arXiv research

Model infers functions for attributes using multi-aggregate datasets with knowledge transfer.

OKDDip uses diverse peers to improve online knowledge distillation.

One-Shot Federated Learning learns a global model in one round.

MULTIPOLAR aggregates diverse source policies for efficient transfer RL.

The paper uses tensor decompositions to improve neural network models for tree data.

The paper examines the feasibility of managing aggregate cyber-risk in IoT environments.

Paper proves impossible for large language models to control hallucinations without sacrificing other properties.

Improved meta-learning for dynamics using additional structured knowledge.

The policy objective of safeguarding financial stability has stimulated a wave of research on systemic risk analytics, yet it still faces challenges in measurability. This paper models systemic risk by tapping into expert knowledge of financial supervisors. We decompose systemic risk into a number of interconnected seg…

Optimized Q-learning reduces regret in state-aggregated MDPs.

New method explains ML performance gaps without causal knowledge.

RE-NET predicts future interactions in temporal knowledge graphs.

In order to improve forecasts, a decisionmaker often combines probabilities given by various sources, such as human experts and machine learning classifiers. When few training data are available, aggregation can be improved by incorporating prior knowledge about the event being forecasted and about salient properties o…

PREMA recovers detailed data from aggregated views.

New method aggregates bootstrapped DAGs for causal discovery.

This paper introduces glocal explanations for expected goal models in soccer.

State aggregation is a popular model reduction method rooted in optimal control. It reduces the complexity of engineering systems by mapping the system's states into a small number of meta-states. The choice of aggregation map often depends on the data analysts' knowledge and is largely ad hoc. In this paper, we propos…

This study examines yield aggregators in DeFi, summarizing strategies and analyzing performance.

Crowdsourced wisdom improves causal learning.

Paper proposes a new method to aggregate multiple sources with different label distributions.

We prove a lower bound for feature dimension in linear MDPs and propose a novel dynamics aggregation framework.

Early-stopped aggregation improves computational efficiency in adaptive statistical inference.

Proposes a novel MTL approach based on bias-variance analysis.

RR-GCN uses random transformations instead of learned weights for node embeddings.

PhyDNN uses physics knowledge to improve drag force prediction models.

The paper introduces a tensor-based approach to improve neural models' aggregation of structural context.

A key factor in developing high performing machine learning models is the availability of sufficiently large datasets. This work is motivated by applications arising in Software as a Service (SaaS) companies where there exist numerous similar yet disjoint datasets from multiple client companies. To overcome the challen…

We analyze a fast incremental aggregated gradient method for optimizing nonconvex problems of the form $\min_x \sum_i f_i(x)$. Specifically, we analyze the SAGA algorithm within an Incremental First-order Oracle framework, and show that it converges to a stationary point provably faster than both gradient descent and s…

New method ranks sectors and countries using local and aggregate I-O data.

GENI estimates node importance in KGs using GNNs.

This paper improves prediction accuracy for multi-input classification tasks using p-value aggregation.

Proposes a new method for predicting missing relations in knowledge graphs.

The paper calculates VaR and CTE for extreme and aggregate risks using FGM copula.

Graph few-shot learning improves node classification with prior knowledge transfer.

Since time immemorial, people have been looking for ways to organize scientific knowledge into some systems to facilitate search and discovery of new ideas. The problem was partially solved in the pre-Internet era using library classifications, but nowadays it is nearly impossible to classify all scientific and popular…

This paper improves route choice models by incorporating contextual factors.

Simple aggregation of multiple methods defends against adversarial attacks on neural networks.

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…

Log-Loss scores expose membership privacy breaches.

A new framework for deep learning from multiple experts tackles long-tailed data issues.

GCNs improve regression tasks by aggregating neighbor signals.

Proposes OpenKI for better web-scale knowledge extraction and alignment.

Federated Learning speeds up speech recognition training by 7x and reduces error rate by 6%.

Paper tackles sparse, unstructured data tensors by optimizing adaptive aggregation granularity.

HGKT transfers knowledge from seen to unseen classes in GZSL without prior unseen class info.

AdarGCN tackles noisy web images in few-shot learning.

We consider the multi-label ranking approach to multi-label learning. Boosting is a natural method for multi-label ranking as it aggregates weak predictions through majority votes, which can be directly used as scores to produce a ranking of the labels. We design online boosting algorithms with provable loss bounds for…

Proposes a method for stable variable selection in high-dimensional data.