A student classifier learns from feature visualizations of a teacher network to achieve high accuracy.
problem Machine learning-based sleep apnea detection with limited access to training data.
method Interpretation-based indirect knowledge transfer using activation maximization and synthetic datasets.
result The student classifier achieves 97.8% accuracy on MNIST and 86.1-89.5% on Apnea-ECG dataset.
Modular deep learning framework using pairwise labels without backpropagation.
problem Efficiently training deep neural networks with limited supervision.
method Stacked linear models in feature spaces, provably optimal modular learning framework.
result High accuracy (94.88%) achieved with minimal labeled examples (1 per class).
Dockless bike sharing systems need effective bike flow prediction models.
problem Imbalanced and dynamic use of bikes leads to mandatory rebalancing operations.
method Divide urban area into regions, model spatio-temporal bike flows, extract traffic patterns, and predict bike flows.
result Interpretable bike flow prediction model provides valuable insights into bike flow analysis.
Standardized fairness measures for continuous risk scores using Wasserstein distance.
problem Quantifying and interpreting group disparities in continuous risk scores.
method Proposes standardized fairness measures based on Wasserstein distance for continuous scores.
result Proposed measures outperform ROC-based fairness measures by being more explicit and quantifying significant biases.
Paper explores GAN generalization via privacy protection, proving bounds on generalization gap and reducing leakage.
problem Understanding and bounding the generalization gap of GANs.
method Theoretical proof using differential privacy, reinterpreting Bayesian GAN, membership attacks.
result Proven bounds on generalization gap and reduced information leakage.
Inner product-based convolution has been a central component of convolutional neural networks (CNNs) and the key to learning visual representations. Inspired by the observation that CNN-learned features are naturally decoupled with the norm of features corresponding to the intra-class variation and the angle correspond…
A method compares AI corrections to a base model for explaining predictions.
problem Creating explanations for AI predictions.
method Introduces a surrogate model to correct a simpler base model and provides criteria for accuracy and fidelity.
result Induces neighborhoods of instances with ideal accuracy and fidelity.
Study compares exponential and power-law kernels in modeling high-frequency trading data.
problem Modeling high-frequency trading data with specific kernel types.
method Proposes and analyzes two bivariate Hawkes processes with exponential and power-law kernels.
result Identifies strengths and limitations of exponential and power-law kernels for high-frequency trading data.
Closed-form polynomial approximations replace MLPs in transformers, enabling new interpretability methods.
problem Replacing MLPs with polynomial approximations for transformer models.
method Theoretical derivation of closed-form least-squares approximations of MLPs and GLUs using polynomial functions.
result Polynomial approximations explain over 95% of MLP and GLU outputs' variance, enabling interpretability.
Improved Shapley Value method for better model interpretation.
problem Misunderstanding and incorrect interpretation of Shapley Values in machine learning models.
method Identification of null and active coalitions, coalitional Shapley Value computation.
result Correct computation and inference of important variables using Shapley Values.
This work interprets GELU and related activations via a first-order loss function.
problem Understanding and optimizing activation functions in neural networks.
method Complementary interpretation using the Gaussian first-order loss function.
result Calibrated or learned uniform-threshold gates are competitive and often outperform GELU, ReLU, and SiLU/Swish.
Shampoo achieves higher token efficiency than Muon in language models.
problem Understanding the relationship and relative data efficiency of Shampoo and Muon compared to Adam and Signum.
method Extensive experiments on language models, demonstrating Shampoo's higher efficiency and decomposing its updates.
result Shampoo's benefits are attributed to its application to weight matrices, challenging interpretations based on variance adaptation and whitening.
Improves interpretability of anomaly scores in GBRBM-based detection.
problem Difficulty in setting a proper threshold for anomaly scores.
method Proposes a measure based on cumulative distribution and uses simulated annealing for evaluation.
result Established a guideline for setting the threshold using the interpretable measure.
Transfer learning improves portfolio optimization by identifying transfer risk.
problem Financial portfolio optimization problem.
method Introduces transfer risk concept within transfer learning framework.
result Transfer risk is a significant indicator of transferability and enhances portfolio management efficiency.
Paper analyzes transfer risk in transfer learning for finance.
problem Evaluate transferability of transfer learning in finance.
method Proposes transfer risk concept and applies to stock return prediction and portfolio optimization.
result Transfer risk correlates with transfer learning performance and identifies appropriate source tasks.
This paper explores the connection between adversarial and knowledge transferability.
problem Understanding the factors affecting knowledge transferability.
method Theoretical analysis and practical metrics for adversarial transferability.
result Adversarial transferability and knowledge transferability are closely related.
Mathematical framework for transfer learning feasibility and transfer risk.
problem Theoretical analysis of transfer learning.
method Reformulated transfer learning as an optimization problem, introduced transfer risk concept.
result Demonstrated the potential and benefits of incorporating transfer risk in transfer learning evaluation.
Transfer learning borrows knowledge from a source domain to facilitate learning in a target domain. Two primary issues to be addressed in transfer learning are what and how to transfer. For a pair of domains, adopting different transfer learning algorithms results in different knowledge transferred between them. To dis…
YASENN interprets neural networks by partitioning activation sequences.
problem Interpreting complex neural network decisions.
method YASENN uses layer-wise gradient boosting decision trees to distill and partition neuron activation sequences.
result YASENN provides interpretable partitions of the input space, revealing neural network decision artifacts.
Survey connects and systematizes transfer learning research.
problem Reduce dependence on target domain data for target learners.
method Systematic review of 40+ transfer learning approaches.
result Importance of choosing appropriate transfer learning models.
Enhances transfer learning with semantic reasoning for robust predictions.
problem Improving robustness of transfer learning models.
method Integrates semantic representations for better knowledge transfer.
result Demonstrated robustness in bus delay and air quality forecasting.
Study measures impact of data and neural net similarity on transferability in restaurant sales data.
problem Identify indicators for successful transferability of neural nets across different data sets.
method Empirical study on sales data from six restaurants, calculating indicators based on data and neural net similarities.
result Negative correlations between transferability and indicators, allowing better model performance and fewer transfers.
Paper defines and mitigates negative transfer in transfer learning.
problem Negative transfer occurs when transferring knowledge from a less related source task inversely harms target performance.
method Formal definition, analysis of three aspects, adversarial networks-based technique.
result The proposed method consistently improves target performance and largely avoids negative transfer.
The paper analyzes phase transitions in transfer learning for perceptrons.
problem Understanding when transfer learning from a source task to a target task is beneficial.
method Theoretical analysis of a pair of related perceptron learning tasks.
result Reveals a phase transition from negative to positive transfer as task similarity changes.
Adaptive source selection for positive transfer in linear models improves target dataset performance.
problem Limited task-specific labeled data in business settings.
method Greedily decides from which sources and how many samples to incorporate into the target dataset using an accept/reject rule based on a data-dependent estimate of the transfer gain.
result Consistent gains over classical and recent strong baselines while avoiding negative transfer.
New research on limits of transfer learning, proving key selection and dependence requirements.
problem Insufficient theoretical foundation for transfer learning.
method Proved novel results on transfer learning, emphasizing selection of information and dependence between domains.
result Upper bound on improvement possible with transfer learning, highlighting the need for careful selection.
EPP scores interpret model performance better than traditional metrics.
problem Lack of interpretable and stable performance metrics for model selection and hyperparameter tuning.
method Introducing EPP (interpretable predictive power) rating system.
result EPP scores provide probabilistic interpretations of model performance differences.
Proposes a transfer learning method for high-dimensional quantile regression.
problem Inadequate handling of heterogeneity and heavy tails in transfer learning.
method High-dimensional quantile regression framework with double transfer learning estimator.
result Established error bounds and valid confidence intervals for high-dimensional quantile regression coefficients.
DNAS disentangles neural architecture search for better interpretability and performance.
problem Lack of interpretability in existing neural architecture search methods.
method DNAS disentangles the hidden representation of the controller into semantically meaningful concepts.
result DNAS achieves state-of-the-art performance and competitive architectures.
Localized transfer learning improves nonparametric regression performance.
problem Improving nonparametric regression performance on target tasks.
method Localized transfer learning framework that models heterogeneity and partition covariate space into cells.
result Sharp minimax rates show local transfer mitigates the curse of dimensionality.
In order for machine learning to be deployed and trusted in many applications, it is crucial to be able to reliably explain why the machine learning algorithm makes certain predictions. For example, if an algorithm classifies a given pathology image to be a malignant tumor, then the doctor may need to know which parts …
This work transfers causal knowledge between tasks for Individual Treatment Effect estimation.
problem Estimating Individual Treatment Effects (ITE) requires a large amount of data, making it challenging.
method The authors introduce a practical framework for efficient transfer of causal knowledge between tasks, using a Causal Inference Task Affinity (CITA) measure.
result ITE knowledge transfer can significantly reduce the amount of data needed for ITE estimation.
Investigates transfer learning in spatial statistics.
problem Applying transfer learning to spatial statistics.
method Simple MLP models for spatial data.
result Potential of transfer learning in spatial statistics.
With the help of transfer entropy, we analyze information flows between communities of complex networks. We show that the transfer entropy provides a coherent description of interactions between communities, including non-linear interactions. To put some flesh on the bare bones, we analyze transfer entropies between co…
A meta-learning approach for automatic knowledge transfer between networks.
problem Improving performance in small-data real-world problems with heterogeneous architectures and tasks.
method Meta-learning to automatically learn what knowledge to transfer and where in the target network.
result Meta-transfer approach significantly outperforms hand-crafted methods on various datasets and network architectures.
Simple methods improve regression transferability estimation.
problem Estimating how well regression models transfer between tasks.
method Two simple, computationally efficient approaches based on negative regularized mean squared error.
result Significantly outperform existing methods in accuracy and efficiency.
This paper defines and quantifies transferability in domain generalization.
problem Understanding and quantifying transferability between domains.
method Formal definition and estimation of transferability, upper bound for target error.
result Many algorithms do not learn transferable features, proposing a new algorithm.
Training a source model optimally for its own task is suboptimal for downstream transfer.
problem The optimality of a source model for its own task hinders downstream transfer performance.
method Analyzes L2-SP ridge regression, characterizes transfer-optimal source penalty, and identifies alignment-dependent effects.
result Transfer benefits from stronger source regularization when aligned imperfectly, and from weaker regularization when aligned perfectly.
Transfer learning does not improve character recognition performance.
problem Improving character recognition performance using transfer learning.
method Performed experiments with varying levels of similarity between source and target tasks, transferring both parameters and features.
result No significant advantage gained by transfer learning over traditional machine learning.
AdaTrans adapts to feature and sample transfer in high-dimensional regression.
problem High-dimensional linear regression with more features than samples.
method F-AdaTrans and S-AdaTrans methods using fused-penalties and adaptive weights.
result AdaTrans achieves convergence rates close to oracle estimators and near-minimax optimal rates.
Adversarial perturbations fool wearable sensor systems, showing transferability across different systems.
problem Adversarial examples fool wearable sensor systems, showing transferability across different systems.
method Study of adversarial transferability in wearable sensor systems from four perspectives: systems, subjects, sensor body locations, and datasets.
result Strong untargeted transferability in most cases, targeted attacks less successful.
Paper tackles continuous transfer learning with evolving target domains.
problem Challenges of negative transfer in evolving target domains.
method Proposes label-informed C-divergence for measuring distribution shift and negative transfer.
result Demonstrates effectiveness of TransLATE framework in minimizing classification error and C-divergence.
Paper introduces a new method for improving reinforcement learning performance using transfer learning.
problem Improving reinforcement learning performance with limited sample sizes in dynamic decision-making scenarios.
method Developed a novel ``re-weighted targeting procedure'' and ``transfer deep Q∗-learning'' approach. result Demonstrated improved reinforcement learning performance through strategic sample construction.
We observe standard transfer learning can improve prediction accuracies of target tasks at the cost of lowering their prediction fairness -- a phenomenon we named discriminatory transfer. We examine prediction fairness of a standard hypothesis transfer algorithm and a standard multi-task learning algorithm, and show th…
LEEP measures transferability of learned representations efficiently.
problem Evaluating the transferability of learned representations in machine learning.
method LEEP: Log Expected Empirical Prediction, a simple measure requiring one pass through the target data set.
result LEEP predicts transfer and meta-transfer learning performance and convergence speed, outperforming existing measures.
This study investigates how much knowledge from natural images can be transferred to pathology images.
problem Quantifying how much knowledge from natural images can be transferred to pathology images.
method Proposes a framework to quantify knowledge gain by a particular layer, conducts empirical investigation in pathology image centered transfer learning.
result Early layers of deep models can transfer knowledge to pathology image classification tasks.
We analyze a monetary system of random money transfer on the basis of double entry bookkeeping. Without boundary conditions, we do not reach a price equilibrium and violate text-book formulas of economists quantity theory (MV=PQ). To match the resulting quantity of money with the model assumption of a constant price, w…
Paper proposes a statistical test for transfer learning in linear regression.
problem Theoretical framework for parameter transfer in linear regression.
method Developed a statistical test to predict transfer quality.
result The test can predict if a fine-tuned model has lower prediction risk.