Search Results for author: Aidong Zhang

Found 36 papers, 18 papers with code

Client-Centric Federated Adaptive Optimization

no code implementations17 Jan 2025 Jianhui Sun, Xidong Wu, Heng Huang, Aidong Zhang

Federated Learning (FL) is a distributed learning paradigm where clients collaboratively train a model while keeping their own data private.

Federated Learning

Leveraging Scale-aware Representations for improved Concept-Representation Alignment in ViTs

no code implementations16 Jan 2025 Sanchit Sinha, Guangzhi Xiong, Aidong Zhang

Vision Transformers (ViTs) are increasingly being adopted in various sensitive vision applications - like medical diagnosis, facial recognition, etc.

Medical Diagnosis

Humans Continue to Outperform Large Language Models in Complex Clinical Decision-Making: A Study with Medical Calculators

no code implementations8 Nov 2024 Nicholas Wan, Qiao Jin, Joey Chan, Guangzhi Xiong, Serina Applebaum, Aidan Gilson, Reid McMurry, R. Andrew Taylor, Aidong Zhang, Qingyu Chen, Zhiyong Lu

Although large language models (LLMs) have been assessed for general medical knowledge using medical licensing exams, their ability to effectively support clinical decision-making tasks, such as selecting and using medical calculators, remains uncertain.

Decision Making Multiple-choice +1

Improving Scientific Hypothesis Generation with Knowledge Grounded Large Language Models

no code implementations4 Nov 2024 Guangzhi Xiong, Eric Xie, Amir Hassan Shariatmadari, Sikun Guo, Stefan Bekiranov, Aidong Zhang

To overcome these challenges, we propose KG-CoI (Knowledge Grounded Chain of Ideas), a novel system that enhances LLM hypothesis generation by integrating external, structured knowledge from knowledge graphs (KGs).

Experimental Design Hallucination +1

IdeaBench: Benchmarking Large Language Models for Research Idea Generation

no code implementations31 Oct 2024 Sikun Guo, Amir Hassan Shariatmadari, Guangzhi Xiong, Albert Huang, Eric Xie, Stefan Bekiranov, Aidong Zhang

To address this gap, we propose IdeaBench, a benchmark system that includes a comprehensive dataset and an evaluation framework for standardizing the assessment of research idea generation using LLMs.

Benchmarking scientific discovery

Structural Causality-based Generalizable Concept Discovery Models

no code implementations20 Oct 2024 Sanchit Sinha, Guangzhi Xiong, Aidong Zhang

Our method assumes generative factors and concepts to form a bipartite graph, with directed causal edges from generative factors to concepts.

Disentanglement

ProtoNAM: Prototypical Neural Additive Models for Interpretable Deep Tabular Learning

1 code implementation7 Oct 2024 Guangzhi Xiong, Sanchit Sinha, Aidong Zhang

In this work, we propose a new deep tabular learning method, termed Prototypical Neural Additive Model (ProtoNAM), which introduces prototypes into neural networks in the framework of GAMs.

Additive models

Benchmarking Spurious Bias in Few-Shot Image Classifiers

1 code implementation4 Sep 2024 Guangtao Zheng, Wenqian Ye, Aidong Zhang

In this paper, we propose a systematic and rigorous benchmark framework, termed FewSTAB, to fairly demonstrate and quantify varied degrees of robustness of few-shot classifiers to spurious bias.

Attribute Benchmarking +1

Improving Retrieval-Augmented Generation in Medicine with Iterative Follow-up Questions

1 code implementation1 Aug 2024 Guangzhi Xiong, Qiao Jin, Xiao Wang, Minjia Zhang, Zhiyong Lu, Aidong Zhang

The emergent abilities of large language models (LLMs) have demonstrated great potential in solving medical questions.

MedQA MMLU +4

CoLiDR: Concept Learning using Aggregated Disentangled Representations

no code implementations27 Jul 2024 Sanchit Sinha, Guangzhi Xiong, Aidong Zhang

Interpretability of Deep Neural Networks using concept-based models offers a promising way to explain model behavior through human-understandable concepts.

Representation Learning

MM-SpuBench: Towards Better Understanding of Spurious Biases in Multimodal LLMs

no code implementations24 Jun 2024 Wenqian Ye, Guangtao Zheng, Yunsheng Ma, Xu Cao, Bolin Lai, James M. Rehg, Aidong Zhang

Our findings illuminate the persistence of the reliance on spurious correlations from these models and underscore the urge for new methodologies to mitigate spurious biases.

Question Answering Visual Question Answering

Spuriousness-Aware Meta-Learning for Learning Robust Classifiers

1 code implementation15 Jun 2024 Guangtao Zheng, Wenqian Ye, Aidong Zhang

In this paper, we propose a novel learning framework based on meta-learning, termed SPUME -- SPUriousness-aware MEta-learning, to train an image classifier to be robust to spurious correlations.

Attribute Language Modelling +1

MAML-en-LLM: Model Agnostic Meta-Training of LLMs for Improved In-Context Learning

no code implementations19 May 2024 Sanchit Sinha, Yuguang Yue, Victor Soto, Mayank Kulkarni, Jianhua Lu, Aidong Zhang

In this paper, we propose MAML-en-LLM, a novel method for meta-training LLMs, which can learn truly generalizable parameters that not only perform well on disjointed tasks but also adapts to unseen tasks.

In-Context Learning

Learning Robust Classifiers with Self-Guided Spurious Correlation Mitigation

1 code implementation6 May 2024 Guangtao Zheng, Wenqian Ye, Aidong Zhang

The fine-grained training labels are formulated with different prediction behaviors of the classifier identified in a novel spuriousness embedding space.

Attribute

A Self-explaining Neural Architecture for Generalizable Concept Learning

1 code implementation1 May 2024 Sanchit Sinha, Guangzhi Xiong, Aidong Zhang

With the wide proliferation of Deep Neural Networks in high-stake applications, there is a growing demand for explainability behind their decision-making process.

Concept Alignment Contrastive Learning +2

Spurious Correlations in Machine Learning: A Survey

1 code implementation20 Feb 2024 Wenqian Ye, Guangtao Zheng, Xu Cao, Yunsheng Ma, Aidong Zhang

Machine learning systems are known to be sensitive to spurious correlations between non-essential features of the inputs (e. g., background, texture, and secondary objects) and the corresponding labels.

Survey

Benchmarking Retrieval-Augmented Generation for Medicine

2 code implementations20 Feb 2024 Guangzhi Xiong, Qiao Jin, Zhiyong Lu, Aidong Zhang

However, a RAG system can involve multiple flexible components, and there is a lack of best practices regarding the optimal RAG setting for various medical purposes.

Benchmarking Information Retrieval +3

AdvST: Revisiting Data Augmentations for Single Domain Generalization

1 code implementation20 Dec 2023 Guangtao Zheng, Mengdi Huai, Aidong Zhang

Then, we propose Adversarial learning with Semantics Transformations (AdvST) that augments the source domain data with semantics transformations and learns a robust model with the augmented data.

Data Augmentation Domain Generalization

On the Role of Server Momentum in Federated Learning

no code implementations19 Dec 2023 Jianhui Sun, Xidong Wu, Heng Huang, Aidong Zhang

To our best knowledge, this is the first work that thoroughly analyzes the performances of server momentum with a hyperparameter scheduler and system heterogeneity.

Federated Learning

On Task-personalized Multimodal Few-shot Learning for Visually-rich Document Entity Retrieval

no code implementations1 Nov 2023 Jiayi Chen, Hanjun Dai, Bo Dai, Aidong Zhang, Wei Wei

However, prior works for Few-shot VDER mainly address the problem at the document level with a predefined global entity space, which doesn't account for the entity-level few-shot scenario: target entity types are locally personalized by each task and entity occurrences vary significantly among documents.

Contrastive Learning Entity Retrieval +2

Solving a Class of Non-Convex Minimax Optimization in Federated Learning

1 code implementation NeurIPS 2023 Xidong Wu, Jianhui Sun, Zhengmian Hu, Aidong Zhang, Heng Huang

We propose FL algorithms (FedSGDA+ and FedSGDA-M) and reduce existing complexity results for the most common minimax problems.

Federated Learning

Learning for Counterfactual Fairness from Observational Data

no code implementations17 Jul 2023 Jing Ma, Ruocheng Guo, Aidong Zhang, Jundong Li

A prerequisite for existing methods to achieve counterfactual fairness is the prior human knowledge of the causal model for the data.

Attribute Causal Discovery +4

Enhance Diffusion to Improve Robust Generalization

1 code implementation5 Jun 2023 Jianhui Sun, Sanchit Sinha, Aidong Zhang

We approximate the dynamic of PGD-AT by a continuous-time Stochastic Differential Equation (SDE), and show that the diffusion term of this SDE determines the robust generalization.

Understanding and Enhancing Robustness of Concept-based Models

no code implementations29 Nov 2022 Sanchit Sinha, Mengdi Huai, Jianhui Sun, Aidong Zhang

Subsequently, we propose a potential general adversarial training-based defense mechanism to increase robustness of these systems to the proposed malicious attacks.

Decision Making Financial Analysis +1

CLEAR: Generative Counterfactual Explanations on Graphs

no code implementations16 Oct 2022 Jing Ma, Ruocheng Guo, Saumitra Mishra, Aidong Zhang, Jundong Li

Counterfactual explanations promote explainability in machine learning models by answering the question "how should an input instance be perturbed to obtain a desired predicted label?".

counterfactual Counterfactual Explanation +1

Correlation Networks for Extreme Multi-label Text Classification

3 code implementations Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining 2022 Guangxu Xun, Kishlay Jha, Jianhui Sun, Aidong Zhang

This paper develops the Correlation Networks (CorNet) architecture for the extreme multi-label text classification (XMTC) task, where the objective is to tag an input text sequence with the most relevant subset of labels from an extremely large label set.

Multi Label Text Classification Multi-Label Text Classification +2

Learning Fair Node Representations with Graph Counterfactual Fairness

1 code implementation10 Jan 2022 Jing Ma, Ruocheng Guo, Mengting Wan, Longqi Yang, Aidong Zhang, Jundong Li

In this framework, we generate counterfactuals corresponding to perturbations on each node's and their neighbors' sensitive attributes.

Attribute counterfactual +2

HetMAML: Task-Heterogeneous Model-Agnostic Meta-Learning for Few-Shot Learning Across Modalities

no code implementations17 May 2021 Jiayi Chen, Aidong Zhang

To deal with task heterogeneity and promote fast within-task adaptions for each type of tasks, in this paper, we propose HetMAML, a task-heterogeneous model-agnostic meta-learning framework, which can capture both the type-specific and globally shared knowledge and can achieve the balance between knowledge customization and generalization.

Few-Shot Learning Vocal Bursts Type Prediction

A Survey on Causal Inference

1 code implementation5 Feb 2020 Liuyi Yao, Zhixuan Chu, Sheng Li, Yaliang Li, Jing Gao, Aidong Zhang

Embraced with the rapidly developed machine learning area, various causal effect estimation methods for observational data have sprung up.

BIG-bench Machine Learning Causal Inference +1

Incorporating Biological Knowledge with Factor Graph Neural Network for Interpretable Deep Learning

no code implementations3 Jun 2019 Tianle Ma, Aidong Zhang

To address this challenge, we developed the Factor Graph Neural Network model that is interpretable and predictable by combining probabilistic graphical models with deep learning.

Deep Learning Graph Neural Network

Representation Learning for Treatment Effect Estimation from Observational Data

1 code implementation NeurIPS 2018 Liuyi Yao, Sheng Li, Yaliang Li, Mengdi Huai, Jing Gao, Aidong Zhang

Estimating individual treatment effect (ITE) is a challenging problem in causal inference, due to the missing counterfactuals and the selection bias.

Causal Inference Representation Learning +1

Multi-view Factorization AutoEncoder with Network Constraints for Multi-omic Integrative Analysis

no code implementations6 Sep 2018 Tianle Ma, Aidong Zhang

Our framework employs deep representation learning to learn feature embeddings and patient embeddings simultaneously, enabling us to integrate feature interaction network and patient view similarity network constraints into the training objective.

Representation Learning

AffinityNet: semi-supervised few-shot learning for disease type prediction

1 code implementation22 May 2018 Tianle Ma, Aidong Zhang

The kNN attention pooling layer is a generalization of the Graph Attention Model (GAM), and can be applied to not only graphs but also any set of objects regardless of whether a graph is given or not.

Deep Learning Few-Shot Learning +3

Cannot find the paper you are looking for? You can Submit a new open access paper.