CybAI news

[Submitted on 21 Nov 2024] View a PDF of the paper titled NBMLSS: probabilistic forecasting of electricity prices via Neural Basis Models for Location Scale and Shape, by Alessandro Brusaferri and Danial Ramin and Andrea Ballarino View PDF HTML (experimental) Abstract:Forecasters using flexible neural networks (NN) in multi-horizon distributional regression setups often struggle to gain detailed insights into the underlying mechanisms that lead to the predicted feature-conditioned distribution parameters. In this work, we deploy a Neural Basis Model for Location, Scale and Shape, that blends the principled interpretability of GAMLSS with a computationally scalable shared basis decomposition, combined by linear…

arXiv:2411.13578v1 Announce Type: new Abstract: How can models effectively detect out-of-distribution (OOD) samples in complex, multi-label settings without extensive retraining? Existing OOD detection methods struggle to capture the intricate semantic relationships and label co-occurrences inherent in multi-label settings, often requiring large amounts of training data and failing to generalize to unseen label combinations. While large language models have revolutionized zero-shot OOD detection, they primarily focus on single-label scenarios, leaving a critical gap in handling real-world tasks where samples can be associated with multiple interdependent labels. To address these challenges, we introduce COOD, a novel zero-shot multi-label OOD detection framework. COOD…

arXiv:2411.14318v1 Announce Type: new Abstract: It is well-known that a diverse corpus is critical for training large language models, which are typically constructed from a mixture of various domains. In general, previous efforts resort to sampling training data from different domains with static proportions, as well as adjusting data proportions during training. However, few methods have addressed the complexities of domain-adaptive continual pre-training. To fill this gap, we propose Velocitune, a novel framework dynamically assesses learning velocity and adjusts data proportions accordingly, favoring slower-learning domains while shunning faster-learning ones, which is guided by a scaling law to indicate the desired…

[Submitted on 20 Sep 2024 (v1), last revised 21 Nov 2024 (this version, v3)] View a PDF of the paper titled SatFed: A Resource-Efficient LEO Satellite-Assisted Heterogeneous Federated Learning Framework, by Yuxin Zhang and 7 other authors View PDF HTML (experimental) Abstract:Traditional federated learning (FL) frameworks rely heavily on terrestrial networks, where coverage limitations and increasing bandwidth congestion significantly hinder model convergence. Fortunately, the advancement of low-Earth orbit (LEO) satellite networks offers promising new communication avenues to augment traditional terrestrial FL. Despite this potential, the limited satellite-ground communication bandwidth and the heterogeneous operating environments of ground devices-including variations in data,…

arXiv:2411.13731v1 Announce Type: new Abstract: Addressing data integrity challenges, such as unlearning the effects of data poisoning after model training, is necessary for the reliable deployment of machine learning models. State-of-the-art influence functions, such as EK-FAC, often fail to accurately attribute abnormal model behavior to the specific poisoned training data responsible for the data poisoning attack. In addition, traditional unlearning algorithms often struggle to effectively remove the influence of poisoned samples, particularly when only a few affected examples can be identified. To address these challenge, we introduce $Delta$-Influence, a novel approach that leverages influence functions to trace abnormal model behavior…

[Submitted on 23 May 2023 (v1), last revised 20 Nov 2024 (this version, v5)] View a PDF of the paper titled Schema-Driven Information Extraction from Heterogeneous Tables, by Fan Bai and 5 other authors View PDF HTML (experimental) Abstract:In this paper, we explore the question of whether large language models can support cost-efficient information extraction from tables. We introduce schema-driven information extraction, a new task that transforms tabular data into structured records following a human-authored schema. To assess various LLM's capabilities on this task, we present a benchmark comprised of tables from four diverse domains: machine learning papers, chemistry literature,…