Framework for lifelong learning using eigentasks to avoid forgetting and transfer knowledge.
problem Avoiding forgetting and transferring knowledge in lifelong learning.
method Eigentask framework: skills paired with generative models, wake-sleep cycle for learning and consolidation.
result Improved performance in supervised continual learning, evidence of forward knowledge transfer.
Enhances PCE surrogates using transfer learning for expensive simulations.
problem Over-sampling in PCE for expensive forward models.
method Transfer learning from similar tasks to a new task with limited training data.
result Improves scalability and accuracy of PCE surrogates.
Transferring knowledge across many streaming processes remains an uncharted territory in the existing literature and features unique characteristics: no labelled instance of the target domain, covariate shift of source and target domain, different period of drifts in the source and target domains. Autonomous transfer l…
Current reinforcement learning (RL) methods can successfully learn single tasks but often generalize poorly to modest perturbations in task domain or training procedure. In this work, we present a decoupled learning strategy for RL that creates a shared representation space where knowledge can be robustly transferred. …
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.
Injecting human knowledge is an effective way to accelerate reinforcement learning (RL). However, these methods are underexplored. This paper presents our discovery that an abstract forward model (thought-game (TG)) combined with transfer learning (TL) is an effective way. We take StarCraft II as our study environment.…
A simple approach improves performance on both past and future tasks in lifelong learning.
problem Forgetting in lifelong learning, where performance on past tasks degrades when learning new tasks.
method Representation ensembling to improve performance on both future and past tasks.
result Representation ensembling demonstrates both forward and backward transfer across various datasets.
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.
Unified framework predicts S&P500 index direction using transfer learning and causal graph.
problem Predicting the movement of financial indices like S&P500.
method Transfer learning, causal graph, multidisciplinary knowledge, VAE network.
result 74.3% accuracy, 67% F1-score, 0.42 Matthew correlation on 12 years test period.
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.
Unified framework supports lifelong learning properties.
problem Capturing desirable properties of human learning in machine learning.
method Unified framework with one central mechanism.
result Supports almost all desirable properties of human learning.
UDA learns target domain from unlabeled data via source knowledge transfer.
problem Learning unlabeled target domain data.
method Transferring both source knowledge and target-relatedness.
result Improves UDA performance by simultaneous knowledge transfer.
We consider the problem of building a state representation model in a continual fashion. As the environment changes, the aim is to efficiently compress the sensory state's information without losing past knowledge. The learned features are then fed to a Reinforcement Learning algorithm to learn a policy. We propose to …
TX-Ray analyzes and quantifies model knowledge transfer in NLP.
problem Insufficient methods for explaining and quantifying model knowledge transfer in NLP.
method Modified computer vision explainability principle to NLP, visualizing feature preference distributions.
result TX-Ray reveals how self-supervised models learn linguistic abstractions and improves generalization.
Enhances generative model accuracy through knowledge transfer.
problem Improving generative model precision across different tasks.
method Introduces a novel framework for transfer learning using shared structures.
result Demonstrates enhanced performance in diffusion and normalizing flows models.
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.
The introduction of deep learning and transfer learning techniques in fields such as computer vision allowed a leap forward in the accuracy of image classification tasks. Currently there is only limited use of such techniques in neuroscience. The challenge of using deep learning methods to successfully train models in …
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.
Transfer learning methods for reinforcement learning (RL) domains facilitate the acquisition of new skills using previously acquired knowledge. The vast majority of existing approaches assume that the agents have the same design, e.g. same shape and action spaces. In this paper we address the problem of transferring pr…
SETrLUSI combines diverse knowledge from multiple domains for faster convergence.
problem Handling diverse knowledge from multiple domains in transfer learning.
method Stochastic Ensemble Multi-Source Transfer Learning Using Statistical Invariant (SETrLUSI).
result SETrLUSI accelerates convergence and outperforms related methods.
Weight Squeezing transfers knowledge from large models to smaller ones, improving performance and speed.
problem Transfer learning and model compression for faster and more efficient training.
method Reparameterization of weights from a large model to a smaller one.
result Weight Squeezing outperforms other methods on GLUE benchmark with faster training.
Often we wish to transfer representational knowledge from one neural network to another. Examples include distilling a large network into a smaller one, transferring knowledge from one sensory modality to a second, or ensembling a collection of models into a single estimator. Knowledge distillation, the standard approa…
DERWENT learns paths for distant transfer learning via deep random walk.
problem Transfer learning between distant domains is challenging.
method DERWENT uses deep random walk to explicitly learn paths between source and target domains.
result DERWENT achieves state-of-the-art performance on benchmark datasets.
Knowledge Transfer (KT) techniques tackle the problem of transferring the knowledge from a large and complex neural network into a smaller and faster one. However, existing KT methods are tailored towards classification tasks and they cannot be used efficiently for other representation learning tasks. In this paper a n…
The paper proposes a method to transfer knowledge across different settings using causal theory.
problem Learning transfer across similar but different settings.
method Bayesian perspective of causal theory induction, integrating instance-level associative learning and abstract-level structural causal knowledge.
result The proposed model achieved transfer behavior across trials and learning situations, unlike RL algorithms.
Autonomous Vehicles(AV) are one of the brightest promises of the future which would help cut down fatalities and improve travel time while working in harmony. Autonomous vehicles will face with challenging situations and experiences not seen before. These experiences should be converted to knowledge and help the vehicl…
Paper tackles hypothesis transfer learning for black-box models.
problem Difficult to build universal machine learning models across different institutions.
method Dynamic Knowledge Distillation (dkdHTL) with instance-wise weighting.
result Empirical results show the effectiveness of dkdHTL.
Paper tackles robust knowledge transfer in parallel RL tasks.
problem Transfer knowledge from low-tier to high-tier tasks in parallel RL without shared dynamics or reward functions.
method Identifies Optimal Value Dominance condition and proposes online learning algorithms for both tasks.
result Achieves constant regret on partial states and near-optimal regret when tasks are dissimilar.
A new KD layer lets student models learn and apply teacher knowledge explicitly.
problem Implicit action of traditional KD on student's feature transform limits its use in intermediate layers.
method Proposes a learnable KD layer that explicitly embeds teacher's knowledge in feature transform.
result Improves KD with two abilities: leveraging teacher's knowledge and feeding forward knowledge deeper.
Bayesian method transfers knowledge between brain tumor datasets.
problem Applying deep learning to small medical datasets.
method Generative Bayesian Prior network for knowledge transfer.
result Best results in Dice Similarity Coefficient for BRATS2018.
Taxonomy of knowledge modalities in RL for better transfer.
problem Tackling the transfer of knowledge in reinforcement learning.
method Systematic analysis of knowledge modalities in RL.
result A taxonomy of knowledge modalities in reinforcement learning.
New algorithm improves knowledge transfer in dynamic decision-making.
problem Utilizing data from existing ventures to improve decision-making in new ventures.
method Proposes Transferred Fitted Q-Iteration algorithm for estimating optimal action-state function Q∗. result Significantly improved final learning error of Q∗ function. 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…
Sharing knowledge between tasks is vital for efficient learning in a multi-task setting. However, most research so far has focused on the easier case where knowledge transfer is not harmful, i.e., where knowledge from one task cannot negatively impact the performance on another task. In contrast, we present an approach…
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.
KG-WDRO optimizes transfer learning with external knowledge.
problem Over-pessimism in WDRO for small target samples.
method KG-WDRO incorporates multiple sources of external knowledge to construct smaller Wasserstein ambiguity sets.
result KG-WDRO improves transfer learning performance and adaptivity.
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 which aims at utilizing knowledge learned from one problem (source domain) to solve another different but related problem (target domain) has attracted wide research attentions. However, the current transfer learning methods are mostly uninterpretable, especially to people without ML expertise. In thi…
Paper explores how knowledge distillation transfers inductive biases between models.
problem Transferring inductive biases between models for tasks with limited data.
method Knowledge distillation applied to models with different inductive biases (LSTMs vs. Transformers, CNNs vs. MLPs).
result Effect of inductive biases is transferred through knowledge distillation, impacting both performance and solution characteristics.
Meta-Learning is a subarea of Machine Learning that aims to take advantage of prior knowledge to learn faster and with fewer data [1]. There are different scenarios where meta-learning can be applied, and one of the most common is algorithm recommendation, where previous experience on applying machine learning algorith…
KEEN Universe provides reproducible and transferable knowledge graph embeddings.
problem Lack of reproducibility and transferability in KGE experiments.
method Developed an ecosystem with Python packages for reproducible and transferable KGEs.
result KEEN Universe facilitates sharing of trained KGE models across different fields.
SPEQ improves quantized neural networks by stochastic precision sharing and cosine similarity loss.
problem Improving quantized deep neural networks for edge devices.
method SPEQ combines stochastic precision sharing and cosine similarity loss for knowledge distillation.
result SPEQ outperforms existing methods in various tasks.
In complex transfer learning scenarios new tasks might not be tightly linked to previous tasks. Approaches that transfer information contained only in the final parameters of a source model will therefore struggle. Instead, transfer learning at a higher level of abstraction is needed. We propose Leap, a framework that …
Improved sales forecasting for new products using transfer learning.
problem Insufficient training data for new products leads to inaccurate sales forecasts.
method Network-based Transfer Learning approach for deep neural networks.
result Deep neural networks' prediction accuracy for food sales forecasting can be effectively increased.
An activation boundary for a neuron refers to a separating hyperplane that determines whether the neuron is activated or deactivated. It has been long considered in neural networks that the activations of neurons, rather than their exact output values, play the most important role in forming classification friendly par…
HGKT transfers knowledge from seen to unseen classes in GZSL without prior unseen class info.
problem Learning to classify unseen classes in GZSL.
method Structured heterogeneous graph with graph neural network for knowledge transfer.
result Achieves state-of-the-art results on public benchmark datasets.
Paper tackles high-dimensional quantile regression with distribution shift using transfer learning.
problem Efficiency of knowledge transfer is severely impacted by distribution shift in high-dimensional regression.
method Proposes a novel transferable set and framework for three types of distribution shift: parameter, covariate, and residual.
result Establishes estimation error bounds and source detection consistency for the proposed method.
Knowledge transfer speeds up neural classifier training.
problem Lack of theoretical analysis of knowledge transfer in neural networks.
method Regularization of fit between teacher and student networks using privileged information.
result Wide two-layer networks can interpolate between privileged information and data, improving generalization.