Search Results for author:
Found 76 papers, 27 papers with code
Efficient Sharpness-aware Minimization for Molecular Graph Transformer Models
Sharpness-aware minimization (SAM) has received increasing attention in computer vision since it can effectively eliminate the sharp local minima from the training trajectory and mitigate generalization degradation.
Quantifying Multilingual Performance of Large Language Models Across Languages
However, currently there is no work to quantitatively measure the performance of LLMs in low-resource languages.
Retrieval-Enhanced Knowledge Editing for Multi-Hop Question Answering in Language Models
Large Language Models (LLMs) have shown proficiency in question-answering tasks but often struggle to integrate real-time knowledge updates, leading to potentially outdated or inaccurate responses.
Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era
Therefore, in this paper, we introduce Usable XAI in the context of LLMs by analyzing (1) how XAI can benefit LLMs and AI systems, and (2) how LLMs can contribute to the advancement of XAI.
A Survey of Deep Learning and Foundation Models for Time Series Forecasting
Furthermore, there is a vast amount of knowledge available that deep learning models can tap into, including Knowledge Graphs and Large Language Models fine-tuned with scientific domain knowledge.
Revolutionizing Finance with LLMs: An Overview of Applications and Insights
Additionally, we conducted holistic tests on multiple financial tasks through the combination of natural language instructions.
On the Promises and Challenges of Multimodal Foundation Models for Geographical, Environmental, Agricultural, and Urban Planning Applications
The advent of large language models (LLMs) has heightened interest in their potential for multimodal applications that integrate language and vision.
PokeMQA: Programmable knowledge editing for Multi-hop Question Answering
Multi-hop question answering (MQA) is one of the challenging tasks to evaluate machine's comprehension and reasoning abilities, where large language models (LLMs) have widely achieved the human-comparable performance.
Applying Large Language Models and Chain-of-Thought for Automatic Scoring
We found a more balanced accuracy across different proficiency categories when CoT was used with a scoring rubric, highlighting the importance of domain-specific reasoning in enhancing the effectiveness of LLMs in scoring tasks.
Improving Faithfulness for Vision Transformers
However, ViTs suffer from issues with explanation faithfulness, as their focal points are fragile to adversarial attacks and can be easily changed with even slight perturbations on the input image.
Transformation vs Tradition: Artificial General Intelligence (AGI) for Arts and Humanities
Recent advances in artificial general intelligence (AGI), particularly large language models and creative image generation systems have demonstrated impressive capabilities on diverse tasks spanning the arts and humanities.
A Theoretical Approach to Characterize the Accuracy-Fairness Trade-off Pareto Frontier
While the accuracy-fairness trade-off has been frequently observed in the literature of fair machine learning, rigorous theoretical analyses have been scarce.
Automated Natural Language Explanation of Deep Visual Neurons with Large Models
Deep neural networks have exhibited remarkable performance across a wide range of real-world tasks.
From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning
In this work, we investigate how the instruction tuning adjusts pre-trained models with a focus on intrinsic changes.
MedEdit: Model Editing for Medical Question Answering with External Knowledge Bases
Focusing on medical QA using the MedQA-SMILE dataset, we evaluate the impact of different retrieval models and the number of facts provided to the LLM.
RadOnc-GPT: A Large Language Model for Radiation Oncology
This paper presents RadOnc-GPT, a large language model specialized for radiation oncology through advanced tuning methods.
Mitigating Shortcuts in Language Models with Soft Label Encoding
Recent research has shown that large language models rely on spurious correlations in the data for natural language understanding (NLU) tasks.
Natural Language Understanding
Out-of-Distribution Generalization
Towards Artificial General Intelligence (AGI) in the Internet of Things (IoT): Opportunities and Challenges
Artificial General Intelligence (AGI), possessing the capacity to comprehend, learn, and execute tasks with human cognitive abilities, engenders significant anticipation and intrigue across scientific, commercial, and societal arenas.
Explainability for Large Language Models: A Survey
For each paradigm, we summarize the goals and dominant approaches for generating local explanations of individual predictions and global explanations of overall model knowledge.
GiGaMAE: Generalizable Graph Masked Autoencoder via Collaborative Latent Space Reconstruction
By considering embeddings encompassing graph topology and attribute information as reconstruction targets, our model could capture more generalized and comprehensive knowledge.
XGBD: Explanation-Guided Graph Backdoor Detection
An emerging detection strategy in the vision and NLP domains is based on an intriguing phenomenon: when training models on a mixture of backdoor and clean samples, the loss on backdoor samples drops significantly faster than on clean samples, allowing backdoor samples to be easily detected by selecting samples with the lowest loss values.
CohortGPT: An Enhanced GPT for Participant Recruitment in Clinical Study
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 clinical research.
Hierarchical Semantic Tree Concept Whitening for Interpretable Image Classification
With the popularity of deep neural networks (DNNs), model interpretability is becoming a critical concern.
ENGAGE: Explanation Guided Data Augmentation for Graph Representation Learning
Then, we design two data augmentation schemes on graphs for perturbing structural and feature information, respectively.
Could Small Language Models Serve as Recommenders? Towards Data-centric Cold-start Recommendations
To evaluate our approach, we introduce a cold-start recommendation benchmark, and the results demonstrate that the enhanced small language models can achieve comparable cold-start recommendation performance to that of large models with only $17\%$ of the inference time.
Exploring New Frontiers in Agricultural NLP: Investigating the Potential of Large Language Models for Food Applications
ChatGPT has shown to be a strong baseline in many NLP tasks, and we believe it has the potential to improve our model in the task of semantic matching and enhance our model's understanding of food-related concepts and relationships.
Improving Generalizability of Graph Anomaly Detection Models via Data Augmentation
In this paper, we base on the phenomenon and propose a general and novel research problem of generalized graph anomaly detection that aims to effectively identify anomalies on both the training-domain graph and unseen testing graph to eliminate potential dangers.
Efficient GNN Explanation via Learning Removal-based Attribution
A strategy of subgraph sampling is designed in LARA to improve the scalability of the training process.
Interpretation of Time-Series Deep Models: A Survey
Deep learning models developed for time-series associated tasks have become more widely researched nowadays.
DEGREE: Decomposition Based Explanation For Graph Neural Networks
Graph Neural Networks (GNNs) are gaining extensive attention for their application in graph data.
BadSAM: Exploring Security Vulnerabilities of SAM via Backdoor Attacks
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.
AGI: Artificial General Intelligence for Education
AGI, driven by the recent large pre-trained models, represents a significant leap in the capability of machines to perform tasks that require human-level intelligence, such as reasoning, problem-solving, decision-making, and even understanding human emotions and social interactions.
Interactive System-wise Anomaly Detection
Anomaly detection, where data instances are discovered containing feature patterns different from the majority, plays a fundamental role in various applications.
On the Opportunities and Challenges of Foundation Models for Geospatial Artificial Intelligence
In this work, we explore the promises and challenges of developing multimodal foundation models for GeoAI.
AGI for Agriculture
Artificial General Intelligence (AGI) is poised to revolutionize a variety of sectors, including healthcare, finance, transportation, and education.
Did You Train on My Dataset? Towards Public Dataset Protection with Clean-Label Backdoor Watermarking
To overcome this challenge, we introduce a clean-label backdoor watermarking framework that uses imperceptible perturbations to replace mislabeled samples.
A Survey of Graph Prompting Methods: Techniques, Applications, and Challenges
In particular, we introduce the basic concepts of graph prompt learning, organize the existing work of designing graph prompting functions, and describe their applications and future challenges.
AugGPT: Leveraging ChatGPT for Text Data Augmentation
Text data augmentation is an effective strategy for overcoming the challenge of limited sample sizes in many natural language processing (NLP) tasks.
NoPPA: Non-Parametric Pairwise Attention Random Walk Model for Sentence Representation
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-trained word embedding and pre-counted word frequency.
Matching Exemplar as Next Sentence Prediction (MeNSP): Zero-shot Prompt Learning for Automatic Scoring in Science Education
Developing models to automatically score students' written responses to science problems is critical for science education.
Bring Your Own View: Graph Neural Networks for Link Prediction with Personalized Subgraph Selection
To bridge the gap, we introduce a Personalized Subgraph Selector (PS2) as a plug-and-play framework to automatically, personally, and inductively identify optimal subgraphs for different edges when performing GNNLP.
Interpreting Unfairness in Graph Neural Networks via Training Node Attribution
In this paper, we study a novel problem of interpreting GNN unfairness through attributing it to the influence of training nodes.
SEAT: Stable and Explainable Attention
Results show that SEAT is more stable against different perturbations and randomness while also keeps the explainability of attention, which indicates it is a more faithful explanation.
Coarse-to-fine Knowledge Graph Domain Adaptation based on Distantly-supervised Iterative Training
In this framework, we apply distant-supervision on cross-domain knowledge graph adaptation.
AdaGCL: Adaptive Subgraph Contrastive Learning to Generalize Large-scale Graph Training
To bridge the gap between large-scale graph training and contrastive learning, we propose adaptive subgraph contrastive learning (AdaGCL).
Improving Generalizability of Graph Anomaly Detection Models via Data Augmentation
In this paper, we base on the phenomenon and propose a general and novel research problem of generalized graph anomaly detection that aims to effectively identify anomalies on both the training-domain graph and unseen testing graph to eliminate potential dangers.
DIVISION: Memory Efficient Training via Dual Activation Precision
Activation compressed training provides a solution towards reducing the memory cost of training deep neural networks~(DNNs).
Mitigating Algorithmic Bias with Limited Annotations
Existing work on fairness modeling commonly assumes that sensitive attributes for all instances are fully available, which may not be true in many real-world applications due to the high cost of acquiring sensitive information.
Unseen Anomaly Detection on Networks via Multi-Hypersphere Learning
Network anomaly detection is a crucial task since a few anomalies can cause huge losses.
G-Mixup: Graph Data Augmentation for Graph Classification
To this end, we propose $\mathcal{G}$-Mixup to augment graphs for graph classification by interpolating the generator (i. e., graphon) of different classes of graphs.
Geometric Graph Representation Learning via Maximizing Rate Reduction
Learning discriminative node representations benefits various downstream tasks in graph analysis such as community detection and node classification.
MGAE: Masked Autoencoders for Self-Supervised Learning on Graphs
We introduce a novel masked graph autoencoder (MGAE) framework to perform effective learning on graph structure data.
Defense Against Explanation Manipulation
Explainable machine learning attracts increasing attention as it improves transparency of models, which is helpful for machine learning to be trusted in real applications.
Modeling Techniques for Machine Learning Fairness: A Survey
Machine learning models are becoming pervasive in high-stakes applications.
G-Mixup: Graph Augmentation for Graph Classification
To this end, we propose $\mathcal{G}$-Mixup to augment graphs for graph classification by interpolating the generator (i. e., graphon) of different classes of graphs.
Adaptive Label Smoothing To Regularize Large-Scale Graph Training
Graph neural networks (GNNs), which learn the node representations by recursively aggregating information from its neighbors, have become a predominant computational tool in many domains.
EDITS: Modeling and Mitigating Data Bias for Graph Neural Networks
We then develop a framework EDITS to mitigate the bias in attributed networks while maintaining the performance of GNNs in downstream tasks.
ExAD: An Ensemble Approach for Explanation-based Adversarial Detection
Several defense methods have been proposed against adversarial attacks to detect adversarial examples at test time or to make machine learning models more robust.
Sparse-Interest Network for Sequential Recommendation
Our sparse-interest module can adaptively infer a sparse set of concepts for each user from the large concept pool and output multiple embeddings accordingly.
Dynamic Memory based Attention Network for Sequential Recommendation
It segments the overall long behavior sequence into a series of sub-sequences, then trains the model and maintains a set of memory blocks to preserve long-term interests of users.
Generative Counterfactuals for Neural Networks via Attribute-Informed Perturbation
With the wide use of deep neural networks (DNN), model interpretability has become a critical concern, since explainable decisions are preferred in high-stake scenarios.
Learning sparse codes from compressed representations with biologically plausible local wiring constraints
Unfortunately, current proposals for sparse coding in the compressed space require a centralized compression process (i. e., dense random matrix) that is biologically unrealistic due to local wiring constraints observed in neural circuits.
Are Interpretations Fairly Evaluated? A Definition Driven Pipeline for Post-Hoc Interpretability
Recent years have witnessed an increasing number of interpretation methods being developed for improving transparency of NLP models.
Explainable Recommender Systems via Resolving Learning Representations
Different from previous work, in our model, factor discovery and representation learning are simultaneously conducted, and we are able to handle extra attribute information and knowledge.
An Embarrassingly Simple Approach for Trojan Attack in Deep Neural Networks
In this paper, we investigate a specific security problem called trojan attack, which aims to attack deployed DNN systems relying on the hidden trigger patterns inserted by malicious hackers.
Adversarial Attacks and Defenses: An Interpretation Perspective
In this paper, we review recent work on adversarial attacks and defenses, particularly from the perspective of machine learning interpretation.
Learning to Hash with Graph Neural Networks for Recommender Systems
In this work, we investigate the problem of hashing with graph neural networks (GNNs) for high quality retrieval, and propose a simple yet effective discrete representation learning framework to jointly learn continuous and discrete codes.
Distribution-Guided Local Explanation for Black-Box Classifiers
Existing local explanation methods provide an explanation for each decision of black-box classifiers, in the form of relevance scores of features according to their contributions.
Learning Credible Deep Neural Networks with Rationale Regularization
Recent explainability related studies have shown that state-of-the-art DNNs do not always adopt correct evidences to make decisions.
Deep Structured Cross-Modal Anomaly Detection
To this end, we propose a novel deep structured anomaly detection framework to identify the cross-modal anomalies embedded in the data.
Is a Single Vector Enough? Exploring Node Polysemy for Network Embedding
Network embedding models are powerful tools in mapping nodes in a network into continuous vector-space representations in order to facilitate subsequent tasks such as classification and link prediction.
Deep Representation Learning for Social Network Analysis
First, we introduce the basic models for learning node representations in homogeneous networks.
On Attribution of Recurrent Neural Network Predictions via Additive Decomposition
REAT decomposes the final prediction of a RNN into additive contribution of each word in the input text.
Techniques for Interpretable Machine Learning
Interpretable machine learning tackles the important problem that humans cannot understand the behaviors of complex machine learning models and how these models arrive at a particular decision.
Towards Explanation of DNN-based Prediction with Guided Feature Inversion
While deep neural networks (DNN) have become an effective computational tool, the prediction results are often criticized by the lack of interpretability, which is essential in many real-world applications such as health informatics.
Contextual Outlier Interpretation
Outlier detection plays an essential role in many data-driven applications to identify isolated instances that are different from the majority.
