Search Results for author:
Found 37 papers, 12 papers with code
dS^2LBI: Exploring Structural Sparsity on Deep Network via Differential Inclusion Paths
Over-parameterization is ubiquitous nowadays in training neural networks to benefit both optimization in seeking global optima and generalization in reducing prediction error.
Exploring Counterfactual Alignment Loss towards Human-centered AI
In particular, we utilize the counterfactual generation's ability for causal attribution to introduce a novel loss called the CounterFactual Alignment (CF-Align) loss.
The Blessings of Multiple Treatments and Outcomes in Treatment Effect Estimation
To accommodate these scenarios, we consider a new setting dubbed as multiple treatments and multiple outcomes.
Doubly Robust Proximal Causal Learning for Continuous Treatments
To address these challenges, we propose a kernel-based DR estimator that can well handle continuous treatments.
DIVERSIFY: A General Framework for Time Series Out-of-distribution Detection and Generalization
We propose DIVERSIFY, a general framework, for OOD detection and generalization on dynamic distributions of time series.
Causal Discovery with Unobserved Variables: A Proxy Variable Approach
Our observation is that discretizing continuous variables can can lead to serious errors and comprise the power of the proxy.
Causal Discovery from Subsampled Time Series with Proxy Variables
Based on these, we can leverage the proxies to remove the bias induced by the hidden variables and hence achieve identifiability.
Joint fMRI Decoding and Encoding with Latent Embedding Alignment
Our Latent Embedding Alignment (LEA) model concurrently recovers visual stimuli from fMRI signals and predicts brain activity from images within a unified framework.
Knockoffs-SPR: Clean Sample Selection in Learning with Noisy Labels
While Knockoffs-SPR can be regarded as a sample selection module for a standard supervised training pipeline, we further combine it with a semi-supervised algorithm to exploit the support of noisy data as unlabeled data.
Ranked #1 on
Learning with noisy labels
on Clothing1M
PatchMix Augmentation to Identify Causal Features in Few-shot Learning
We theoretically show that such an augmentation mechanism, different from existing ones, is able to identify the causal features.
Out-of-Distribution Representation Learning for Time Series Classification
Time series classification is an important problem in real world.
Domain Invariant Model with Graph Convolutional Network for Mammogram Classification
To resolve this problem, we propose a novel framework, namely Domain Invariant Model with Graph Convolutional Network (DIM-GCN), which only exploits invariant disease-related features from multiple domains.
Scalable Penalized Regression for Noise Detection in Learning with Noisy Labels
Noisy training set usually leads to the degradation of generalization and robustness of neural networks.
Ranked #4 on
Learning with noisy labels
on Clothing1M
Recovering Latent Causal Factor for Generalization to Distributional Shifts
To avoid such a spurious correlation, we propose \textbf{La}tent \textbf{C}ausal \textbf{I}nvariance \textbf{M}odels (LaCIM) that specifies the underlying causal structure of the data and the source of distributional shifts, guiding us to pursue only causal factor for prediction.
Context-LGM: Leveraging Object-Context Relation for Context-Aware Object Recognition
Finally, to implement this contextual posterior, we introduce a Transformer that takes the object's information as a reference and locates correlated contextual factors.
Relative Instance Credibility Inference for Learning with Noisy Labels
Specifically, we re-purpose a sparse linear model with incidental parameters as a unified Relative Instance Credibility Inference (RICI) framework, which will detect and remove outliers in the forward pass of each mini-batch and use the remaining instances to train the network.
DIVERSIFY to Generalize: Learning Generalized Representations for Time Series Classification
In this paper, we propose to view the time series classification problem from the distribution perspective.
Which Invariance Should We Transfer? A Causal Minimax Learning Approach
When this condition fails, we surprisingly find with an example that this whole stable set, although can fully exploit stable information, is not the optimal one to transfer.
Causal Hidden Markov Model for Time Series Disease Forecasting
We propose a causal hidden Markov model to achieve robust prediction of irreversible disease at an early stage, which is safety-critical and vital for medical treatment in early stages.
Forecasting Irreversible Disease via Progression Learning
In order to account for the degree of progression of the disease, we propose a temporal generative model to accurately generate the future image and compare it with the current one to get a residual image.
Identifying Invariant Texture Violation for Robust Deepfake Detection
To learn such an invariance for deepfake detection, our InTeLe introduces an auto-encoder framework with different decoders for pristine and fake images, which are further appended with a shallow classifier in order to separate out the obvious artifact-effect.
Latent Causal Invariant Model
To avoid spurious correlation, we propose a Latent Causal Invariance Model (LaCIM) which pursues causal prediction.
Learning Causal Semantic Representation for Out-of-Distribution Prediction
Conventional supervised learning methods, especially deep ones, are found to be sensitive to out-of-distribution (OOD) examples, largely because the learned representation mixes the semantic factor with the variation factor due to their domain-specific correlation, while only the semantic factor causes the output.
Bilateral Asymmetry Guided Counterfactual Generating Network for Mammogram Classification
Mammogram benign or malignant classification with only image-level labels is challenging due to the absence of lesion annotations.
Leveraging both Lesion Features and Procedural Bias in Neuroimaging: An Dual-Task Split dynamics of inverse scale space
Specifically, with a variable the splitting term, two estimators are introduced and split apart, i. e. one is for feature selection (the sparse estimator) and the other is for prediction (the dense estimator).
TCGM: An Information-Theoretic Framework for Semi-Supervised Multi-Modality Learning
In this paper, we propose a novel information-theoretic approach, namely \textbf{T}otal \textbf{C}orrelation \textbf{G}ain \textbf{M}aximization (TCGM), for semi-supervised multi-modal learning, which is endowed with promising properties: (i) it can utilize effectively the information across different modalities of unlabeled data points to facilitate training classifiers of each modality (ii) it has theoretical guarantee to identify Bayesian classifiers, i. e., the ground truth posteriors of all modalities.
DessiLBI: Exploring Structural Sparsity of Deep Networks via Differential Inclusion Paths
Over-parameterization is ubiquitous nowadays in training neural networks to benefit both optimization in seeking global optima and generalization in reducing prediction error.
iSplit LBI: Individualized Partial Ranking with Ties via Split LBI
In this paper, instead of learning a global ranking which is agreed with the consensus, we pursue the tie-aware partial ranking from an individualized perspective.
Split LBI for Deep Learning: Structural Sparsity via Differential Inclusion Paths
Over-parameterization is ubiquitous nowadays in training neural networks to benefit both optimization in seeking global optima and generalization in reducing prediction error.
Exploring Structural Sparsity of Deep Networks via Inverse Scale Spaces
To fill in this gap, this paper proposes a new approach based on differential inclusions of inverse scale spaces, which generate a family of models from simple to complex ones along the dynamics via coupling a pair of parameters, such that over-parameterized deep models and their structural sparsity can be explored simultaneously.
PRUNING IN TRAINING: LEARNING AND RANKING SPARSE CONNECTIONS IN DEEP CONVOLUTIONAL NETWORKS
This paper proposes a Pruning in Training (PiT) framework of learning to reduce the parameter size of networks.
$S^{2}$-LBI: Stochastic Split Linearized Bregman Iterations for Parsimonious Deep Learning
This paper proposes a novel Stochastic Split Linearized Bregman Iteration ($S^{2}$-LBI) algorithm to efficiently train the deep network.
A Margin-based MLE for Crowdsourced Partial Ranking
A preference order or ranking aggregated from pairwise comparison data is commonly understood as a strict total order.
MSplit LBI: Realizing Feature Selection and Dense Estimation Simultaneously in Few-shot and Zero-shot Learning
To solve this task, $L_{1}$ regularization is widely used for the pursuit of feature selection and avoiding overfitting, and yet the sparse estimation of features in $L_{1}$ regularization may cause the underfitting of training data.
Zero-shot Learning via Shared-Reconstruction-Graph Pursuit
With the learned SRG, each unseen class prototype (cluster center) in the image feature space can be synthesized by the linear combination of other class prototypes, so that testing instances can be classified based on the distance to these synthesized prototypes.
Boosting with Structural Sparsity: A Differential Inclusion Approach
Boosting as gradient descent algorithms is one popular method in machine learning.
Split LBI: An Iterative Regularization Path with Structural Sparsity
An iterative regularization path with structural sparsity is proposed in this paper based on variable splitting and the Linearized Bregman Iteration, hence called \emph{Split LBI}.
