predicting game results (win predictions).
On the Fairness of Randomized Trials for Recommendation with Heterogeneous Demographics and Beyond
Observed events in recommendation are consequence of the decisions made by a policy, thus they are usually selectively labeled, namely the data are Missing Not At Random (MNAR), which often causes large bias to the estimate of true outcomes risk.
Less Is Better: Unweighted Data Subsampling via Influence Function
In the time of Big Data, training complex models on large-scale data sets is challenging, making it appealing to reduce data volume for saving computation resources by subsampling.
On Universal Features for High-Dimensional Learning and Inference
We consider the problem of identifying universal low-dimensional features from high-dimensional data for inference tasks in settings involving learning.
An Information-theoretic Approach to Unsupervised Feature Selection for High-Dimensional Data
In this paper, we propose an information-theoretic approach to design the functional representations to extract the hidden common structure shared by a set of random variables.
An Information Theoretic Interpretation to Deep Neural Networks
It is commonly believed that the hidden layers of deep neural networks (DNNs) attempt to extract informative features for learning tasks.
An Information-Theoretic Metric of Transferability for Task Transfer Learning
An important question in task transfer learning is to determine task transferability, i. e. given a common input domain, estimating to what extent representations learned from a source task can help in learning a target task.
An Efficient Approach to Informative Feature Extraction from Multimodal Data
We further generalize the framework to handle more than two modalities and missing modalities.
