arXiv research

A meta-learning approach for automatic knowledge transfer between networks.

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…

Physics-informed neural networks simulate radiative transfer efficiently.

Paper introduces a new method for improving reinforcement learning performance using transfer learning.

Study measures impact of data and neural net similarity on transferability in restaurant sales data.

Parameters in deep neural networks which are trained on large-scale databases can generalize across multiple domains, which is referred as "transferability". Unfortunately, the transferability is usually defined as discrete states and it differs with domains and network architectures. Existing works usually heuristical…

Proposes a transfer learning method for accurate latent variable estimation.

Optimal transport metric transfers deep network representations efficiently.

New method improves knowledge transfer from large to small networks.

We extend graph neural networks to transfer performance across different input sizes.

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…

Bayesian network structure learning algorithms with limited data are being used in domains such as systems biology and neuroscience to gain insight into the underlying processes that produce observed data. Learning reliable networks from limited data is difficult, therefore transfer learning can improve the robustness …

Improved sales forecasting for new products using transfer learning.

Paper shows pre-training and transfer learning reduce sample complexity for neural networks.

Study shows benefits of transfer learning with neural networks.

Measures neural network information transfer for generalization.

Anti-transfer learning prevents misleading representations for speech tasks.

New unsupervised transfer learning method for spatiotemporal tasks.

New method creates powerful, transferable adversarial attacks for deep learning networks.

Transfer learning for deep neural networks is the process of first training a base network on a source dataset, and then transferring the learned features (the network's weights) to a second network to be trained on a target dataset. This idea has been shown to improve deep neural network's generalization capabilities …

Simplifies transfer learning with deep neural networks using ridge regression.

Transfer learning adapted for hybrid classical-quantum neural networks.

Model projection transfers convolutional network properties to feedforward networks.

This work improves GNN training efficiency by maximizing ego-graph information.

Sparse sub-networks win transfer learning tasks.

The paper explores transferability of adversarial examples between convex and 01 loss models, finding non-transferability due to different decision boundaries caused by outliers.

Improves deep transfer learning by preventing performance degradation.

Develops hyperparameter transfer methods for Dense Associative Memories.

Transfer learning is a very important tool in deep learning as it allows propagating information from one "source dataset" to another "target dataset", especially in the case of a small number of training examples in the latter. Yet, discrepancies between the underlying distributions of the source and target data are c…

The paper establishes limits of transfer learning with neural networks.

New method improves adversarial transferability from Bayesian neural networks.

Connections between nodes of fully connected neural networks are usually represented by weight matrices. In this article, functional transfer matrices are introduced as alternatives to the weight matrices: Instead of using real weights, a functional transfer matrix uses real functions with trainable parameters to repre…

Paper proposes transferring neural network learning trajectories.

This work studies adversarial transferability and proposes ensemble methods to improve robustness.

AdaGCN transfers labels across networks via adversarial domain adaptation and graph convolution.

A new method prevents forgetting during knowledge transfer.

Residual networks with depthwise hyperparameter scaling transfer optimal hyperparameters across width and depth.

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…

DANE adapts network embeddings across multiple domains.

Improved drug-protein interaction prediction using FTL method.

Adversarially robust transfer learning improves model robustness with minimal data.

Paper shows spectral filters can transfer between different graphs discretizing the same space.

Study on neural networks' performance in sequential task learning.

New approach for multi-task reinforcement learning without task interference.

Paper proposes CNN-based time series anomaly detection with transfer learning.

A powerful network teaches a weak one, improving its performance.

In this paper we combine one method for hierarchical reinforcement learning - the options framework - with deep Q-networks (DQNs) through the use of different "option heads" on the policy network, and a supervisory network for choosing between the different options. We utilise our setup to investigate the effects of ar…

Many tasks in natural language understanding require learning relationships between two sequences for various tasks such as natural language inference, paraphrasing and entailment. These aforementioned tasks are similar in nature, yet they are often modeled individually. Knowledge transfer can be effective for closely …