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

4.1%8.1%12.2%16.2% · May 202619922001200920172026
48 results for knowledge levels

Paper presents a robust transfer learning method for active level set estimation.

problem Efficiently identifying regions of a black-box function with limited function evaluations.
method Incorporates prior knowledge from a related function while locally adapting it.
result The method achieves better convergence of level sets compared to standard transfer learning.

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.

CSEAL uses cognitive structure to personalize learning paths.

problem Personalized learning paths based on learners' evolving knowledge levels and item structures.
method CSEAL integrates knowledge levels and item structures using a Markov Decision Process and actor-critic algorithm.
result CSEAL effectively personalizes learning paths, improving learning outcomes.

OKDDip uses diverse peers to improve online knowledge distillation.

problem Early saturation in group-based distillation.
method Two-level distillation with multiple auxiliary peers and a group leader, using attention-based aggregation weights.
result OKDDip consistently gives better performance than state-of-the-art approaches.

HAKE embeds entities in polar coordinates to model semantic hierarchies in knowledge graphs.

problem Lack of modeling semantic hierarchies in knowledge graph embeddings.
method HAKE embeds entities in a polar coordinate system, where the radial coordinate represents hierarchy levels and the angular coordinate distinguishes entities at the same level.
result HAKE significantly outperforms existing methods on link prediction tasks in knowledge graphs.

Online news recommender systems aim to address the information explosion of news and make personalized recommendation for users. In general, news language is highly condensed, full of knowledge entities and common sense. However, existing methods are unaware of such external knowledge and cannot fully discover latent k…

2018-01-25abs ↗pdf ↗

The paper characterizes the efficiency of transferring knowledge from a teacher to a student classifier over finite domains.

problem Characterizing the statistical efficiency of knowledge transfer over finite domains.
method Three progressive levels of privileged information: hard labels, teacher probabilities, and soft labels. Novel empirical loss functions used to achieve the fundamental limits.
result Achieving the fundamental limits of knowledge transfer through specific levels of privileged information and novel loss functions.

This study improves knowledge distillation for RNN-T models with noisy labels.

problem Challenges in distilling knowledge from RNN-T models with variable quality teachers.
method Full-sum distillation and sequence-level knowledge distillation.
result Full-sum distillation outperforms other methods for RNN-T models, especially for bad teachers.

Few-shot learning is a technique to learn a model with a very small amount of labeled training data by transferring knowledge from relevant tasks. In this paper, we propose a few-shot learning method for wearable sensor based human activity recognition, a technique that seeks high-level human activity knowledge from lo…

2019-03-25abs ↗pdf ↗

Symbolic knowledge in neural models can inadvertently make them more vulnerable to adversarial attacks.

problem Symbolic knowledge in neural models can make models more susceptible to adversarial attacks.
method Investigated deep probabilistic graphical models that incorporate symbolic knowledge and neural nets.
result Symbolic knowledge can propagate the negative effects of adversarial examples, making models more vulnerable.

A new personality-based recommender system tackles data sparsity without feedback.

problem Data sparsity without common feedback among users.
method Implicitly identifying users' personality type and incorporating it with personal interests and knowledge level.
result The model's effectiveness, especially in data sparsity situations, demonstrated on a real-world dataset.

Improved sentiment analysis in Korean finance using masked PLMs.

problem Fine-grained sentiment analysis in non-English finance literature is lacking due to limited annotated data.
method Developed KorFinASC dataset and applied TGT-Masking to PLMs to remove non-stationary knowledge.
result Improved classification accuracy by 22.63% on KorFinASC.

ZSL-KG learns class representations from common sense knowledge graphs.

problem Predicting classes without labeled examples using semantic class representations.
method TrGCN, a novel transformer graph convolutional network, embeds nodes from common sense knowledge graphs in a vector space.
result ZSL-KG improves over existing methods on five out of six zero-shot benchmark datasets.

Paper proposes a method to generate instance labels from weakly supervised data.

problem Weakly supervised instance labeling in medical image analysis.
method Uses multiple instance learning (MIL) and knowledge distillation to generate instance-level predictions.
result Significantly outperforms state-of-the-art MIL methods in instance-level prediction.

RID framework quantifies and regularizes task-relevant knowledge in distillation.

problem Distilling irrelevant information can hinder student model performance.
method Partial Information Decomposition to quantify and regularize task-relevant knowledge.
result RID framework leads to more resilient distillation under nuisance teachers.

ProbKT uses probabilistic logical reasoning to train object detection models with weak supervision.

problem Training object detection models requires instance-level annotations, which are often unavailable.
method ProbKT, a framework based on probabilistic logical reasoning, uses arbitrary types of weak supervision.
result ProbKT leads to significant improvement and better generalization compared to existing baselines.

Incorporation of a new knowledge into neural networks with simultaneous preservation of the previous one is known to be a nontrivial problem. This problem becomes even more complex when new knowledge is contained not in new training examples, but inside the parameters (connection weights) of another neural network. Her…

2018-09-25abs ↗pdf ↗

Study reveals similarities in knowledge flows between pharmaceutical and AI industries.

problem Understanding the dynamics of drug pipelines in global pharmaceutical industry.
method Multilayer network analysis of drug pipeline, global supply chain, and ownership data.
result Proven similarities in knowledge flows between pharmaceutical and AI industries.

This paper improves understanding of knowledge distillation and its effects.

problem Improving model quality with a fixed capacity budget.
method Categorizing teacher's knowledge into three levels and studying their effects on distillation.
result The three hierarchical levels of teacher's knowledge (universe, domain, instance) significantly impact knowledge distillation.

Bayesian Dark Knowledge fails to perform well with high posterior uncertainty.

problem Performance degradation of Bayesian Dark Knowledge with high posterior uncertainty.
method Compresses posterior predictive distribution into a single network, using a student network matching the teacher ensemble architecture.
result Using a matching student network architecture does not guarantee acceptable performance with high posterior uncertainty.

CLEAS improves neural architecture search for continual learning.

problem Overcoming catastrophic forgetting and adapting to new tasks while controlling model complexity.
method Neural architecture search (NAS) with reinforcement learning to find optimal neural architecture.
result CLEAS achieves higher classification accuracy with simpler neural architectures.

Bayesian model transfers knowledge across different engineering fleets.

problem Data sparsity in predictive models for engineering infrastructure.
method Hierarchical Bayesian approach with multitask learning.
result Improves survival analysis and power prediction in truck fleets and wind farms.

Previous transfer learning methods based on deep network assume the knowledge should be transferred between the same hidden layers of the source domain and the target domains. This assumption doesn't always hold true, especially when the data from the two domains are heterogeneous with different resolutions. In such ca…

2018-09-23abs ↗pdf ↗

The paper improves NLI models' robustness by adding external knowledge to the attention mechanism.

problem NLI models' performance drops significantly on simple adversarial examples.
method Proposes a method to enhance NLI models' robustness by incorporating external knowledge into the attention mechanism.
result The method significantly improves the robustness of NLI models, achieving human-level performance on adversarial data.