Bo Du

Multi-class active learning: A hybrid informative and representative criterion inspired approach

2017

Labeling each instance in a large-scale data set is extremely labor- and time-consuming. One way to alleviate this problem is active learning, which aims to discover the most valuable instances for labeling to construct a …

Long-short Distance Aggregation Networks for Positive Unlabeled Graph Learning

2019

Graph neural nets are emerging tools to represent network nodes for classification. However, existing approaches typically suffer from two limitations: (1) they only aggregate information from short distance (e.g., 1-hop neighbors) each round and fail …

Knowledge Graph Augmented Network Towards Multiview Representation Learning for Aspect-based Sentiment Analysis

2022 · arXiv (Cornell University)

Aspect-based sentiment analysis (ABSA) is a fine-grained task of sentiment analysis. To better comprehend long complicated sentences and obtain accurate aspect-specific information, linguistic and commonsense knowledge are generally required in this task. However, most current …

Dual-branch Density Ratio Estimation for Signed Network Embedding

2022 · Proceedings of the ACM Web Conference 2022

Signed network embedding (SNE) has received considerable attention in recent years. A mainstream idea of SNE is to learn node representations by estimating the ratio of sampling densities. Though achieving promising performance, these methods based …

Not All Instances Contribute Equally: Instance-adaptive Class Representation Learning for Few-Shot Visual Recognition

2022 · arXiv (Cornell University)

Few-shot visual recognition refers to recognize novel visual concepts from a few labeled instances. Many few-shot visual recognition methods adopt the metric-based meta-learning paradigm by comparing the query representation with class representations to predict the …

Exploring Sparsity in Graph Transformers

2023 · arXiv (Cornell University)

Graph Transformers (GTs) have achieved impressive results on various graph-related tasks. However, the huge computational cost of GTs hinders their deployment and application, especially in resource-constrained environments. Therefore, in this paper, we explore the feasibility …

Segment First or Comprehend First? Explore the Limit of Unsupervised Word Segmentation with Large Language Models

2025 · arXiv (Cornell University)

Word segmentation stands as a cornerstone of Natural Language Processing (NLP). Based on the concept of "comprehend first, segment later", we propose a new framework to explore the limit of unsupervised word segmentation with Large …

Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Merging

2025 · IEEE Transactions on Pattern Analysis and Machine Intelligence

Multi-task learning (MTL) leverages a shared model to accomplish multiple tasks and facilitate knowledge transfer. Recent research on task arithmetic-based MTL demonstrates that merging the parameters of independently fine-tuned models can effectively achieve MTL. However, …

DAML: Dual Attention Mutual Learning between Ratings and Reviews for Item Recommendation

2019

Despite the great success of many matrix factorization based collaborative filtering approaches, there is still much space for improvement in recommender system field. One main obstacle is the cold-start and data sparseness problem, requiring better …

Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERT

2023 · arXiv (Cornell University)

Recently, ChatGPT has attracted great attention, as it can generate fluent and high-quality responses to human inquiries. Several prior studies have shown that ChatGPT attains remarkable generation ability compared with existing models. However, the quantitative …