Transfer Learning for Matrix Completion

In this paper, we explore the knowledge transfer under the setting of matrix completion, which aims to enhance the estimation of a low-rank target matrix with auxiliary data available. We propose a transfer learning procedure given prior information on which source datasets are favorable. We study its convergence rates and prove its minimax optimality. Our analysis reveals that with the source matrices close enough to the target matrix, out method outperforms the traditional method using the single target data. In particular, we leverage the advanced sharp concentration inequalities introduced in \cite{brailovskaya2024universality} to eliminate a logarithmic factor in the convergence rate, which is crucial for proving the minimax optimality. When the relevance of source datasets is unknown, we develop an efficient detection procedure to identify informative sources and establish its selection consistency. Simulations and real data analysis are conducted to support the validity of our methodology.

Wildlife Target Re-Identification Using Self-supervised Learning in Non-Urban Settings

Wildlife re-identification aims to match individuals of the same species across different observations. Current state-of-the-art (SOTA) models rely on class labels to train supervised models for individual classification. This dependence on annotated data has driven the curation of numerous large-scale wildlife datasets. This study investigates self-supervised learning Self-Supervised Learning (SSL) for wildlife re-identification. We automatically extract two distinct views of an individual using temporal image pairs from camera trap data without supervision. The image pairs train a self-supervised model from a potentially endless stream of video data. We evaluate the learnt representations against supervised features on open-world scenarios and transfer learning in various wildlife downstream tasks. The analysis of the experimental results shows that self-supervised models are more robust even with limited data. Moreover, self-supervised features outperform supervision across all downstream tasks. The code is available here https://github.com/pxpana/SSLWildlife.

Transfer Learning for VLC-based indoor Localization: Addressing Environmental Variability

Accurate indoor localization is crucial in industrial environments. Visible Light Communication (VLC) has emerged as a promising solution, offering high accuracy, energy efficiency, and minimal electromagnetic interference. However, VLC-based indoor localization faces challenges due to environmental variability, such as lighting fluctuations and obstacles. To address these challenges, we propose a Transfer Learning (TL)-based approach for VLC-based indoor localization. Using real-world data collected at a BOSCH factory, the TL framework integrates a deep neural network (DNN) to improve localization accuracy by 47\%, reduce energy consumption by 32\%, and decrease computational time by 40\% compared to the conventional models. The proposed solution is highly adaptable under varying environmental conditions and achieves similar accuracy with only 30\% of the dataset, making it a cost-efficient and scalable option for industrial applications in Industry 4.0.

Continual Gradient Low-Rank Projection Fine-Tuning for LLMs

Continual fine-tuning of Large Language Models (LLMs) is hampered by the trade-off between efficiency and expressiveness. Low-Rank Adaptation (LoRA) offers efficiency but constrains the model's ability to learn new tasks and transfer knowledge due to its low-rank nature and reliance on explicit parameter constraints. We propose GORP (Gradient LOw Rank Projection) for Continual Learning, a novel training strategy that overcomes these limitations by synergistically combining full and low-rank parameters and jointly updating within a unified low-rank gradient subspace. GORP expands the optimization space while preserving efficiency and mitigating catastrophic forgetting. Extensive experiments on continual learning benchmarks demonstrate GORP's superior performance compared to existing state-of-the-art approaches. Code is available at https://github.com/Wcxwcxw/GORP.

How Weight Resampling and Optimizers Shape the Dynamics of Continual Learning and Forgetting in Neural Networks

Recent work in continual learning has highlighted the beneficial effect of resampling weights in the last layer of a neural network (``zapping"). Although empirical results demonstrate the effectiveness of this approach, the underlying mechanisms that drive these improvements remain unclear. In this work, we investigate in detail the pattern of learning and forgetting that take place inside a convolutional neural network when trained in challenging settings such as continual learning and few-shot transfer learning, with handwritten characters and natural images. Our experiments show that models that have undergone zapping during training more quickly recover from the shock of transferring to a new domain. Furthermore, to better observe the effect of continual learning in a multi-task setting we measure how each individual task is affected. This shows that, not only zapping, but the choice of optimizer can also deeply affect the dynamics of learning and forgetting, causing complex patterns of synergy/interference between tasks to emerge when the model learns sequentially at transfer time.

Fluid Democracy in Federated Data Aggregation

Federated learning (FL) mechanisms typically require each client to transfer their weights to a central server, irrespective of how useful they are. In order to avoid wasteful data transfer costs from clients to the central server, we propose the use of consensus based protocols to identify a subset of clients with most useful model weights at each data transfer step. First, we explore the application of existing fluid democracy protocols to FL from a performance standpoint, comparing them with traditional one-person-one-vote (also known as 1p1v or FedAvg). We propose a new fluid democracy protocol named viscous-retained democracy that always does better than 1p1v under the same assumptions as existing fluid democracy protocols while also not allowing for influence accumulation. Secondly, we identify weaknesses of fluid democracy protocols from an adversarial lens in terms of their dependence on topology and/ or number of adversaries required to negatively impact the global model weights. To this effect, we propose an algorithm (FedVRD) that dynamically limits the effect of adversaries while minimizing cost by leveraging the delegation topology.

Automated Classification of Volcanic Earthquakes Using Transformer Encoders: Insights into Data Quality and Model Interpretability

Precisely classifying earthquake types is crucial for elucidating the relationship between volcanic earthquakes and volcanic activity. However, traditional methods rely on subjective human judgment, which requires considerable time and effort. To address this issue, we developed a deep learning model using a transformer encoder for a more objective and efficient classification. Tested on Mount Asama's diverse seismic activity, our model achieved high F1 scores (0.930 for volcano tectonic, 0.931 for low-frequency earthquakes, and 0.980 for noise), superior to a conventional CNN-based method. To enhance interpretability, attention weight visualizations were analyzed, revealing that the model focuses on key waveform features similarly to human experts. However, inconsistencies in training data, such as ambiguously labeled B-type events with S-waves, were found to influence classification accuracy and attention weight distributions. Experiments addressing data selection and augmentation demonstrated the importance of balancing data quality and diversity. In addition, stations within 3 km of the crater played an important role in improving model performance and interpretability. These findings highlight the potential of Transformer-based models for automated volcanic earthquake classification, particularly in improving efficiency and interpretability. By addressing challenges such as data imbalance and subjective labeling, our approach provides a robust framework for understanding seismic activity at Mount Asama. Moreover, this framework offers opportunities for transfer learning to other volcanic regions, paving the way for enhanced volcanic hazard assessments and disaster mitigation strategies.

High-Order Deep Meta-Learning with Category-Theoretic Interpretation

We introduce a new hierarchical deep learning framework for recursive higher-order meta-learning that enables neural networks (NNs) to construct, solve, and generalise across hierarchies of tasks. Central to this approach is a generative mechanism that creates \emph{virtual tasks} -- synthetic problem instances designed to enable the meta-learner to learn \emph{soft constraints} and unknown generalisable rules across related tasks. Crucially, this enables the framework to generate its own informative, task-grounded datasets thereby freeing machine learning (ML) training from the limitations of relying entirely on human-generated data. By actively exploring the virtual point landscape and seeking out tasks lower-level learners find difficult, the meta-learner iteratively refines constraint regions. This enhances inductive biases, regularises the adaptation process, and produces novel, unanticipated tasks and constraints required for generalisation. Each meta-level of the hierarchy corresponds to a progressively abstracted generalisation of problems solved at lower levels, enabling a structured and interpretable learning progression. By interpreting meta-learners as category-theoretic \emph{functors} that generate and condition a hierarchy of subordinate learners, we establish a compositional structure that supports abstraction and knowledge transfer across progressively generalised tasks. The category-theoretic perspective unifies existing meta-learning models and reveals how learning processes can be transformed and compared through functorial relationships, while offering practical design principles for structuring meta-learning. We speculate this architecture may underpin the next generation of NNs capable of autonomously generating novel, instructive tasks and their solutions, thereby advancing ML towards general artificial intelligence.

Towards Perception-Informed Latent HRTF Representations

Personalized head-related transfer functions (HRTFs) are essential for ensuring a realistic auditory experience over headphones, because they take into account individual anatomical differences that affect listening. Most machine learning approaches to HRTF personalization rely on a learned low-dimensional latent space to generate or select custom HRTFs for a listener. However, these latent representations are typically learned in a manner that optimizes for spectral reconstruction but not for perceptual compatibility, meaning they may not necessarily align with perceptual distance. In this work, we first study whether traditionally learned HRTF representations are well correlated with perceptual relations using auditory-based objective perceptual metrics; we then propose a method for explicitly embedding HRTFs into a perception-informed latent space, leveraging a metric-based loss function and supervision via Metric Multidimensional Scaling (MMDS). Finally, we demonstrate the applicability of these learned representations to the task of HRTF personalization. We suggest that our method has the potential to render personalized spatial audio, leading to an improved listening experience.

TD-MPC-Opt: Distilling Model-Based Multi-Task Reinforcement Learning Agents

We present a novel approach to knowledge transfer in model-based reinforcement learning, addressing the critical challenge of deploying large world models in resource-constrained environments. Our method efficiently distills a high-capacity multi-task agent (317M parameters) into a compact model (1M parameters) on the MT30 benchmark, significantly improving performance across diverse tasks. Our distilled model achieves a state-of-the-art normalized score of 28.45, surpassing the original 1M parameter model score of 18.93. This improvement demonstrates the ability of our distillation technique to capture and consolidate complex multi-task knowledge. We further optimize the distilled model through FP16 post-training quantization, reducing its size by $\sim$50\%. Our approach addresses practical deployment limitations and offers insights into knowledge representation in large world models, paving the way for more efficient and accessible multi-task reinforcement learning systems in robotics and other resource-constrained applications. Code available at https://github.com/dmytro-kuzmenko/td-mpc-opt.