Machine Learning (ML) Latest News and Trending articles from all top sources only on Techminis

A naukri.com initiative

New

Home

ML News

Arxiv

275

Image Credit: Arxiv

Agentic Multimodal AI for Hyperpersonalized B2B and B2C Advertising in Competitive Markets: An AI-Driven Competitive Advertising Framework

Researchers have developed a multilingual, multimodal AI framework for hyper-personalized advertising in B2B and B2C markets.
The framework integrates retrieval-augmented generation (RAG), multimodal reasoning, and adaptive persona-based targeting.
It generates culturally relevant, market-aware ads tailored to shifting consumer behaviors and competition.
The framework combines real-world product experiments and synthetic experiments to optimize strategies at scale and maximize return on advertising spend (ROAS).

Read Full Article

16 Likes

Arxiv

Image Credit: Arxiv

Reducing Smoothness with Expressive Memory Enhanced Hierarchical Graph Neural Networks

Graphical forecasting models learn the structure of time series data via projecting onto a graph.
Hierarchical Graph Flow (HiGFlow) network introduces a memory buffer variable to store previously seen information across variable resolutions.
HiGFlow reduces smoothness when mapping onto new feature spaces in the hierarchy.
Empirical results show that HiGFlow outperforms state-of-the-art baselines, including transformer models, in MAE and RMSE.

Read Full Article

2 Likes

Arxiv

208

Image Credit: Arxiv

Deep learning for state estimation of commercial sodium-ion batteries using partial charging profiles: validation with a multi-temperature ageing dataset

Accurately predicting the state of health for sodium-ion batteries is crucial for managing battery modules and ensuring operational safety.
A new framework was designed that integrates the neural ordinary differential equation and 2D convolutional neural networks to predict the state of charge (SOC), capacity, and state of health (SOH) of batteries using partial charging profiles as input.
The model demonstrated high accuracy, with an R^2 accuracy of 0.998 for SOC and 0.997 for SOH across various temperatures.
The trained model can be used to predict single cells at temperatures outside the training set and battery modules with different capacity and current levels.

Read Full Article

12 Likes

Arxiv

215

Image Credit: Arxiv

Minimum Description Length of a Spectrum Variational Autoencoder: A Theory

Deep neural networks (DNNs) trained through end-to-end learning have achieved remarkable success across diverse machine learning tasks, but they are not designed to adhere to the Minimum Description Length (MDL) principle.
A novel theoretical framework for designing and evaluating deep Variational Autoencoders (VAEs) based on MDL is introduced.
The Spectrum VAE, a specific VAE architecture, is designed and its MDL can be rigorously evaluated under given conditions.
This work lays the foundation for future research on designing deep learning systems that explicitly adhere to information-theoretic principles.

Read Full Article

12 Likes

Discover more

Arxiv

246

Image Credit: Arxiv

Forward Learning with Differential Privacy

Differential privacy (DP) in deep learning is a critical concern for maintaining data confidentiality and model utility.
Forward-learning algorithms add noise during the forward pass to estimate gradients, providing potential natural differential privacy protection.
A new algorithm, DP-ULR, is introduced as a privatized forward-learning algorithm with differential privacy guarantees.
DP-ULR achieves competitive performance compared to traditional differential privacy training algorithms based on backpropagation.

Read Full Article

14 Likes

Arxiv

123

Image Credit: Arxiv

HERA: Hybrid Edge-cloud Resource Allocation for Cost-Efficient AI Agents

Large language models (LLMs) like GPT-4 predominantly operate in the cloud, incurring high operational costs.
The necessity of cloud-exclusive processing for AI agents is being reconsidered with the improved accuracy of local-based small language models (SLMs).
A lightweight scheduler called Adaptive Iteration-level Model Selector (AIMS) is proposed to partition AI agent's subtasks between SLM and LLM based on subtask features to maximize SLM usage and maintain accuracy.
Experimental results show that AIMS improves accuracy by up to 9.1% and increases SLM usage by up to 10.8% compared to existing approaches.

Read Full Article

7 Likes

Arxiv

Image Credit: Arxiv

MetaLoRA: Tensor-Enhanced Adaptive Low-Rank Fine-tuning

There has been a significant increase in the deployment of neural network models, presenting challenges in model adaptation and fine-tuning.
Low-Rank Adaptation (LoRA) has emerged as a promising parameter-efficient fine-tuning method.
This research proposes MetaLoRA, a novel parameter-efficient adaptation framework that integrates meta-learning principles.
MetaLoRA accurately captures task patterns by incorporating meta-learning mechanisms and dynamic parameter adjustment strategies.

Read Full Article

5 Likes

Arxiv

Image Credit: Arxiv

Efficient Near-Optimal Algorithm for Online Shortest Paths in Directed Acyclic Graphs with Bandit Feedback Against Adaptive Adversaries

In this paper, the authors propose an efficient algorithm for the online shortest path problem in directed acyclic graphs (DAGs) under bandit feedback against an adaptive adversary.
The algorithm achieves a near-minimax optimal regret bound of O(√|E|Tlog|X|) with high probability against any adaptive adversary.
The algorithm utilizes a novel loss estimator and a centroid-based decomposition to attain this regret bound.
The algorithm's application extends to various domains, including extensive-form games, shortest walks in directed graphs, hypercubes, and multi-task multi-armed bandits, providing improved regret guarantees in each of these settings.

Read Full Article

5 Likes

Arxiv

109

Image Credit: Arxiv

Informed Greedy Algorithm for Scalable Bayesian Network Fusion via Minimum Cut Analysis

This paper presents the Greedy Min-Cut Bayesian Consensus (GMCBC) algorithm for the structural fusion of Bayesian Networks (BNs).
GMCBC integrates principles from flow network theory into BN fusion, adapting the Backward Equivalence Search (BES) phase of the Greedy Equivalence Search (GES) algorithm and applying the Ford-Fulkerson algorithm for minimum cut analysis.
Experimental results on synthetic Bayesian Networks demonstrate that GMCBC achieves near-optimal network structures.
In federated learning simulations, GMCBC produces a consensus network that improves structural accuracy and dependency preservation compared to the average of the input networks, resulting in a structure that better captures the real underlying (in)dependence relationships.

Read Full Article

6 Likes

Arxiv

193

Image Credit: Arxiv

Less is More: Efficient Black-box Attribution via Minimal Interpretable Subset Selection

Researchers propose LiMA (Less input is More faithful for Attribution), a novel black-box attribution mechanism for AI systems.
LiMA reformulates attribution of important regions as an optimization problem for submodular subset selection.
The method accurately assesses input-prediction interactions and improves optimization efficiency using a bidirectional greedy search algorithm.
Experiments show that LiMA provides faithful interpretations with fewer regions, exhibits strong generalization, and outperforms other attribution algorithms.

Read Full Article

11 Likes

Arxiv

320

Image Credit: Arxiv

Enhancing stroke disease classification through machine learning models via a novel voting system by feature selection techniques

Heart disease remains a leading cause of mortality, necessitating accurate predictive models.
Nine machine learning algorithms were applied, including XGBoost, logistic regression, decision tree, random forest, KNN, SVM, NB Gaussian, adaptive boosting, and linear regression.
Feature selection techniques were used to refine the models and enhance performance and interpretability.
XGBoost demonstrated exceptional performance with 99% accuracy, precision, F1-score, 98% recall, and 100% ROC AUC.

Read Full Article

19 Likes

Arxiv

Image Credit: Arxiv

ParallelFlow: Parallelizing Linear Transformers via Flow Discretization

Researchers introduce a theoretical framework called Parallel Flows for analyzing linear attention models using matrix-valued state space models (SSMs).
The approach of Parallel Flows decouples temporal dynamics from implementation constraints, allowing independent analysis of chunking, parallelization, and information aggregation.
The framework reinterprets chunking procedures as computations of the flows governing system dynamics, connecting it to mathematical tools from rough path theory.
The application of Parallel Flows to DeltaNet in a low-rank setting allows for the design of simple, streamlined generalizations with lower complexity, demonstrating the power of theoretical analysis in inspiring new computational approaches.

Read Full Article

4 Likes

Arxiv

105

Image Credit: Arxiv

Operator Learning with Domain Decomposition for Geometry Generalization in PDE Solving

Neural operators have gained popularity in solving partial differential equations (PDEs) due to their ability to capture complex mappings in function spaces over complex domains.
The data requirements of neural operators limit their widespread use and transferability to new geometries.
To overcome this issue, a local-to-global framework called operator learning with domain decomposition is proposed for solving PDEs on arbitrary geometries.
The framework utilizes an iterative scheme called Schwarz Neural Inference (SNI) to solve local problems with neural operators and stitch local solutions to construct a global solution.

Read Full Article

6 Likes

Arxiv

123

Image Credit: Arxiv

Training Frozen Feature Pyramid DINOv2 for Eyelid Measurements with Infinite Encoding and Orthogonal Regularization

Accurate measurement of eyelid parameters such as MRD1, MRD2, and LF is limited by manual methods.
Deep learning models, including DINOv2, are evaluated for automating these measurements using smartphone-acquired images.
DINOv2, pretrained through self-supervised learning, demonstrates scalability and robustness, especially under frozen conditions ideal for mobile deployment.
Enhancements such as focal loss, orthogonal regularization, and binary encoding strategies improve generalization and prediction accuracy of DINOv2.

Read Full Article

7 Likes

Arxiv

Image Credit: Arxiv

Adversarial Curriculum Graph-Free Knowledge Distillation for Graph Neural Networks

Researchers propose a new method called Adversarial Curriculum Graph-Free Knowledge Distillation (ACGKD) for data-free knowledge distillation of graph neural networks.
ACGKD leverages the Binary Concrete distribution to model graph structures and introduces a spatial complexity tuning parameter, reducing the spatial complexity of pseudo-graphs.
The proposed method accelerates the distillation process by enabling efficient gradient computation for the graph structure.
ACGKD achieves state-of-the-art performance in distilling knowledge from GNNs without training data.

Read Full Article

4 Likes

For uninterrupted reading, download the app