We demonstrate the efficacy of using intermediate representations from a single foundation model to enhance various music downstream tasks. We introduce SoniDo, a music foundation model (MFM) designed to extract hierarchical features from target music samples. By leveraging hierarchical intermediate features, SoniDo constrains the information granularity, leading to improved performance across various downstream tasks including both understanding and generative tasks. We specifically evaluated this approach on representative tasks such as music tagging, music transcription, music source separation, and music mixing. Our results reveal that the features extracted from foundation models provide valuable enhancements in training downstream task models. This highlights the capability of using features extracted from music foundation models as a booster for downstream tasks. Our approach not only benefits existing task-specific models but also supports music downstream tasks constrained by data scarcity. This paves the way for more effective and accessible music processing solutions. Figure 1: SoniDo extracts hierarchical features of target music samples, which are useful for solving music downstream tasks including understanding and generative tasks.

Early and accurate diagnosis of brain tumors is crucial for improving patient survival rates. However, the detection and classification of brain tumors are challenging due to their diverse types and complex morphological characteristics. This study investigates the application of pre-trained models for brain tumor classification, with a particular focus on deploying the Mamba model. We fine-tuned several mainstream transfer learning models and applied them to the multi-class classification of brain tumors. By comparing these models to those trained from scratch, we demonstrated the significant advantages of transfer learning, especially in the medical imaging field, where annotated data is often limited. Notably, we introduced the Vision Mamba (Vim), a novel network architecture, and applied it for the first time in brain tumor classification, achieving exceptional classification accuracy. Experimental results indicate that the Vim model achieved 100% classification accuracy on an independent test set, emphasizing its potential for tumor classification tasks. These findings underscore the effectiveness of transfer learning in brain tumor classification and reveal that, compared to existing state-of-the-art models, the Vim model is lightweight, efficient, and highly accurate, offering a new perspective for clinical applications. Furthermore, the framework proposed in this study for brain tumor classification, based on transfer learning and the Vision Mamba model, is broadly applicable to other medical imaging classification problems.

In recent years, Edge AI has become more prevalent with applications across various industries, from environmental monitoring to smart city management. Edge AI facilitates the processing of Internet of Things (IoT) data and provides privacy-enabled and latency-sensitive services to application users using Machine Learning (ML) algorithms, e.g., Time Series Classification (TSC). However, existing TSC algorithms require access to full raw data and demand substantial computing resources to train and use them effectively in runtime. This makes them impractical for deployment in resource-constrained Edge environments. To address this, in this paper, we propose an Adaptive Brownian Bridge-based Symbolic Aggregation Vector Space Model (ABBA-VSM). It is a new TSC model designed for classification services on Edge. Here, we first adaptively compress the raw time series into symbolic representations, thus capturing the changing trends of data. Subsequently, we train the classification model directly on these symbols. ABBA-VSM reduces communication data between IoT and Edge devices, as well as computation cycles, in the development of resource-efficient TSC services on Edge. We evaluate our solution with extensive experiments using datasets from the UCR time series classification archive. The results demonstrate that the ABBA-VSM achieves up to 80% compression ratio and 90-100% accuracy for binary classification. Whereas, for non-binary classification, it achieves an average compression ratio of 60% and accuracy ranging from 60-80%.

Multi-modal deep metric learning is crucial for effectively capturing diverse representations in tasks such as face verification, fine-grained object recognition, and product search. Traditional approaches to metric learning, whether based on distance or margin metrics, primarily emphasize class separation, often overlooking the intra-class distribution essential for multi-modal feature learning. In this context, we propose a novel loss function called Density-Aware Adaptive Margin Loss(DAAL), which preserves the density distribution of embeddings while encouraging the formation of adaptive sub-clusters within each class. By employing an adaptive line strategy, DAAL not only enhances intra-class variance but also ensures robust inter-class separation, facilitating effective multi-modal representation. Comprehensive experiments on benchmark fine-grained datasets demonstrate the superior performance of DAAL, underscoring its potential in advancing retrieval applications and multi-modal deep metric learning.

Contrastive learning has become a dominant approach in self-supervised visual representation learning. Hard negatives - samples closely resembling the anchor - are key to enhancing learned representations' discriminative power. However, efficiently leveraging hard negatives remains challenging. We introduce SynCo (Synthetic Negatives in Contrastive learning), a novel approach that improves model performance by generating synthetic hard negatives on the representation space. Building on the MoCo framework, SynCo introduces six strategies for creating diverse synthetic hard negatives on-the-fly with minimal computational overhead. SynCo achieves faster training and better representation learning, reaching 67.9% top-1 accuracy on ImageNet ILSVRC-2012 linear evaluation after 200 pretraining epochs, surpassing MoCo's 67.5% using the same ResNet-50 encoder. It also transfers more effectively to detection tasks: on PASCAL VOC, it outperforms both the supervised baseline and MoCo with 82.5% AP; on COCO, it sets new benchmarks with 40.9% AP for bounding box detection and 35.5% AP for instance segmentation. Our synthetic hard negative generation approach significantly enhances visual representations learned through self-supervised contrastive learning. Code is available at https://github.com/giakoumoglou/synco.

Generalization outside the scope of one's training data requires leveraging prior knowledge about the effects that transfer, and the effects that don't, between different data sources. Bayesian transfer learning is a principled paradigm for specifying this knowledge, and refining it on the basis of data from the source (training) and target (prediction) tasks. We address the challenging transfer learning setting where the learner (i) cannot fine-tune in the target task, and (ii) does not know which source data points correspond to the same task (i.e., the data sources are unknown). We propose a proxy-informed robust method for probabilistic transfer learning (PROMPT), which provides a posterior predictive estimate tailored to the structure of the target task, without requiring the learner have access to any outcome information from the target task. Instead, PROMPT relies on the availability of proxy information. PROMPT uses the same proxy information for two purposes: (i) estimation of effects specific to the target task, and (ii) construction of a robust reweighting of the source data for estimation of effects that transfer between tasks. We provide theoretical results on the effect of this reweighting on the risk of negative transfer, and demonstrate application of PROMPT in two synthetic settings.

Ensuring robust model performance across diverse real-world scenarios requires addressing both transportability across domains with covariate shifts and extrapolation beyond observed data ranges. However, there is no formal procedure for statistically evaluating generalizability in machine learning algorithms, particularly in causal inference. Existing methods often rely on arbitrary metrics like AUC or MSE and focus predominantly on toy datasets, providing limited insights into real-world applicability. To address this gap, we propose a systematic and quantitative framework for evaluating model generalizability under covariate distribution shifts, specifically within causal inference settings. Our approach leverages the frugal parameterization, allowing for flexible simulations from fully and semi-synthetic benchmarks, offering comprehensive evaluations for both mean and distributional regression methods. By basing simulations on real data, our method ensures more realistic evaluations, which is often missing in current work relying on simplified datasets. Furthermore, using simulations and statistical testing, our framework is robust and avoids over-reliance on conventional metrics. Grounded in real-world data, it provides realistic insights into model performance, bridging the gap between synthetic evaluations and practical applications.

The Bethe-Hessian matrix, introduced by Saade, Krzakala, and Zdeborov\'a (2014), is a Hermitian matrix designed for applying spectral clustering algorithms to sparse networks. Rather than employing a non-symmetric and high-dimensional non-backtracking operator, a spectral method based on the Bethe-Hessian matrix is conjectured to also reach the Kesten-Stigum detection threshold in the sparse stochastic block model (SBM). We provide the first rigorous analysis of the Bethe-Hessian spectral method in the SBM under both the bounded expected degree and the growing degree regimes. Specifically, we demonstrate that: (i) When the expected degree $d\geq 2$, the number of negative outliers of the Bethe-Hessian matrix can consistently estimate the number of blocks above the Kesten-Stigum threshold, thus confirming a conjecture from Saade, Krzakala, and Zdeborov\'a (2014) for $d\geq 2$. (ii) For sufficiently large $d$, its eigenvectors can be used to achieve weak recovery. (iii) As $d\to\infty$, we establish the concentration of the locations of its negative outlier eigenvalues, and weak consistency can be achieved via a spectral method based on the Bethe-Hessian matrix.

As a prominent challenge in addressing real-world issues within a dynamic environment, label shift, which refers to the learning setting where the source (training) and target (testing) label distributions do not match, has recently received increasing attention. Existing label shift methods solely use unlabeled target samples to estimate the target label distribution, and do not involve them during the classifier training, resulting in suboptimal utilization of available information. One common solution is to directly blend the source and target distributions during the training of the target classifier. However, we illustrate the theoretical deviation and limitations of the direct distribution mixture in the label shift setting. To tackle this crucial yet unexplored issue, we introduce the concept of aligned distribution mixture, showcasing its theoretical optimality and generalization error bounds. By incorporating insights from generalization theory, we propose an innovative label shift framework named as Aligned Distribution Mixture (ADM). Within this framework, we enhance four typical label shift methods by introducing modifications to the classifier training process. Furthermore, we also propose a one-step approach that incorporates a pioneering coupling weight estimation strategy. Considering the distinctiveness of the proposed one-step approach, we develop an efficient bi-level optimization strategy. Experimental results demonstrate the effectiveness of our approaches, together with their effectiveness in COVID-19 diagnosis applications.

Statistical learning in high-dimensional spaces is challenging without a strong underlying data structure. Recent advances with foundational models suggest that text and image data contain such hidden structures, which help mitigate the curse of dimensionality. Inspired by results from nonparametric statistics, we hypothesize that this phenomenon can be partially explained in terms of decomposition of complex tasks into simpler subtasks. In this paper, we present a controlled experimental framework to test whether neural networks can indeed exploit such ``hidden factorial structures.'' We find that they do leverage these latent patterns to learn discrete distributions more efficiently, and derive scaling laws linking model sizes, hidden factorizations, and accuracy. We also study the interplay between our structural assumptions and the models' capacity for generalization.