Machine Learning Journal (@[email protected])
@MLJ_Social
Followers
480
Following
74
Media
0
Statuses
874
This is the official social media account of the Machine Learning journal, published by Springer
Joined November 2020
Another @ECMLPKDD 2025 JT paper: "Search or split: policy gradient with adaptive policy space" by Gianmarco Tedeschi, Matteo Papini, Alberto Maria Metelli & Marcello Restelli (.
link.springer.com
Machine Learning - Policy search is one of the most effective reinforcement learning classes of methods for solving continuous control tasks. These methodologies attempt to find a good policy for...
0
0
0
Also open access @ #MLJ: "Construction of the Kolmogorov-Arnold networks using the Newton-Kaczmarz method" by Michael Poluektov & Andrew Polar ( #OA.
link.springer.com
Machine Learning - It is known that any continuous multivariate function can be represented exactly by a composition functions of a single variable—the so-called Kolmogorov-Arnold...
0
0
0
Generate videos in just a few seconds. Try Grok Imagine, free for a limited time.
387
158
2K
E!C!M!L!P!K!D!D! open! access! "Analyzing the effect of residual connections to oversmoothing in graph neural networks" by Dimitrios Kelesis, Dimitris Fotakis & Georgios Paliouras ( #OA #MLJ #ECMLPKDD2025 @ECMLPKDD.
link.springer.com
Machine Learning - The performance of Graph Neural Networks (GNNs) diminishes as their depth increases. That is mainly attributed to oversmoothing, which leads to similar node representations...
1
0
0
"PCE-GNN: a node feature-enhanced graph neural network with pre-clustering strategy" by Yongbo Li, Fangfang Xie, Xi Li, Kaiyan Chen, Jiangyi Yao & Xiongwei Li (.
link.springer.com
Machine Learning - Graph Neural Networks (GNNs) exhibit excellent performance in extracting node features from graph-structured data. To enhance the representation of central node features and...
0
0
0
"Community detection via structured adaptive block-diagonal learning with topology-subspace fusion" by Ling Wu, Ziqi Cai, Yingjie Yang & Kun Guo (.
link.springer.com
Machine Learning - Subspace clustering can capture the structural features of complex networks. However, existing subspace-based methods encounter challenges related to dependence on priori...
0
0
0
And another one: "TransFed: cross-domain feature alignment for semi-supervised federated transfer learning" by Linghui Zeng, Ruixuan Liu, Li Xiong & Joyce C. Ho (.
link.springer.com
Machine Learning - Healthcare institutions often need to collaborate on developing predictive models while adhering to privacy regulations and handling heterogeneous data collection practices....
0
0
0
Another very interesting-sounding open access article: "Physics encoded blocks in residual neural network architectures for digital twin models" by Muhammad Saad Zia, Corentin Houpert, Ashiq Anjum, Lu Liu, Anthony Conway & Anasol Peña-Rios ( #MLJ #OA.
link.springer.com
Machine Learning - Physics Informed Machine Learning has emerged as a popular approach for modeling and simulation in digital twins, enabling the generation of accurate models of processes and...
0
0
0
New @ECMLPKDD 2025 journal track ( #MLJ paper: "Single image inpainting and super-resolution with simultaneous uncertainty guarantees by universal reproducing kernels" by Bálint Horváth & Balázs Csanád Csáji ( And open access! #OA.
link.springer.com
Machine Learning - The paper proposes a statistical learning approach to the problem of estimating missing pixels of images, crucial for image inpainting and super-resolution problems. One of the...
1
0
0
"Improving graph neural networks through feature importance learning" by Fouad Alkhoury, Tamás Horváth, @CBauckhage & Stefan Wrobel. Open access! ( #OA #MLJ.
link.springer.com
Machine Learning - Graph neural networks (GNNs) are among the most widely used methods for node classification in graphs. A common strategy to improve their predictive performance is to enrich...
0
0
0
A bit more than 2 months out, the @ECMLPKDD 2025 papers continue to come out: "JANET: Joint Adaptive predictioN-region Estimation for Time-series" by E. English, E. Wong-Toi, M. Fontana, S. Mandt, P. Smyth & C. Lippert. Open access again: #OA #MLJ.
link.springer.com
Machine Learning - Conformal prediction provides machine learning models with prediction sets that offer theoretical guarantees, but the underlying assumption of exchangeability limits its...
0
0
0
Another @ECMLPKDD 2025 ( paper: "MUSO: achieving exact machine unlearning in over-parameterized regimes" by Ruikai Yang, Mingzhen He, Zhenghao He, Youmei Qiu & Xiaolin Huang (.
link.springer.com
Machine Learning - Machine unlearning (MU) is to make a well-trained model behave as if it had never been trained on specific data. In today’s over-parameterized models, dominated by neural...
0
0
0
Open! Access! "Panda: partially approximate newton methods for distributed minimax optimization with unbalanced dimensions" by Minheng Xiao, Chengchang Liu, Cheng Chen, John C. S. Lui & Sen Na ( #OA #MLJ.
link.springer.com
Machine Learning - Unbalanced dimensions are crucial characteristics in various minimax optimization problems, such as few-shot learning (Cortes and Mohri in Adv Neural Inf Process Syst 16, 2003;...
0
0
0
And another #MLJ open access paper: "All-time safety and sample-efficient meta update for online safe meta reinforcement learning under Markov task transition" by Zhenyuan Yuan, Siyuan Xu & Minghui Zhu ( #OA.
link.springer.com
Machine Learning - This paper studies the issues of ensuring all-time safety and sample-efficient meta update in online safe meta reinforcement learning (MRL) on physical agents (e.g., mobile...
0
0
0
The Discovery Science 2024 collection's here:
link.springer.com
https://link.springer.com/journal/10994/updates/27716666
0
0
0
A #DS2024 open access paper: "Segmentation and feature extraction-based classification of pavement damages using hybrid computer vision and machine learning approaches" by Lizette Tello-Cifuentes, Johannio Marulanda & Peter Thomson ( #OA #MLJ.
link.springer.com
Machine Learning - Ensuring the safety, durability, and cost-effectiveness of road infrastructure maintenance requires accurate and efficient damage assessment. However, the heterogeneous nature of...
1
0
0
"Entangle-then-disentangle: a novel approach for enhancing large vision-language model" by Jiajun Yuan, Haiting Zheng, Hang Yu & Xiangfeng Luo ( #MLJ.
link.springer.com
Machine Learning - Large-scale foundation models, such as the contrastive language-image pre-training model and the align language model, have shown promising performance on downstream tasks....
0
0
0
"HFIA: a parasitic feature inference attack and gradient-based defense strategy in SplitNN-based vertical federated learning" by Qixuan Dong, Boyang Zhou, ZhiQiang Ru, Ying He, Jingyu Hua & Sheng Zhong ( #MLJ.
link.springer.com
Machine Learning - Vertical Federated Learning (VFL) is widely adopted in industries like healthcare, enabling collaborators to enhance model performance using disparate data sources. Split Neural...
0
0
0
"RCC-MAS: a new algorithm for computing all rough-set-constructs" by Yanir González Díaz, Manuel S. Lazo Cortés, José Fco. Martínez Trinidad & Jesús A. Carrasco Ochoa (.
link.springer.com
Machine Learning - In rough set theory, a construct is defined as a subset of attributes possessing the same capacity as the complete set of attributes to discern objects from different classes,...
0
0
0
"Leveraging differentiable NAS and abstract genetic algorithms for optimizing on-mobile VSR performance" by Xuncheng Liu, Weizhan Zhang, Tieliang Gong, Caixia Yan & Rui Li (.
link.springer.com
Machine Learning - The proliferation of mobile video applications has for real-time Video Super-Resolution (VSR) technologies, necessitating architectures that simultaneously achieve...
0
0
0
Another @ECMLPKDD 2025 open access paper just dropped: "Fedflow: a personalized federated learning framework for passenger flow prediction" by Franca Rocco di Torrepadula, Marco Fisichella, Sergio Di Martino & Nicola Mazzocca ( #OA #MLJ #ECMLPKDD.
link.springer.com
Machine Learning - In the Intelligent Public Transportation Systems (IPTS) domain, predicting the number of commuters on-board, entering or leaving a metro train or a bus, i.e. the Passenger Flow...
0
0
0