128 citations · 718 across the 52 of their papers we have counts for
53 papers
Mitigating Shortcuts in Language Models with Soft Label Encoding
Zirui He, Huiqi Deng, Haiyan Zhao +2
Recent research has shown that large language models rely on spurious correlations in the data for natural language understanding (NLU) tasks. In this work, we aim to answer the fo…
Explainability for Large Language Models: A Survey
Haiyan Zhao, Hanjie Chen, Fan Yang +6
Large language models (LLMs) have demonstrated impressive capabilities in natural language processing. However, their internal mechanisms are still unclear and this lack of transpa…
GiGaMAE: Generalizable Graph Masked Autoencoder via Collaborative Latent Space Reconstruction
Yucheng Shi, Yushun Dong, Qiaoyu Tan +2
Self-supervised learning with masked autoencoders has recently gained popularity for its ability to produce effective image or textual representations, which can be applied to vari…
XGBD: Explanation-Guided Graph Backdoor Detection
Zihan Guan, Mengnan Du, Ninghao Liu
Backdoor attacks pose a significant security risk to graph learning models. Backdoors can be embedded into the target model by inserting backdoor triggers into the training dataset…
CohortGPT: An Enhanced GPT for Participant Recruitment in Clinical Study
Zihan Guan, Zihao Wu, Zhengliang Liu +5
Participant recruitment based on unstructured medical texts such as clinical notes and radiology reports has been a challenging yet important task for the cohort establishment in c…
Hierarchical Semantic Tree Concept Whitening for Interpretable Image Classification
Haixing Dai, Lu Zhang, Lin Zhao +9
With the popularity of deep neural networks (DNNs), model interpretability is becoming a critical concern. Many approaches have been developed to tackle the problem through post-ho…
ENGAGE: Explanation Guided Data Augmentation for Graph Representation Learning
Yucheng Shi, Kaixiong Zhou, Ninghao Liu
The recent contrastive learning methods, due to their effectiveness in representation learning, have been widely applied to modeling graph data. Random perturbation is widely used…
Exploring New Frontiers in Agricultural NLP: Investigating the Potential of Large Language Models for Food Applications
Saed Rezayi, Zhengliang Liu, Zihao Wu +8
This paper explores new frontiers in agricultural natural language processing by investigating the effectiveness of using food-related text corpora for pretraining transformer-base…
Improving Generalizability of Graph Anomaly Detection Models via Data Augmentation
Shuang Zhou, Xiao Huang, Ninghao Liu +3
Graph anomaly detection (GAD) is a vital task since even a few anomalies can pose huge threats to benign users. Recent semi-supervised GAD methods, which can effectively leverage t…
Efficient GNN Explanation via Learning Removal-based Attribution
Yao Rong, Guanchu Wang, Qizhang Feng +4
As Graph Neural Networks (GNNs) have been widely used in real-world applications, model explanations are required not only by users but also by legal regulations. However, simultan…
Could Small Language Models Serve as Recommenders? Towards Data-centric Cold-start Recommendations
Xuansheng Wu, Huachi Zhou, Yucheng Shi +3
Recommendation systems help users find matched items based on their previous behaviors. Personalized recommendation becomes challenging in the absence of historical user-item inter…
Interpretation of Time-Series Deep Models: A Survey
Ziqi Zhao, Yucheng Shi, Shushan Wu +3
Deep learning models developed for time-series associated tasks have become more widely researched nowadays. However, due to the unintuitive nature of time-series data, the interpr…
DEGREE: Decomposition Based Explanation For Graph Neural Networks
Qizhang Feng, Ninghao Liu, Fan Yang +3
Graph Neural Networks (GNNs) are gaining extensive attention for their application in graph data. However, the black-box nature of GNNs prevents users from understanding and trusti…
BadSAM: Exploring Security Vulnerabilities of SAM via Backdoor Attacks
Zihan Guan, Mengxuan Hu, Zhongliang Zhou +3
Recently, the Segment Anything Model (SAM) has gained significant attention as an image segmentation foundation model due to its strong performance on various downstream tasks. How…
Interactive System-wise Anomaly Detection
Guanchu Wang, Ninghao Liu, Daochen Zha +1
Anomaly detection, where data instances are discovered containing feature patterns different from the majority, plays a fundamental role in various applications. However, it is cha…
On the Opportunities and Challenges of Foundation Models for Geospatial Artificial Intelligence
Gengchen Mai, Weiming Huang, Jin Sun +11
Large pre-trained models, also known as foundation models (FMs), are trained in a task-agnostic manner on large-scale data and can be adapted to a wide range of downstream tasks by…
Did You Train on My Dataset? Towards Public Dataset Protection with Clean-Label Backdoor Watermarking
Ruixiang Tang, Qizhang Feng, Ninghao Liu +2
The huge supporting training data on the Internet has been a key factor in the success of deep learning models. However, this abundance of public-available data also raises concern…
AGI: Artificial General Intelligence for Education
Ehsan Latif, Gengchen Mai, Matthew Nyaaba +6
Artificial general intelligence (AGI) has gained global recognition as a future technology due to the emergence of breakthrough large language models and chatbots such as GPT-4 and…
AugGPT: Leveraging ChatGPT for Text Data Augmentation
Haixing Dai, Zhengliang Liu, Wenxiong Liao +15
Text data augmentation is an effective strategy for overcoming the challenge of limited sample sizes in many natural language processing (NLP) tasks. This challenge is especially p…
Black-box Backdoor Defense via Zero-shot Image Purification
Yucheng Shi, Mengnan Du, Xuansheng Wu +3
Backdoor attacks inject poisoned samples into the training data, resulting in the misclassification of the poisoned input during a model's deployment. Defending against such attack…
A Survey of Graph Prompting Methods: Techniques, Applications, and Challenges
Xuansheng Wu, Kaixiong Zhou, Mingchen Sun +2
The recent "pre-train, prompt, predict training" paradigm has gained popularity as a way to learn generalizable models with limited labeled data. The approach involves using a pre-…
NoPPA: Non-Parametric Pairwise Attention Random Walk Model for Sentence Representation
Xuansheng Wu, Zhiyi Zhao, Ninghao Liu
We propose a novel non-parametric/un-trainable language model, named Non-Parametric Pairwise Attention Random Walk Model (NoPPA), to generate sentence embedding only with pre-train…
Matching Exemplar as Next Sentence Prediction (MeNSP): Zero-shot Prompt Learning for Automatic Scoring in Science Education
Xuansheng Wu, Xinyu He, Tianming Liu +2
Developing models to automatically score students' written responses to science problems is critical for science education. However, collecting and labeling sufficient student resp…
Bring Your Own View: Graph Neural Networks for Link Prediction with Personalized Subgraph Selection
Qiaoyu Tan, Xin Zhang, Ninghao Liu +5
Graph neural networks (GNNs) have received remarkable success in link prediction (GNNLP) tasks. Existing efforts first predefine the subgraph for the whole dataset and then apply G…