Search Results for author:
Found 28 papers, 14 papers with code
A Unified and General Framework for Continual Learning
Extensive experiments on CL benchmarks and theoretical analysis demonstrate the effectiveness of the proposed refresh learning.
Few-Shot Class Incremental Learning with Attention-Aware Self-Adaptive Prompt
Few-Shot Class-Incremental Learning (FSCIL) models aim to incrementally learn new classes with scarce samples while preserving knowledge of old ones.
Representation Surgery for Multi-Task Model Merging
That is, there is a significant discrepancy in the representation distribution between the merged and individual models, resulting in poor performance of merged MTL.
Task-Distributionally Robust Data-Free Meta-Learning
TDS leads to a biased meta-learner because of the skewed task distribution towards newly generated tasks.
AdaMerging: Adaptive Model Merging for Multi-Task Learning
This approach aims to autonomously learn the coefficients for model merging, either in a task-wise or layer-wise manner, without relying on the original training data.
Continual Learning From a Stream of APIs
Next, we train the CL model by minimizing the gap between the responses of the CL model and the black-box API on synthetic data, to transfer the API's knowledge to the CL model.
Distributionally Robust Cross Subject EEG Decoding
In this work, we propose a principled approach to perform dynamic evolution on the data for improvement of decoding robustness.
A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning
Through this comprehensive survey, we aspire to uncover potential solutions by drawing upon ideas and approaches from various fields that have dealt with forgetting.
Learning to Learn from APIs: Black-Box Data-Free Meta-Learning
Data-free meta-learning (DFML) aims to enable efficient learning of new tasks by meta-learning from a collection of pre-trained models without access to the training data.
Customized Load Profiles Synthesis for Electricity Customers Based on Conditional Diffusion Models
In this paper, we propose a novel customized load profiles synthesis method based on conditional diffusion models for heterogeneous customers.
Architecture, Dataset and Model-Scale Agnostic Data-free Meta-Learning
The goal of data-free meta-learning is to learn useful prior knowledge from a collection of pre-trained models without accessing their training data.
Data Augmented Flatness-aware Gradient Projection for Continual Learning
In this paper, we first revisit the gradient projection method from the perspective of flatness of loss surface, and find that unflatness of the loss surface leads to catastrophic forgetting of the old tasks when the projection constraint is reduced to improve the performance of new tasks.
MetaMix: Towards Corruption-Robust Continual Learning With Temporally Self-Adaptive Data Transformation
To make them trustworthy and robust to corruptions deployed in safety-critical scenarios, we propose a meta-learning framework of self-adaptive data augmentation to tackle the corruption robustness in CL.
Meta-Learning with Less Forgetting on Large-Scale Non-Stationary Task Distributions
Two key challenges arise in this more realistic setting: (i) how to use unlabeled data in the presence of a large amount of unlabeled out-of-distribution (OOD) data; and (ii) how to prevent catastrophic forgetting on previously learned task distributions due to the task distribution shift.
Improving Task-free Continual Learning by Distributionally Robust Memory Evolution
To address these problems, for the first time, we propose a principled memory evolution framework to dynamically evolve the memory data distribution by making the memory buffer gradually harder to be memorized with distributionally robust optimization (DRO).
Space4HGNN: A Novel, Modularized and Reproducible Platform to Evaluate Heterogeneous Graph Neural Network
Heterogeneous Graph Neural Network (HGNN) has been successfully employed in various tasks, but we cannot accurately know the importance of different design dimensions of HGNNs due to diverse architectures and applied scenarios.
Learning To Learn and Remember Super Long Multi-Domain Task Sequence
We propose a domain shift detection technique to capture latent domain change and equip the meta optimizer with it to work in this setting.
Uncertainty Detection and Reduction in Neural Decoding of EEG Signals
In this work, we proposed an uncertainty estimation and reduction model (UNCER) to quantify and mitigate the uncertainty during the EEG decoding process.
Meta Learning on a Sequence of Imbalanced Domains with Difficulty Awareness
In this paper, we explore a more practical and challenging setting where task distribution changes over time with domain shift.
Meta-Learning with Neural Tangent Kernels
We achieve this goal by 1) replacing the adaptation with a fast-adaptive regularizer in the RKHS; and 2) solving the adaptation analytically based on the NTK theory.
Towards Learning to Remember in Meta Learning of Sequential Domains
However, a natural generalization to the sequential domain setting to avoid catastrophe forgetting has not been well investigated.
Meta-Learning in Reproducing Kernel Hilbert Space
Within this paradigm, we introduce two meta learning algorithms in RKHS, which no longer need an explicit inner-loop adaptation as in the MAML framework.
Repulsive Attention: Rethinking Multi-head Attention as Bayesian Inference
The neural attention mechanism plays an important role in many natural language processing applications.
A Multitask Deep Learning Approach for User Depression Detection on Sina Weibo
In recent years, due to the mental burden of depression, the number of people who endanger their lives has been increasing rapidly.
Towards Faithful Neural Table-to-Text Generation with Content-Matching Constraints
Text generation from a knowledge base aims to translate knowledge triples to natural language descriptions.
Bayesian Meta Sampling for Fast Uncertainty Adaptation
Specifically, we propose a Bayesian meta sampling framework consisting of two main components: a meta sampler and a sample adapter.
Learning Diverse Stochastic Human-Action Generators by Learning Smooth Latent Transitions
In this paper, we focus on skeleton-based action generation and propose to model smooth and diverse transitions on a latent space of action sequences with much lower dimensionality.
Ranked #4 on
Human action generation
on NTU RGB+D 2D
Location Augmentation for CNN
For example, a salient object is more likely to be closer to the center of the image, the sky in the top part of an image, etc.
