Research
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.

168,932 papers · 148 categories

Trend · papers per month

2.5%5.0%7.5%10.0% · Jun 202019922001200920172026
48 results for Meta Knowledge

MetaR learns few-shot link prediction in KGs by transferring relation-specific meta info.

problem Few-shot link prediction in KGs with limited associative triples.
method MetaR framework focusing on transferring relation-specific meta information.
result MetaR achieves state-of-the-art results on few-shot link prediction benchmarks.

Bayesian TAML balances meta-knowledge and task-specific learning for imbalanced tasks.

problem Meta-learning approaches struggle with varying instance and class numbers and distributional differences.
method Bayesian inference framework with variational inference to adaptively balance meta-knowledge and task-specific learning.
result Bayesian TAML significantly outperforms existing meta-learning approaches on imbalanced datasets.

In this thesis, we study the problem of feature learning on heterogeneous knowledge graphs. These features can be used to perform tasks such as link prediction, classification and clustering on graphs. Knowledge graphs provide rich semantics encoded in the edge and node types. Meta-paths consist of these types and abst…

2018-09-07abs ↗pdf ↗

When fitting Bayesian machine learning models on scarce data, the main challenge is to obtain suitable prior knowledge and encode it into the model. Recent advances in meta-learning offer powerful methods for extracting such prior knowledge from data acquired in related tasks. When it comes to meta-learning in Gaussian…

2019-01-23abs ↗pdf ↗

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

problem Improving performance in small-data real-world problems with heterogeneous architectures and tasks.
method Meta-learning to automatically learn what knowledge to transfer and where in the target network.
result Meta-transfer approach significantly outperforms hand-crafted methods on various datasets and network architectures.

The paper proposes new strategies to exploit relationships between meta-tasks for better few-shot learning.

problem Few-shot learning struggles with domain gaps and poorly sampled data.
method Proposes exploiting relationships between meta-tasks to improve robustness and performance.
result Developed new learning objectives (MDA and MKD) to address domain gaps and improve robustness.

Meta-GNN tackles few-shot node classification in graphs.

problem Few-shot learning in graph meta-learning.
method Meta-GNN learns prior knowledge from many similar few-shot learning tasks and applies it to new classes with few labeled samples.
result Meta-GNN improves node classification performance significantly on few-shot learning problems.

HARMLESS meta-learning method models short event sequences with relational information.

problem Learning heterogeneous point process models from short event sequence data.
method Hierarchical Bayesian mixture Hawkes process model with stochastic variational meta expectation maximization.
result HARMLESS outperforms existing methods in predicting future events.

Meta-learning approach improves object detection on new classes.

problem Deterioration of object detection performance on old classes in incremental settings.
method Meta-learning to reshape model gradients for optimal task adaptation.
result Meta-learning approach outperforms state-of-the-art methods in incremental object detection.

In meta-learning an agent extracts knowledge from observed tasks, aiming to facilitate learning of novel future tasks. Under the assumption that future tasks are 'related' to previous tasks, the accumulated knowledge should be learned in a way which captures the common structure across learned tasks, while allowing the…

2017-11-03abs ↗pdf ↗

A new method improves EEG classification across subjects efficiently.

problem Challenges in adapting and retaining knowledge for EEG classifiers across different subjects.
method Meta UPdate Strategy (MUPS-EEG) for continuous EEG classification.
result Outperforms current state-of-the-art methods in adapting to new subjects and retaining knowledge of learned subjects.

Framework uses physics knowledge to improve spatiotemporal prediction with limited data.

problem Challenges in modeling physical systems with limited real-world data.
method Physics-aware meta-learning with auxiliary tasks, incorporating PDE-independent spatial and temporal modules.
result Framework outperforms in spatiotemporal prediction tasks with limited data.

Develops HMRL for sparse reward RL problems, improving meta policy efficiency and transferability.

problem Difficulty in learning meta policies for sparse reward RL problems.
method Hyper-Meta RL framework with cross-environment meta state embedding and shaped meta reward.
result Improves meta policy generalization and efficiency for sparse reward RL problems.

SeqFOMAML uses meta-learning to prevent forgetting across tasks.

problem Catastrophic forgetting in neural networks when learning multiple tasks sequentially.
method Meta-learning approach exposing neural network to multiple tasks sequentially.
result SeqFOMAML reduces catastrophic forgetting in sequential learning problems.

The paper provides fast, sample-efficient algorithms for learning common features in multi-task linear regression.

problem Learning transferable features from multiple related tasks.
method Provably fast, sample-efficient algorithms for multi-task linear regression.
result Theoretical guarantees on sample complexity for learning common features.

Meta-learning reduces training overhead for communication systems.

problem Inefficiency in machine learning due to frequent retraining when system configuration changes.
method Meta-learning selects a suitable inductive bias from related tasks, reducing training data and time requirements.
result Meta-learning can reduce training overhead for communication systems.

A method learns matrix factorization from diverse matrices and applies the knowledge to unseen matrices.

problem Matrix factorization without shared rows or columns.
method Neural network meta-learned to minimize expected imputation error using MAP estimation.
result The method can impute missing values from unseen matrices efficiently.

MetaCL enables neural networks to learn from small data streams without forgetting.

problem Learning from limited data and adapting to new concepts over time.
method MetaCL trains a model to exploit intrinsic data features and dynamically penalize model parameter changes.
result MetaCL achieves state-of-the-art performance on image classification benchmarks.

A new method trains a smaller model from a larger one without needing the actual training data.

problem Training a smaller model from a larger one without access to the training data.
method Synthesizes data impressions from the Teacher model to train the Student model.
result Zero-Shot Knowledge Distillation achieves competitive generalization performance.

MetaTNE tackles few-shot novel labels in graphs, improving node classification.

problem Node classification on graphs with novel labels and limited training data.
method MetaTNE framework with structural, meta-learning, and optimization modules.
result MetaTNE significantly improves node classification over state-of-the-art methods.

New algorithm for online meta-learning with task boundary detection.

problem Adapting to new tasks in a non-stationary environment.
method Two detection mechanisms for task switches and distribution shift; online model updates based on current data.
result Achieves sublinear task-averaged regret under mild conditions.

Paper tackles robustness in adversarial noise with a meta-optimizer.

problem Sensitivity to adversarial noise hinders machine learning deployment.
method Meta-optimizer learns to robustly optimize models using adversarial examples.
result Meta-optimizer transfers adversarial knowledge to new models without generating new examples.

Study on selecting between base algorithms in stochastic bandit problems.

problem Model selection in stochastic environments with contextual information.
method Developed a meta-algorithm-base algorithm abstraction with a smoothing transformation for optimal O(T)O(\sqrt{T}) guarantees.
result Optimal O(T)O(\sqrt{T}) model selection guarantees for stochastic contextual bandit problems.

A new system recommends specific knowledge concepts in MOOCs based on student interests.

problem MOOCs recommend courses but ignore specific knowledge concepts interests.
method End-to-end graph neural network (ACKRec) that combines content and context information.
result ACKRec effectively recommends knowledge concepts to MOOC students.

Meta-learning improves few-shot learning by propagating knowledge across related classes on a graph.

problem Few-shot learning suffers from insufficient training data.
method Developed a Gated Propagation Network (GPN) that learns to propagate messages between prototypes of different classes on a graph.
result GPN outperforms recent meta-learning methods on benchmark datasets.

Fully automating machine learning pipelines is one of the key challenges of current artificial intelligence research, since practical machine learning often requires costly and time-consuming human-powered processes such as model design, algorithm development, and hyperparameter tuning. In this paper, we verify that au…

2018-06-11abs ↗pdf ↗

Neural networks have been successfully applied in applications with a large amount of labeled data. However, the task of rapid generalization on new concepts with small training data while preserving performances on previously learned ones still presents a significant challenge to neural network models. In this work, w…

2017-03-02abs ↗pdf ↗

CosML combines domain-specific meta-learners for cross-domain few-shot classification.

problem Generalizing to unseen domains while meta-learning on multiple seen domains.
method CosML trains domain-specific meta-learners and combines their meta-parameters in the parameter space.
result CosML outperforms state-of-the-art methods and achieves strong cross-domain generalization.

MARS meta-learns function scores for improved predictive accuracy and uncertainty.

problem Difficulty in specifying expressive priors for Bayesian meta-learning.
method Meta-learning the score function of data-generating process marginals in the function space.
result State-of-the-art predictive accuracy and improved uncertainty estimates.

Paper extends meta-learning framework to non-convex settings with improved performance.

problem Learning from past tasks for faster future tasks in a sequential setting.
method Generalized online meta-learning framework to non-convex settings, introduced local regret as performance measure.
result The framework achieves logarithmic local regret and robustness to hyperparameter initialization.