New attention mechanism improves meta-transfer learning in dynamic tasks.
problem Underfitting in meta-transfer learning with dynamic tasks.
method Proposed Recurrent Memory Reconstruction (RMR) attention mechanism.
result ASNP-RMR significantly outperforms baselines in various tasks.
Improved language models with talking-heads attention.
problem Language model perplexity and quality issues.
method Added linear projections in multi-head attention.
result Better perplexities and quality in language tasks.
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…
TAP transfers knowledge from unlabeled data to improve cross-modal learning.
problem Improving supervised learning performance using unlabeled data from a different modality.
method Probabilistic approach for missing information estimation, kernel regression, cross-attention module, TAP neural network.
result TAP significantly improves generalization across different domains and neural network architectures.
Model improves information transfer from visual streams.
problem Challenges in unsupervised learning from continuous visual data.
method Inspired by physics, maximizes mutual information through temporal process.
result Focus of attention enhances information transfer from input stream.
Paper proposes AoA, a new adversarial attack method that significantly increases transferability.
problem Developing universal adversarial attacks on deep neural networks.
method AoA attacks the semantic property of attention in DNNs, enhancing transferability by altering the loss function.
result AoA generates adversarial samples that defeat 13 well-trained DNNs, achieving over 85% error rate.
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…
Most previous studies on multi-agent reinforcement learning focus on deriving decentralized and cooperative policies to maximize a common reward and rarely consider the transferability of trained policies to new tasks. This prevents such policies from being applied to more complex multi-agent tasks. To resolve these li…
LoLCATs improves linearized LLM quality with less memory and compute.
problem Linearizing large language models (LLMs) often degrades model quality and requires expensive training.
method Two-step method: attention transfer and low-rank adaptation.
result Significant improvement in linearizing quality with 20+ points on 5-shot MMLU.
A new distillation method transfers channel information from teacher to student.
problem Transfer knowledge from teacher to student with fewer parameters and calculations.
method Channel Distillation (CD) and Guided Knowledge Distillation (GKD) with loss decay.
result Achieved 27.68% top-1 error on ImageNet with ResNet18, outperforming state-of-the-art methods.
In recent years, deep learning models have shown great potential in source code modeling and analysis. Generally, deep learning-based approaches are problem-specific and data-hungry. A challenging issue of these approaches is that they require training from starch for a different related problem. In this work, we propo…
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.
EWS-GCN improves credit scoring by analyzing money transfer connections.
problem Improving credit scoring in transactional banking data.
method Edge Weight-Shared Graph Convolutional Network (EWS-GCN) combining graph and recurrent neural networks.
result EWS-GCN outperforms state-of-the-art models in credit scoring.
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…
As a new classification platform, deep learning has recently received increasing attention from researchers and has been successfully applied to many domains. In some domains, like bioinformatics and robotics, it is very difficult to construct a large-scale well-annotated dataset due to the expense of data acquisition …
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.
Transfer learning has received a lot of attention in the machine learning community over the last years, and several effective algorithms have been developed. However, relatively little is known about their theoretical properties, especially in the setting of lifelong learning, where the goal is to transfer information…
Recent years, transfer learning has attracted much attention in the community of machine learning. In this paper, we mainly focus on the tasks of parameter transfer under the framework of extreme learning machine (ELM). Unlike the existing parameter transfer approaches, which incorporate the source model information in…
Bayesian methods improve learning from related domains.
problem Finding optimal information to transfer between domains.
method Bayesian approaches to transfer learning.
result Bayesian methods outperform frequentist competitors in simulations.
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…
The recent advances in deep transfer learning reveal that adversarial learning can be embedded into deep networks to learn more transferable features to reduce the distribution discrepancy between two domains. Existing adversarial domain adaptation methods either learn a single domain discriminator to align the global …
Transfer learning improves MNI's performance in high-dimensional linear regression.
problem Improving model performance in high-dimensional linear regression with diverse data.
method Proposes a Transfer MNI approach, analyzing its excess risk and conditions for outperformance.
result Identifies free-lunch covariate shift regimes where knowledge transfer benefits.
This paper introduces a new transfer learning method for regression.
problem Boosting predictive power in scenarios with scarce data.
method Affine model transfer, following expected-square loss minimization.
result The affine model transfer method encompasses various existing methods and clarifies its theoretical properties.
Transfer learning has recently attracted significant research attention, as it simultaneously learns from different source domains, which have plenty of labeled data, and transfers the relevant knowledge to the target domain with limited labeled data to improve the prediction performance. We propose a Bayesian transfer…
Paper proposes a novel online transfer learning method to reduce domain discrepancy.
problem Online transfer learning with online distribution discrepancy minimization.
method The method seeks a new feature representation to simultaneously reduce marginal and conditional distribution discrepancies.
result The proposed method outperforms state-of-the-art methods in comprehensive experiments.
Fused Encoder Networks improve momentum strategies on crypto data.
problem Deploying momentum strategies on crypto data with limited samples leads to over-fitted models.
method Hybrid transfer learning model combining source and target datasets.
result Fused Encoder Networks outperform classical momentum strategies and benchmarks.
Zero-shot learning transfers knowledge from seen classes to novel unseen classes to reduce human labor of labelling data for building new classifiers. Much effort on zero-shot learning however has focused on the standard multi-class setting, the more challenging multi-label zero-shot problem has received limited attent…
This paper improves kernel-based regression using transfer learning.
problem Improving generalization performance in kernel-based regression.
method Two-step kernel-based estimator for known transferable sources and novel aggregation algorithm for unknown sources.
result Established statistical properties and validated effectiveness of proposed methods.
Modeling student behaviors and multiple predictions for early intervention.
problem Predicting student outcomes and interactions among multiple tasks.
method Proposes a variant of LSTM and soft-attention mechanism for heterogeneous behaviors, and co-attention mechanism for task interactions.
result Demonstrated effectiveness in predicting student outcomes and interactions.
New method automates asymmetric choice for better skill transfer in reinforcement learning.
problem Improving sample efficiency and transferability of reinforcement learning agents.
method Attentive Priors for Expressive and Transferable Skills (APES) using hierarchical KL-regularization.
result APES automates asymmetric choice, leading to better skill transfer across sequential tasks.
Time series prediction with deep learning methods, especially long short-term memory neural networks (LSTMs), have scored significant achievements in recent years. Despite the fact that the LSTMs can help to capture long-term dependencies, its ability to pay different degree of attention on sub-window feature within mu…
Proposes a method to improve multi-output Gaussian process for transfer learning.
problem Negative transfer and domain inconsistency in multi-output Gaussian process.
method Regularized MGP with convolution process and domain adaptation.
result Outperforms state-of-the-art benchmarks in simulation and real-world studies.
Typical reinforcement learning (RL) agents learn to complete tasks specified by reward functions tailored to their domain. As such, the policies they learn do not generalize even to similar domains. To address this issue, we develop a framework through which a deep RL agent learns to generalize policies from smaller, s…
Transfer learning improves HVAC fault detection with minimal labeled data.
problem Lack of labeled data for HVAC system faults.
method Bayesian classifier trained on large data, then transferred to new buildings with few normal operation samples.
result Few samples are sufficient to maintain classifier precision and recall.
This paper explores how the generalization of substitute classifiers affects the success of black-box adversarial attacks.
problem Understanding the factors driving the transferability of black-box adversarial examples.
method Max-min adversarial example game framework and theoretical generalization bounds.
result Substitute NN with better generalization behavior results in more transferable adversarial examples.
Unified framework for studying softmax attention under large prompts.
problem Challenges in theoretical analysis of softmax attention.
method Measure-based framework for finite and infinite prompts.
result Softmax attention converges to linear attention in the large-prompt regime.
Adapts Neyman-Pearson classification for both source and target distribution shifts.
problem Minimizing errors while controlling both Type-I and Type-II errors under distribution shifts.
method Derives an adaptive procedure that guarantees improved error rates and adapts to uninformative sources.
result Automatic adaptation to uninformative sources avoids negative transfer.
OTSeg uses multi-prompt Sinkhorn attention to improve zero-shot semantic segmentation.
problem Leveraging pre-trained CLIP knowledge to align text embeddings with pixel embeddings.
method OTSeg employs Multi-Prompts Sinkhorn (MPS) and Multi-Prompts Sinkhorn Attention (MPSA) to enhance semantic feature matching.
result OTSeg achieves state-of-the-art performance in zero-shot semantic segmentation tasks.
Paper proposes DAPNA to improve few-shot learning with domain adaptation.
problem Improving recognition of unseen classes with limited samples.
method Domain adaptation prototypical network with attention (DAPNA).
result DAPNA outperforms state-of-the-art FSL alternatives in experiments.
AReLU uses attention-based rectification to improve neural network performance.
problem Improving neural network performance through better activation functions.
method Integrates attention mechanism with rectified linear unit (ReLU) to learn and scale feature maps.
result AReLU significantly boosts performance of most network architectures with minimal changes.
Improved online AED models with multi-stage training and multi-task learning.
problem Enhance performance of online attention-based encoder-decoder models.
method Three-stage training with character encoder, BPE encoder, and attention decoder; multi-task learning at character and BPE levels; transfer learning from bidirectional encoder.
result 35% and 10% relative improvement over baselines for smaller and bigger models, respectively.
Recent efforts on training visual navigation agents conditioned on language using deep reinforcement learning have been successful in learning policies for different multimodal tasks, such as semantic goal navigation and embodied question answering. In this paper, we propose a multitask model capable of jointly learnin…
DDSTN improves breast cancer diagnosis by leveraging imbalanced ultrasound modalities.
problem Imbalanced ultrasound modalities in diagnosing breast cancer.
method Integrates LUPI and MMD into a deep transfer learning framework.
result Outperforms state-of-the-art algorithms in BUS-based CAD.
This paper proposes a new method to improve domain adaptation by distinguishing between marginal and dependence structure differences.
problem Existing domain adaptation methods fail to differentiate between marginal and dependence structure differences, leading to suboptimal transferability.
method The paper introduces a new approach that measures and optimizes the differences in internal dependence structure separately from marginals.
result The new method significantly improves transferability and robustness compared to existing benchmarks on real-world datasets.
Recurrent neural networks (RNNs), particularly long short-term memory (LSTM), have gained much attention in automatic speech recognition (ASR). Although some successful stories have been reported, training RNNs remains highly challenging, especially with limited training data. Recent research found that a well-trained …
Orion-Bix combines biaxial attention and meta-learning for tabular few-shot learning.
problem Scaling and generalizing tabular models with mixed numeric and categorical fields, weak feature structure, and limited labeled data.
method Orion-Bix uses biaxial attention and meta-learned in-context reasoning to efficiently capture local and global dependencies.
result Orion-Bix outperforms gradient-boosting baselines and state-of-the-art tabular models on public benchmarks.
We provide a benchmark dataset for hand gesture recognition using force myography.
problem Lack of publicly available benchmark data for force myography hand gesture recognition.
method Collected data from 20 persons covering 18 unique gestures using a commercially available sensor setup.
result Improved gesture recognition accuracy through transfer learning.
The study reveals how attention paths in Transformers influence learning outcomes.
problem Understanding the theoretical basis of Transformers' performance.
method Developed a statistical mechanics theory for a simplified attention network.
result The predictor statistics are influenced by the combination of attention paths.