Search Results for author:
Found 18 papers, 9 papers with code
Spurious Correlations in Machine Learning: A Survey
Machine learning systems are known to be sensitive to spurious correlations between biased features of the inputs (e. g., background, texture, and secondary objects) and the corresponding labels.
Benchmarking Retrieval-Augmented Generation for Medicine
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.
AdvST: Revisiting Data Augmentations for Single Domain Generalization
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.
On the Role of Server Momentum in Federated Learning
To our best knowledge, this is the first work that thoroughly analyzes the performances of server momentum with a hyperparameter scheduler and system heterogeneity.
On Task-personalized Multimodal Few-shot Learning for Visually-rich Document Entity Retrieval
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.
Solving a Class of Non-Convex Minimax Optimization in Federated Learning
We propose FL algorithms (FedSGDA+ and FedSGDA-M) and reduce existing complexity results for the most common minimax problems.
Learning for Counterfactual Fairness from Observational Data
A prerequisite for existing methods to achieve counterfactual fairness is the prior human knowledge of the causal model for the data.
Enhance Diffusion to Improve Robust Generalization
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
Subsequently, we propose a potential general adversarial training-based defense mechanism to increase robustness of these systems to the proposed malicious attacks.
CLEAR: Generative Counterfactual Explanations on Graphs
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?".
Correlation Networks for Extreme Multi-label Text Classification
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
In this framework, we generate counterfactuals corresponding to perturbations on each node's and their neighbors' sensitive attributes.
HetMAML: Task-Heterogeneous Model-Agnostic Meta-Learning for Few-Shot Learning Across Modalities
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.
A Survey on Causal Inference
Embraced with the rapidly developed machine learning area, various causal effect estimation methods for observational data have sprung up.
Incorporating Biological Knowledge with Factor Graph Neural Network for Interpretable Deep Learning
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.
Representation Learning for Treatment Effect Estimation from Observational Data
Estimating individual treatment effect (ITE) is a challenging problem in causal inference, due to the missing counterfactuals and the selection bias.
Multi-view Factorization AutoEncoder with Network Constraints for Multi-omic Integrative Analysis
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.
AffinityNet: semi-supervised few-shot learning for disease type prediction
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.
