Previous transfer learning methods based on deep network assume the knowledge should be transferred between the same hidden layers of the source domain and the target domains. This assumption doesn't always hold true, especially when the data from the two domains are heterogeneous with different resolutions. In such ca…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,742 papers · 148 categories
Trend · papers per month
48 results for “Transfer Layer”
Deep networks, composed of multiple layers of hierarchical distributed representations, tend to learn low-level features in initial layers and transition to high-level features towards final layers. Paradigms such as transfer learning, multi-task learning, and continual learning leverage this notion of generic hierarch…
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.
RIFLE improves deep transfer learning by reinitializing fully-connected layers.
problem Limited improvement in transfer learning accuracy with pre-trained models on small datasets.
method Re-Initializing fully-connected layers with random scratch during fine-tuning.
result Significant improvement in deep transfer learning accuracy across various datasets.
This paper quantifies hyperparameter transfer and finds embedding layer learning rate is key.
problem Quantifying optimal hyperparameters for large language models across scales.
method Developed three metrics to quantify hyperparameter transfer and investigated the importance of embedding layer learning rate.
result Maximal Update (μP) parameterization offers high-quality learning rate transfer compared to standard parameterization (SP).
New smart contract mechanisms evade traditional AML systems by decoupling transaction roles.
problem Current AML systems fail to track economic value migration in composable smart contracts.
method Introduce PEB separation and state-mediated value migration to demonstrate how traditional tracing fails.
result Transfer-layer observation is incomplete and causally ambiguous in composable smart contracts.
TransFall uses transfer learning to improve activity recognition from mobile sensors.
problem Performance degradation due to platform and user movement differences.
method Two-tier data transformation, label estimation, and model generation layers.
result TransFall enhances activity recognition accuracy for new scenarios.
A new method prevents forgetting during knowledge transfer.
problem Catastrophic forgetting in transfer learning.
method Transfer without Forgetting (TwF) using a fixed pretrained network.
result TwF outperforms other CL methods by 4.81% in Class-Incremental accuracy.
New adversarial attack method based on deep feature distributions.
problem Adversarial attacks on CNN classifiers using output layer information.
method Modeling and exploiting class-wise and layer-wise deep feature distributions.
result Achieves state-of-the-art transfer-based attack results for undefended ImageNet models.
Develops hyperparameter transfer methods for Dense Associative Memories.
problem Challenges in transferring hyperparameters for DenseAMs due to unique architecture and activation functions.
method Derives explicit prescriptions for hyperparameter transfer from small to large models.
result Excellent agreement between theoretical and empirical results.
The parameter server architecture is prevalently used for distributed deep learning. Each worker machine in a parameter server system trains the complete model, which leads to a hefty amount of network data transfer between workers and servers. We empirically observe that the data transfer has a non-negligible impact o…
SmallML predicts customer churn for SMEs with small data, improving accuracy by 24.2 points.
problem AI exclusion of SMEs due to data scale mismatch.
method Bayesian transfer learning with hierarchical pooling and conformal prediction.
result 96.7% AUC on 100 obs SMEs, 24.2 point improvement over logistic regression.
The paper explores transferability of adversarial examples between convex and 01 loss models, finding non-transferability due to different decision boundaries caused by outliers.
problem Transferability of adversarial examples between convex and 01 loss models.
method Empirical study of transferability between linear 01 loss and convex (hinge) loss models, and between neural networks with different activation functions.
result Adversarial examples are non-transferable between convex and 01 loss models due to different decision boundaries caused by outliers.
Adversarially-trained models transfer better in limited data scenarios.
problem Improving transfer learning performance with limited data.
method Adversarially-train deep nets, freeze early layers, fine-tune last layers, observe shape vs texture bias.
result Adversarially-trained models transfer better than non-adversarially-trained models, especially with limited data.
Neural networks are vulnerable to adversarial examples, malicious inputs crafted to fool trained models. Adversarial examples often exhibit black-box transfer, meaning that adversarial examples for one model can fool another model. However, adversarial examples may be overfit to exploit the particular architecture and …
The paper establishes limits of transfer learning with neural networks.
problem Understanding the fundamental limits of transfer learning.
method Statistical minimax framework for regression with linear and neural network models.
result Lower bounds for target generalization error.
Transfer learning through fine-tuning a pre-trained neural network with an extremely large dataset, such as ImageNet, can significantly accelerate training while the accuracy is frequently bottlenecked by the limited dataset size of the new target task. To solve the problem, some regularization methods, constraining th…
New method improves blackbox attack transferability by perturbing feature hierarchy.
problem Improving transferability of blackbox attacks across different models and datasets.
method Perturbs representations throughout feature hierarchy to mimic other classes.
result Achieves 10x increase in targeted success rate compared to other methods.
Transfer learning benefits vary in DRL, affecting representation and policy learning.
problem Understanding how much of DRL's sample complexity is due to representation learning.
method Transfer learning experiments comparing performance on related games.
result Benefits of transfer learning are highly variable and non-symmetric across tasks.
Genetically-inspired convective heat transfer enhancement in a turbulent boundary layerphysics.flu-dyn
LGAC enhances heat transfer in turbulent boundary layers using slot jets.
problem Enhancing convective heat transfer in turbulent boundary layers.
method Artificial intelligence-based linear genetic algorithms control (LGAC) with slot jets.
result LGAC optimizes heat transfer and flow asymmetry in turbulent boundary layers.
Neural networks are vulnerable to adversarial examples, malicious inputs crafted to fool trained models. Adversarial examples often exhibit black-box transfer, meaning that adversarial examples for one model can fool another model. However, adversarial examples are typically overfit to exploit the particular architectu…
A framework for multilayer networks predicts links without shared structures.
problem Link prediction in multilayer networks without shared structures.
method Bi-level model averaging with -fold cross-validation.
result Framework outperforms existing methods in predictive accuracy and robustness.
Random layer-wise pruning profiles are as effective as metric-based ones for various datasets.
problem Reduction of model size and computational resources in neural networks.
method Conducted baseline experiments, developed RL-based search algorithm for finding transferable layer-wise pruning profiles.
result RL-based layer-wise pruning profiles are as good or better than best profiles found on the original dataset via exhaustive search.
On-device CNN inference for real-time computer vision applications can result in computational demands that far exceed the energy budgets of mobile devices. This paper proposes FixyNN, a co-designed hardware accelerator platform which splits a CNN model into two parts: a set of layers that are fixed in the hardware pla…
Learning from small amounts of labeled data is a challenge in the area of deep learning. This is currently addressed by Transfer Learning where one learns the small data set as a transfer task from a larger source dataset. Transfer Learning can deliver higher accuracy if the hyperparameters and source dataset are chose…
Method selects task-specific neurons for unsupervised transfer learning.
problem Challenges in fine-tuning large language models for specific tasks.
method Selects important neurons for a specific classification task and extends to multi-source transfer learning.
result Higher similarity between task-specific fingerprints leads to better transferability.
A Target-Agnostic Attack on Deep Models: Exploiting Security Vulnerabilities of Transfer Learningcs.LG
Due to insufficient training data and the high computational cost to train a deep neural network from scratch, transfer learning has been extensively used in many deep-neural-network-based applications. A commonly used transfer learning approach involves taking a part of a pre-trained model, adding a few layers at the …
RaNNDy uses randomized neural networks to learn transfer operators efficiently.
problem Efficiently learning transfer operators from data.
method Randomized neural network approach with randomly initialized hidden layers and trained output layer.
result Significant reduction in training time and resources with improved stability.
The cross-domain recommendation technique is an effective way of alleviating the data sparse issue in recommender systems by leveraging the knowledge from relevant domains. Transfer learning is a class of algorithms underlying these techniques. In this paper, we propose a novel transfer learning approach for cross-doma…
To reduce the large computation and storage cost of a deep convolutional neural network, the knowledge distillation based methods have pioneered to transfer the generalization ability of a large (teacher) deep network to a light-weight (student) network. However, these methods mostly focus on transferring the probabili…
The paper uses VGG-19 for plant species classification from leaf images.
problem Manual inspection of plant species by botanists is time-consuming.
method Transfer learning with VGG-19 for feature extraction and classification.
result The model achieves 99.70% accuracy in predicting plant species.
Pre-training is crucial for learning deep neural networks. Most of existing pre-training methods train simple models (e.g., restricted Boltzmann machines) and then stack them layer by layer to form the deep structure. This layer-wise pre-training has found strong theoretical foundation and broad empirical support. Howe…
State-of-the-art machine learning models frequently misclassify inputs that have been perturbed in an adversarial manner. Adversarial perturbations generated for a given input and a specific classifier often seem to be effective on other inputs and even different classifiers. In other words, adversarial perturbations s…
Improved VGG networks enhance image classification accuracy.
problem Enhancing image classification accuracy using modified VGG architectures.
method Two improved VGG architectures were created by freezing the first two blocks and applying different dilation rates in the last three blocks.
result Significant out-performance on image classification tasks on CIFAR-10 and CIFAR-100 datasets.
Study shows benefits of transfer learning with neural networks.
problem Understanding generalization errors in transfer learning.
method Mean-field analysis applied to -ERM and fine-tuning.
result Established conditions for generalization error and convergence rates.
We introduce a novel method that enables parameter-efficient transfer and multi-task learning with deep neural networks. The basic approach is to learn a model patch - a small set of parameters - that will specialize to each task, instead of fine-tuning the last layer or the entire network. For instance, we show that l…
In this paper, we present a novel approach for initializing deep neural networks, i.e., by turning PCA into neural layers. Usually, the initialization of the weights of a deep neural network is done in one of the three following ways: 1) with random values, 2) layer-wise, usually as Deep Belief Network or as auto-encod…
HiDe learns hierarchical control for complex tasks by separating planning and control.
problem Solving long horizon control tasks with generalization to unseen scenarios.
method Functional decomposition of state-action spaces, RL-based planner, modular transfer of policy layers.
result Generalizes across unseen test environments and scales to longer horizons.
New model predicts radiative properties of nanoparticle layers with high accuracy and uncertainty.
problem Predicting radiative properties of nanoparticle embedded layers accurately and with uncertainty.
method Conditional normalizing flows learn conditional distributions of optical outputs given input parameters.
result The model achieves high predictive accuracy and reliable uncertainty estimates.
Optimal scaling found to depend on operator norm across large models and datasets.
problem Lack of unifying principle for optimal hyperparameter scaling across models and datasets.
method Discovered that optimal scaling is conditioned on the operator norm of the output layer.
result The optimal learning rate/batch size pair consistently has the same operator norm value.
New algorithm detects outliers from rare abnormal data.
problem Detecting outliers from rare abnormal data in transfer learning.
method Meta-algorithm for transfer learning in outlier detection.
result Meta-algorithm yields strong guarantees and outperforms existing methods.
New method improves model robustness against adversarial attacks.
problem Adversarial attacks can deceive models trained with transfer learning.
method Noisy feature distillation method for random initialization.
result Models trained with random initialization are more robust to attacks.
Proof of learning rate transfer in MLPs with P parameterization.
problem Understanding and optimizing learning rates in neural networks with different parameterizations.
method Theoretical analysis and empirical validation of learning rate transfer in MLPs with P, SP, and NTP parameterizations.
result The optimal learning rate converges to a non-zero constant as width goes to infinity under P, explaining learning rate transfer.
Paper shows pre-training and transfer learning reduce sample complexity for neural networks.
problem Training high-dimensional supervised learning with limited labeled data.
method Study of single-layer neural networks via online stochastic gradient descent, considering concept shift.
result Pre-training and transfer learning reduce sample complexity by polynomial factors under general assumptions.
LOTOS improves ensemble robustness by promoting orthogonal transformations.
problem Transferability of adversarial examples threatens robustness of classification models.
method LOTOS promotes orthogonality among sub-spaces of transformations in ensemble models.
result LOTOS increases robust accuracy of ensembles by 6 percentage points against black-box attacks.
New findings on representation changes in transfer learning.
problem Understanding representation changes in transfer learning.
method Analysis of pre-trained and fine-tuned representations in transfer learning.
result Representation changes mainly occur in the head, but early layers are also important for cross-domain adaptation.
GNNs generalize CNNs for graph data, showing equivariance and stability.
problem Processing signals on graphs.
method Graph convolutional filters, nonlinearities, stacked layers.
result GNNs converge to graphon neural networks under graph convergence.
As the application of deep learning has expanded to real-world problems with insufficient volume of training data, transfer learning recently has gained much attention as means of improving the performance in such small-data regime. However, when existing methods are applied between heterogeneous architectures and task…