Recent variants improve knowledge distillation performance.
problem Improving the performance of knowledge distillation.
method Introducing additional components or changing the learning process.
result These variants have shown promising results.
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.
168,742 papers · 148 categories
Trend · papers per month
48 results for “knowledge improvement”
Interactive Elicitation of Knowledge on Feature Relevance Improves Predictions in Small Data Setscs.AI
Providing accurate predictions is challenging for machine learning algorithms when the number of features is larger than the number of samples in the data. Prior knowledge can improve machine learning models by indicating relevant variables and parameter values. Yet, this prior knowledge is often tacit and only availab…
Semantic TrueLearn uses semantic graphs to improve educational recommendation systems.
problem Challenges in handling semantic and hierarchical structure in knowledge areas.
method Introduces a novel learner model that exploits semantic relatedness between knowledge components using a Wikipedia link graph.
result Achieves statistically significant improvements in predictive performance for educational engagement.
Centuries of development in natural sciences and mathematical modeling provide valuable domain expert knowledge that has yet to be explored for the development of machine learning models. When modeling complex physical systems, both domain knowledge and data provide necessary information about the system. In this paper…
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.
Machine learning refactors knowledge to improve learning efficiency.
problem Inductive program synthesis efficiency through knowledge restructuring.
method Introduces Knorf, a system that refactors knowledge bases using constraint optimization.
result Learning from refactored knowledge improves predictive accuracy fourfold and reduces learning time by half.
DMLreg uses expert knowledge to improve model performance in high-dimensional settings.
problem Improving model performance in high-dimensional prediction problems.
method Learning a Mahalanobis distance metric from expert comparisons and integrating it into a regularized linear model.
result DMLreg leads to improvements in model performance when expert knowledge is relevant.
This paper improves ASR performance by aligning frames more accurately.
problem Disagreement between teacher-student models in frame-level alignment.
method Introduces self-knowledge distillation (SKD) to guide frame-level alignment.
result Improves both resource efficiency and performance in ASR.
This paper enhances language models with knowledge awareness.
problem Understanding how much knowledge pretrained language models grasp.
method Inserting explicit knowledge layers into pretraining without changing transformer architecture.
result Significantly more knowledge packed into transformer parameters.
This paper integrates LLMs into SCD to improve causal inference accuracy.
problem Challenges in acquiring domain expert knowledge for causal models.
method Statistical causal prompting (SCP) for LLMs and prior knowledge augmentation for SCD.
result LLM-KBCI and SCD augmented with LLM-KBCI approach ground truths more closely.
Extracurricular learning closes the accuracy gap in knowledge distillation.
problem Accuracy gap between teacher and student models after knowledge distillation.
method Modeling student and teacher output distributions, sampling from an extended data distribution, and matching over this set.
result Extracurricular learning reduces the accuracy gap by 46% to 68%.
Improved knowledge gradient (iKG) outperforms the original KG algorithm in best arm identification problems.
problem Best arm identification (BAI) problem with limitations of the original KG algorithm.
method Follows the one-step look ahead of KG but chooses the measurement that maximizes the probability of selecting the best arm.
result Improved knowledge gradient (iKG) is asymptotically optimal and easier to extend to variant BAI problems.
Knowledge distillation boosts simple models in banking without complexity.
problem Complexity and performance constraints in banking models.
method Soft Targets, Sample Selection, Data Augmentation.
result Improved model performance without altering model simplicity.
Path queries on a knowledge graph can be used to answer compositional questions such as "What languages are spoken by people living in Lisbon?". However, knowledge graphs often have missing facts (edges) which disrupts path queries. Recent models for knowledge base completion impute missing facts by embedding knowledge…
Proposes LsrKD and MrKD to improve neural network training performance.
problem Improving neural network training performance, especially on deep networks.
method Extends Label Smoothing Regularization with Self-Knowledge Distillation, introducing LsrKD and MrKD.
result LsrKD and MrKD significantly improve training performance on deep neural networks.
Improves algorithmic recourse to guide towards both acceptance and improvement.
problem Algorithmic recourse recommendations may not lead to improvement.
method Improvement-Focused Causal Recourse (ICR) requires recommendations to guide towards improvement and leverages causal knowledge to design accurate decision systems.
result ICR guides towards both acceptance and improvement given correct causal knowledge.
Survey of integrating domain knowledge into DL models.
problem Improving DL model performance with limited data or complex functions.
method Five categories of approaches to inject domain knowledge into DL models.
result Survey identifies five main categories of approaches.
This paper shows how integrating domain knowledge improves ML models for transprecision computing.
problem Improving ML models for transprecision computing with scarce or complex data.
method Injecting domain knowledge into neural networks through additional features, graph-based topology, and regularization schemes.
result ML models with domain knowledge outperform purely data-driven models by around 38%.
Improves model accuracy for neural nets in stochastic dynamics with partial prior knowledge.
problem Stability and accuracy in neural nets modeling stochastic dynamics with many parameters.
method Three steps: probabilistic weights, partial knowledge incorporation, and PAC-Bayesian training.
result Improved model fit with partial and noisy prior knowledge.
The paper improves Gaussian processes by adding sum constraints, enhancing prediction accuracy.
problem Improving Gaussian process predictions with background knowledge constraints.
method Conditioning the prior distribution on sum constraints to ensure fulfillment of linear and nonlinear constraints.
result The approach fulfills constraints with high precision and improves prediction accuracy.
KT models improved slightly with synthetic student data.
problem Limited access to real student data and lack of diversity in public datasets.
method Simulated student data using three statistical strategies and tested on KT baselines.
result Synthetic data can lead to similar performance as real data.
Knowledge distillation improves model accuracy by mimicking teacher model probabilities.
problem Improving model accuracy through model compression.
method Casting knowledge distillation as a semiparametric inference problem, deriving new guarantees, and developing enhancements.
result Enhancements improve student performance by mitigating teacher overfitting and underfitting.
AlphaZero reveals new chess concepts learnable by top experts.
problem Extracting and understanding hidden knowledge from AI systems.
method Proposed method to extract new chess concepts from AlphaZero.
result Top chess grandmasters show improvements in learning new concepts.
SLED improves factuality in LLMs without external knowledge.
problem Unreliable or factually incorrect outputs from large language models.
method Contrasts final layer logits with early layers' logits, uses approximate gradient to refine outputs.
result Consistently improves factual accuracy over existing methods.
b-LOAD extends local causal discovery with prior knowledge, improving causal effect estimation.
problem Local causal discovery struggles in data-scarce settings due to uncertainty and incomplete neighborhoods.
method b-LOAD incorporates prior knowledge directly into local structure learning, using Meek's rules to refine discovery.
result b-LOAD refines the admissible equivalence class and enlarges identifiable causal queries, improving causal effect estimation.
Many recent works on knowledge distillation have provided ways to transfer the knowledge of a trained network for improving the learning process of a new one, but finding a good technique for knowledge distillation is still an open problem. In this paper, we provide a new perspective based on a decision boundary, which…
Role-wise data augmentation improves knowledge distillation effectiveness.
problem Existing knowledge distillation methods fail to utilize the full potential of teacher-student data interaction.
method Design and implement data augmentation agents with distinct roles for teacher and student.
result Specially tailored data points enhance the demonstration of teacher's knowledge to the student.
Improving Network Threat Detection by Knowledge Graph, Large Language Model, and Imbalanced Learningcs.LG
Enhanced network threat detection using KG, LLM, and imbalanced learning.
problem Challenges in network threat detection due to complex attack patterns and limited historical data.
method Integrated framework combining Knowledge Graph, Imbalanced Learning, and Large Language Model.
result Improved threat capture rate by 3%-4% and increased interpretability of risk predictions.
Knowledge-Driven Modulation of Neural Networks with Attention Mechanism for Next Activity Predictioncs.AI
The paper improves neural network predictions by integrating process knowledge.
problem Improving neural network predictions for process execution data.
method Integrates background process knowledge into neural networks with attention mechanisms.
result Improves prediction accuracy for process execution data.
Exploiting the appropriate inductive bias based on the knowledge of data is essential for achieving good performance in statistical machine learning. In practice, however, the domain knowledge of interest often provides information on the relationship of data attributes only distantly, which hinders direct utilization …
Framework evaluates the impact of prior knowledge in deep learning models.
problem Mitigating data-driven model shortcomings like data dependence and generalization ability.
method Model-agnostic framework inspired by interpretable machine learning, assessing data volume and estimation range effects.
result Complex relationship between data and knowledge, including dependence, synergistic, and substitution effects.
Improves transparency and incorporates prior knowledge in Gaussian Process models.
problem Challenges in understanding and expressing prior assumptions in complex Bayesian models.
method Introduces self-explaining variational posterior distributions for Gaussian Processes.
result Allows incorporation of both general and feature-specific prior knowledge.
Framework adds human knowledge to AI decisions to improve outcomes.
problem Conflict between AI recommendations and human insights.
method Develops a framework for integrating human knowledge as a guardrail for AI decisions.
result Human knowledge can improve AI decisions, especially in specific pitfalls.
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.
New research suggests privileged information doesn't improve model performance.
problem Challenges in transferring knowledge using privileged information in machine learning.
method Critical examination of existing theoretical and empirical analyses of LUPI methods.
result LUPI methods often fail to effectively transfer knowledge from privileged information.
Link prediction in large knowledge graphs has received a lot of attention recently because of its importance for inferring missing relations and for completing and improving noisily extracted knowledge graphs. Over the years a number of machine learning researchers have presented various models for predicting the prese…
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.
Recent research in psycholinguistics has provided increasing evidence that humans predict upcoming content. Prediction also affects perception and might be a key to robustness in human language processing. In this paper, we investigate the factors that affect human prediction by building a computational model that can …
Prediction in a small-sized sample with a large number of covariates, the "small n, large p" problem, is challenging. This setting is encountered in multiple applications, such as precision medicine, where obtaining additional samples can be extremely costly or even impossible, and extensive research effort has recentl…
Enhances knowledge graph completion with mixed geometry tensor factorization.
problem Capturing nuanced distributional properties in knowledge graphs.
method Combines Euclidean and hyperbolic geometries for tensor factorization.
result Improves link prediction accuracy with fewer parameters.
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 -Iteration algorithm for estimating optimal action-state function .
result Significantly improved final learning error of function.
Paper characterizes and represents pairwise causal background knowledge for improved causal inference.
problem Improving causal inference by handling pairwise causal constraints.
method Graphical characterization, direct causal clause (DCC), unified representation, MPDAG, polynomial-time algorithms.
result Pairwise causal background knowledge uniquely decomposes into MPDAG and DCCs, improving causal effect identification.
Distilled models often fail to match teacher models, despite improving generalization.
problem The discrepancy between teacher and student predictive distributions remains large.
method Investigated the optimization difficulties and dataset details affecting student performance.
result Optimizing for matching the teacher does not always lead to better generalization.
We present a family of novel methods for embedding knowledge graphs into real-valued tensors. These tensor-based embeddings capture the ordered relations that are typical in the knowledge graphs represented by semantic web languages like RDF. Unlike many previous models, our methods can easily use prior background know…
Study on ensemble, distillation, and self-distillation in deep learning models.
problem Improving test accuracy in deep learning models using ensemble and distillation methods.
method Formal study of ensemble and distillation, considering multi-view data structure.
result Proven that ensemble and distillation can improve test accuracy in deep learning models, and the superior performance can be distilled into a single model.
Cluster-DAGs improve causal discovery with prior knowledge.
problem Finding cause-effect relationships from high-dimensional data.
method Cluster-DAGs as prior knowledge framework, modified constraint-based algorithms Cluster-PC and Cluster-FCI.
result Cluster-PC and Cluster-FCI outperform baselines without prior knowledge.
Enhances model compression with multi-teacher knowledge distillation.
problem Uncertainty evaluation and diverse teacher expertise in model deployment.
method Bayesian inference and teacher-informed prior with entropy-based weighting.
result Improved predictive accuracy and robust uncertainty quantification.
Proposes ConiVAT for better cluster assessment and clustering with background knowledge.
problem Challenges in cluster assessment and clustering with noise and bridge points.
method Uses background constraints to improve VAT/iVAT for complex datasets.
result Improves clustering accuracy and resolves issues with noise and bridge points.