Shuang Li

Joint Adversarial Domain Adaptation

2019

Domain adaptation aims to transfer the enriched label knowledge from large amounts of source data to unlabeled target data. It has raised significant interest in multimedia analysis. Existing researches mainly focus on learning domain-wise transferable …

Energy-Based Models for Continual Learning

2020 · arXiv (Cornell University)

We motivate Energy-Based Models (EBMs) as a promising model class for continual learning problems. Instead of tackling continual learning via the use of external memory, growing models, or regularization, EBMs change the underlying training objective …

Generalized Robust Test-Time Adaptation in Continuous Dynamic Scenarios

2023 · arXiv (Cornell University)

Test-time adaptation (TTA) adapts the pre-trained models to test distributions during the inference phase exclusively employing unlabeled test data streams, which holds great value for the deployment of models in real-world applications. Numerous studies have …

RAPL: A Relation-Aware Prototype Learning Approach for Few-Shot Document-Level Relation Extraction

2023 · arXiv (Cornell University)

How to identify semantic relations among entities in a document when only a few labeled documents are available? Few-shot document-level relation extraction (FSDLRE) is crucial for addressing the pervasive data scarcity problem in real-world scenarios. …

Source-Free Active Domain Adaptation via Augmentation-Based Sample Query and Progressive Model Adaptation

2023 · IEEE Transactions on Neural Networks and Learning Systems

Active domain adaptation (ADA), which enormously improves the performance of unsupervised domain adaptation (UDA) at the expense of annotating limited target data, has attracted a surge of interest. However, in real-world applications, the source data …

High-level preferences as positive examples in contrastive learning for multi-interest sequential recommendation

2024 · Research Square

Abstract The sequential recommendation task based on the multi-interest framework aims to model multiple interests of users from different aspects to predict their future interactions. However, researchers rarely consider the differences in features between the …

FSMR: A Feature Swapping Multi-modal Reasoning Approach with Joint Textual and Visual Clues

2024 · arXiv (Cornell University)

Multi-modal reasoning plays a vital role in bridging the gap between textual and visual information, enabling a deeper understanding of the context. This paper presents the Feature Swapping Multi-modal Reasoning (FSMR) model, designed to enhance …

SEGMENT+: Long Text Processing with Short-Context Language Models

2024 · arXiv (Cornell University)

There is a growing interest in expanding the input capacity of language models (LMs) across various domains. However, simply increasing the context window does not guarantee robust performance across diverse long-input processing tasks, such as …

Research on the key driver analysis technology of the cost deviation of the distribution network project based on the big data statistical analysis

2025

The distribution network project has the characteristics of many voltage levels, complex network structure, diverse equipment types, wide operation points, relatively poor environmental safety and low investment density. Therefore, it is of great significance to …