A finance approach values knowledge, emphasizing the importance of noticing new information.
problem The valuation of knowledge to ensure better training and awareness of new information.
method Formulated a methodology using finance principles, providing axioms and models.
result First attempt to numerically value knowledge, emphasizing the importance of noticing new information.
B-CP reduces knowledge graph model size by replacing real-valued embeddings with binary values.
problem Storage inefficiency in vector embeddings for large knowledge graphs.
method Binarized CANDECOMP/PARAFAC (B-CP) decomposition algorithm.
result B-CP reduces model size by more than an order of magnitude while maintaining task performance.
The paper models crowdlearning dynamics and user expertise evolution.
problem Understanding the evolution of user expertise in crowdlearning platforms.
method Probabilistic modeling framework and scalable estimation method.
result High-value knowledge is rare, and user proficiency varies.
Paper extends knowledge tracing algorithms to infer student knowledge and predict posttest performance.
problem Lack of algorithms that directly infer student knowledge and predict posttest performance.
method Extended DKT and DKVMN to infer knowledge, and applied to BKT and PFA for comparison.
result Knowledge estimates from the extended algorithms correlate better with posttest performance than existing methods.
Improved knowledge transfer from teacher to student DNNs using SVD.
problem Limited knowledge transfer and high computational cost in T-S DNNs.
method Self-supervised knowledge distillation using singular value decomposition.
result S-DNN achieves up to 1.1% better classification accuracy than T-DNN with 1/5 computational cost.
Quaternion embeddings model entities and relations in knowledge graphs.
problem Modeling latent inter-dependencies and expressive rotations in knowledge graphs.
method Quaternion-valued embeddings and rotations in hypercomplex space.
result Quaternion embeddings achieve state-of-the-art performance on knowledge graph benchmarks.
Shapley values explain financial language models, aligning with domain knowledge.
problem Lack of explainability in financial applications of large language models.
method Shapley value analysis for financial textual data.
result Shapley values provide consistent explanations with financial reasoning.
The paper explores the concept of predictive knowledge in reinforcement learning.
problem The relationship between predictions and knowledge in reinforcement learning is underdeveloped.
method The paper discusses the relationship between predictive knowledge learning methods and epistemic notions of justification and truth.
result The paper suggests the need for formalizing predictive knowledge in reinforcement learning.
A novel geometric algebra-based KG embedding framework improves link prediction.
problem KG embedding to model entities and relations in a low-dimensional space.
method Utilizes multivector representations and geometric product in geometric algebra.
result Outperforms state-of-the-art models in link prediction experiments.
Deep-IRT combines deep learning and IRT for explainable knowledge tracing.
problem Lack of explainability in deep learning-based knowledge tracing models.
method Synthesis of DKVMN and IRT models to estimate student and item parameters.
result Deep-IRT retains DKVMN performance while providing psychological interpretations.
MKBE embeds multimodal data for knowledge base completion.
problem Missing multimodal data in knowledge bases.
method Multimodal encoders and decoders for text, images, and numerical values.
result State-of-the-art link prediction with 5-7% improvement.
A new method for faster learning in reinforcement learning.
problem Learning from multiple tasks with different goals.
method Universal Successor Representations (USR) and USR Approximator (USRA).
result Agents initialized with USRA trained on USR can achieve goals faster than random initialization.
Paper presents a method to extract and interpret knowledge from a spiking neural classifier.
problem Extracting and interpreting knowledge from a spiking neural classifier with time-varying synaptic weights.
method The method involves encoding real-valued input data into spike patterns, training the classifier, and mapping the weighted postsynaptic potential to feature strength functions (FSFs).
result The FSFs represent the extracted knowledge from the classifier and can be used for classification and interpretation.
Improves slot key and value prediction for unseen entities.
problem Dealing with unseen slot keys and values in real-world dialogue systems.
method Leverages external knowledge bases to project slots into an attribute space and generate candidate keys and values.
result Significant improvements in F1 score and accuracy (57.7% and 82.7%, respectively) over a previous approach.
Study evaluates margin parameter effects on knowledge embedding quality.
problem Understanding margin parameter's impact on embedding quality.
method Examined margin parameter values for multi-relational categorized data.
result Lower margin values are insufficient, while larger values cause noise.
SAKT improves knowledge tracing by focusing on relevant past activities.
problem Handling sparse data in knowledge tracing models.
method Self-attention based approach to identify relevant past activities.
result SAKT outperforms state-of-the-art models, improving AUC by 4.43%.
SKVMN improves KT models by tracing student knowledge states and dependencies.
problem Tackling limitations of existing KT models in deep learning.
method Proposes SKVMN, a deep learning model unifying recurrent and memory capacities.
result Significantly outperforms state-of-the-art KT models on multiple datasets.
Automates subgroup discovery for real-valued targets using prior knowledge.
problem Finding meaningful patterns in high-dimensional, real-valued data.
method Subjective Interestingness framework FORSIED for efficient subgroup discovery.
result Automatically discovers informative subgroups in data for real-valued targets.
Paper proposes a new approach to unify and compare knowledge graph embedding methods.
problem Lack of understanding and comparison of existing knowledge graph embedding methods.
method Introduces a multi-embedding interaction mechanism to unify and generalize existing models.
result Proposes a new multi-embedding model based on quaternion algebra.
New insights on Shapley value precision for tabular data predictions.
problem Precision of Shapley value explanations for individual observations.
method Conditional Shapley value estimation methods for tabular data.
result Shapley value explanations are less precise for outer observations.
Paper proposes a method to transfer knowledge by distilling activation boundaries in neural networks.
problem Lack of consideration of activation boundaries in knowledge transfer methods.
method Proposes a knowledge transfer method via distillation of activation boundaries formed by hidden neurons, using an activation transfer loss.
result The proposed method outperforms state-of-the-art knowledge transfer methods in various experiments.
Improves dialogue state tracking across multiple domains.
problem Incomplete domain ontology limits DST models' adaptability.
method Model DST as Q&A, using evolving knowledge graph.
result 5.80% and 12.21% relative improvement on datasets.
Paper tackles robust knowledge transfer in parallel RL tasks.
problem Transfer knowledge from low-tier to high-tier tasks in parallel RL without shared dynamics or reward functions.
method Identifies Optimal Value Dominance condition and proposes online learning algorithms for both tasks.
result Achieves constant regret on partial states and near-optimal regret when tasks are dissimilar.
New method for RL tasks transfer using Lipschitz continuity.
problem Knowledge transfer in RL tasks over time.
method Established Lipschitz continuity between MDPs and applied it to RL.
result Improved convergence rate and no negative transfer with high probability.
Tensor-based embeddings improve knowledge graph fact prediction.
problem Predicting new facts in knowledge graphs.
method Knowledge-Enriched Tensor Factorization
result 5% to 50% relative improvement over state-of-the-art techniques.
Complex tensor factorization improves knowledge graph completion.
problem Automatically understanding and predicting missing relationships in large knowledge graphs.
method Use of complex-valued embeddings and unitary diagonalization.
result Complex embeddings lead to scalable and expressive models that outperform existing methods.
LLMs can memorize economic data and recall exact values before their training cutoff.
problem Evaluating the trustworthiness of LLMs' economic forecasts during their training period.
method Demonstrated through counterfactual forecasting and analysis of LLMs' recall ability.
result LLMs have memorized economic and financial data, leading to recall-level accuracy before their knowledge cutoff.
The goal of imitation learning is for an apprentice to learn how to behave in a stochastic environment by observing a mentor demonstrating the correct behavior. Accurate prior knowledge about the correct behavior can reduce the need for demonstrations from the mentor. We present a novel approach to encoding prior knowl…
Enhances neural networks with prior function values to improve accuracy.
problem Improving neural network accuracy in regions without training data.
method Develops a probabilistic approach to augment BNNs with prior function values.
result Predictions rely more on prior information in uncertain regions.
TXtract extracts structured knowledge from thousands of product categories.
problem Extracting structured knowledge from diverse product categories in e-commerce.
method TXtract uses a taxonomy-aware model with category conditional self-attention and multi-task learning.
result TXtract outperforms state-of-the-art approaches by up to 10% in F1 and 15% in coverage across all categories.
This paper systematizes knowledge on synthetic assets in crypto.
problem Disparate academic literature on synthetic assets in crypto.
method Broad perspective, general framework, data-driven analyses.
result Highlights risks and areas of research interest in synthetic assets.
Graph neural networks integrate causal knowledge for more accurate uplift modeling.
problem Identifying the most effective treatments and clients for marketing interventions.
method Combining graph neural networks with causal knowledge to estimate uplift values.
result The proposed method outperforms traditional approaches in predicting uplift values with minimal errors.
Interactive tool improves prediction accuracy in small datasets.
problem Challenges in machine learning with small data sets and tacit expert knowledge.
method Interactive visualization and user model to elicit feature relevance.
result User model significantly improves prediction accuracy and prior knowledge elicitation.
New MARL method combines agent knowledge to reduce complexity.
problem Curse of dimensionality in multiagent reinforcement learning.
method Decomposes multiagent problem into multi-task problem, uses distillation and value-matching.
result Outperforms policy distillation alone and improves learning in both discrete and continuous action spaces.
New RL algorithm gives tighter bounds without domain knowledge.
problem Improving worst-case performance bounds in reinforcement learning.
method Derives algorithm for finite horizon discrete MDPs with analysis yielding state-of-the-art worst-case regret bounds.
result Substantially tighter bounds for environments with small environmental norm, no prior knowledge required.
ASVs incorporate causal knowledge into AI explainability.
problem AI explainability and fairness in models.
method Introduces Asymmetric Shapley values (ASVs) to incorporate causal structure.
result ASVs improve model explanations, detect unfair discrimination, and support feature selection.
Study shows group structures are crucial for financial model explanations.
problem Inconsistent explanations from existing explainable machine learning methods.
method Examined group structures in financial datasets and developed group versions of Shapley values.
result Group versions of Shapley values provide consistent explanations.
USFs capture dynamics for faster RL task transfer.
problem Applying knowledge from one task to another.
method Proposed Universal Successor Features (USFs) for RL.
result USFs accelerate training and transfer knowledge.
This paper argues for decolonizing AI alignment by incorporating open-source Hinduism concepts.
problem Coloniality in AI development and deployment, particularly in alignment practices.
method Proposes three forms of openness: model, societal, and excluded knowledge openness, using Hindu viśe\d{s}a-dharma.
result AI alignment should be decolonialized to avoid moral absolutism and better align with desired values.
The paper proposes a method to improve prediction accuracy by querying expert knowledge sequentially.
problem Prediction in high-dimensional settings with limited samples and costly expert consultation.
method Formulates knowledge elicitation as a probabilistic inference process, sequentially querying experts to improve predictions.
result The method shows improved prediction accuracy with minimal expert effort.
Paper derives constraints for Bayesian Knowledge Tracing parameters.
problem Issues with EM algorithm in BKT parameter estimation.
method From first principles, derives constraints on BKT parameter space.
result Novel algorithm respects derived constraints for parameter estimation.
Interpretable ML models for missing data and visualisation.
problem Understanding and evaluating fairness in ML models.
method Introduced angle-based variants of Learning Vector Quantization (LVQ) models.
result Models can handle missing values and extract knowledge from datasets.
This paper proposes a new VoI analysis framework for complex decision problems.
problem Optimizing resource allocation for information collection in decision-making under uncertainty.
method Surrogate-based framework for Value of Information analysis, integrating knowledge sharing and adaptive training.
result Accurate and robust estimates of VoI with fewer model evaluations compared to state-of-the-art methods.
We present a fully nonparametric method to estimate the value function, via simulation, in the context of expected infinite-horizon discounted rewards for Markov chains. Estimating such value functions plays an important role in approximate dynamic programming and applied probability in general. We incorporate "soft in…
A method to reduce knowledge graph embedding models by binarizing parameters.
problem Large memory requirements for tensor factorization models in knowledge graph completion.
method Introducing a quantization function to binarize parameters of CP tensor decomposition.
result Successfully reduced model size by more than an order of magnitude while maintaining task performance.
A new method improves reinforcement learning by directing exploration towards new knowledge.
problem Efficient exploration in reinforcement learning, especially in complex environments.
method Proposed E-values, a generalization of visit-counters, for directed exploration in model-free reinforcement learning. result Improves learning and performance in continuous Markov Decision Processes (MDPs) compared to traditional methods.
Proposes statistical inference for dependency knowledge graphs from EHR data.
problem Statistical uncertainty in linking entities in EHR data.
method Dynamic log-linear topic model with singular value decomposition.
result Established asymptotic normality for sparse graph edge recovery.
ConEx learns complex embeddings for knowledge graphs, improving link prediction.
problem Predicting missing links in knowledge graphs.
method 2D convolution with Hermitian inner product of complex-valued embeddings.
result ConEx outperforms state-of-the-art methods on various benchmarks.