Search Results for author:
Found 24 papers, 7 papers with code
Generalizing across Temporal Domains with Koopman Operators
By employing Koopman Operators, we effectively address the time-evolving distributions encountered in TDG using the principles of Koopman theory, where measurement functions are sought to establish linear transition relations between evolving domains.
Hessian Aware Low-Rank Weight Perturbation for Continual Learning
We conduct extensive experiments on various benchmarks, including a dataset with large-scale tasks, and compare our method against some recent state-of-the-art methods to demonstrate the effectiveness and scalability of our proposed method.
Mitigating Calibration Bias Without Fixed Attribute Grouping for Improved Fairness in Medical Imaging Analysis
However, models that are well calibrated overall can still be poorly calibrated for a sub-population, potentially resulting in a clinician unwittingly making poor decisions for this group based on the recommendations of the model.
Evaluating the Fairness of Deep Learning Uncertainty Estimates in Medical Image Analysis
Unfortunately, recent studies have indeed shown significant biases in DL models across demographic subgroups (e. g., race, sex, age) in the context of medical image analysis, indicating a lack of fairness in the models.
Clinically Plausible Pathology-Anatomy Disentanglement in Patient Brain MRI with Structured Variational Priors
We propose a hierarchically structured variational inference model for accurately disentangling observable evidence of disease (e. g. brain lesions or atrophy) from subject-specific anatomy in brain MRIs.
On Learning Fairness and Accuracy on Multiple Subgroups
In the upper-level, the fair predictor is updated to be close to all subgroup specific predictors.
Information Gain Sampling for Active Learning in Medical Image Classification
This work presents an information-theoretic active learning framework that guides the optimal selection of images from the unlabelled pool to be labeled based on maximizing the expected information gain (EIG) on an evaluation dataset.
Evolving Domain Generalization
Domain generalization aims to learn a predictive model from multiple different but related source tasks that can generalize well to a target task without the need of accessing any target data.
Fair Representation Learning through Implicit Path Alignment
We consider a fair representation learning perspective, where optimal predictors, on top of the data representation, are ensured to be invariant with respect to different sub-groups.
Gap Minimization for Knowledge Sharing and Transfer
Unlike existing measures which are used as tools to bound the difference of expected risks between tasks (e. g., $\mathcal{H}$-divergence or discrepancy distance), we theoretically show that the performance gap can be viewed as a data- and algorithm-dependent regularizer, which controls the model complexity and leads to finer guarantees.
Directional Domain Generalization
Domain generalization aims to learn a predictive model from multiple different but related source tasks that can generalize well to a target task without the need of accessing any target data.
Generalization Bounds For Meta-Learning: An Information-Theoretic Analysis
We derive a novel information-theoretic analysis of the generalization property of meta-learning algorithms.
On the benefits of representation regularization in invariance based domain generalization
Our regularization is orthogonal to and can be straightforwardly adopted in existing domain generalization algorithms for invariant representation learning.
Aggregating From Multiple Target-Shifted Sources
Multi-source domain adaptation aims at leveraging the knowledge from multiple tasks for predicting a related target domain.
Unified Principles For Multi-Source Transfer Learning Under Label Shifts
We study the label shift problem in multi-source transfer learning and derive new generic principles to control the target generalization risk.
Interventional Domain Adaptation
To address this issue, we intervene in the learning of feature discriminability using unlabeled target data to guide it to get rid of the domain-specific part and be safely transferable.
Beyond $\mathcal{H}$-Divergence: Domain Adaptation Theory With Jensen-Shannon Divergence
We reveal the incoherence between the widely-adopted empirical domain adversarial training and its generally-assumed theoretical counterpart based on $\mathcal{H}$-divergence.
Domain Generalization via Optimal Transport with Metric Similarity Learning
Previous domain generalization approaches mainly focused on learning invariant features and stacking the learned features from each source domain to generalize to a new target domain while ignoring the label information, which will lead to indistinguishable features with an ambiguous classification boundary.
Discriminative Active Learning for Domain Adaptation
To this end, we introduce a discriminative active learning approach for domain adaptation to reduce the efforts of data annotation.
Deep Active Learning: Unified and Principled Method for Query and Training
In this paper, we are proposing a unified and principled method for both the querying and training processes in deep batch active learning.
Toward Metrics for Differentiating Out-of-Distribution Sets
We empirically verify that the most protective OOD sets -- selected according to our metrics -- lead to A-CNNs with significantly lower generalization errors than the A-CNNs trained on the least protective ones.
A Principled Approach for Learning Task Similarity in Multitask Learning
Hence, an important aspect of multitask learning is to understand the similarities within a set of tasks.
Accumulating Knowledge for Lifelong Online Learning
We are providing a theoretical analysis of this algorithm, with a cumulative error upper bound for each task.
Diversity regularization in deep ensembles
Calibrating the confidence of supervised learning models is important for a variety of contexts where the certainty over predictions should be reliable.
