Heterogeneous graph few-shot learning (HGFL) has been developed to address the label sparsity issue in heterogeneous graphs (HGs), which consist of various types of nodes and edges. The core concept of HGFL is to extract knowledge from rich-labeled classes in a source HG, transfer this knowledge to a target HG to facilitate learning new classes with few-labeled training data, and finally make predictions on unlabeled testing data. Existing methods typically assume that the source HG, training data, and testing data all share the same distribution. However, in practice, distribution shifts among these three types of data are inevitable due to two reasons: (1) the limited availability of the source HG that matches the target HG distribution, and (2) the unpredictable data generation mechanism of the target HG. Such distribution shifts result in ineffective knowledge transfer and poor learning performance in existing methods, thereby leading to a novel problem of out-of-distribution (OOD) generalization in HGFL. To address this challenging problem, we propose a novel Causal OOD Heterogeneous graph Few-shot learning model, namely COHF. In COHF, we first characterize distribution shifts in HGs with a structural causal model, establishing an invariance principle for OOD generalization in HGFL. Then, following this invariance principle, we propose a new variational autoencoder-based heterogeneous graph neural network to mitigate the impact of distribution shifts. Finally, by integrating this network with a novel meta-learning framework, COHF effectively transfers knowledge to the target HG to predict new classes with few-labeled data. Extensive experiments on seven real-world datasets have demonstrated the superior performance of COHF over the state-of-the-art methods.
Large pre-trained models excel in zero/few-shot learning for language and vision tasks but face challenges in multivariate time series (TS) forecasting due to diverse data characteristics. Consequently, recent research efforts have focused on developing pre-trained TS forecasting models. These models, whether built from scratch or adapted from large language models (LLMs), excel in zero/few-shot forecasting tasks. However, they are limited by slow performance, high computational demands, and neglect of cross-channel and exogenous correlations. To address this, we introduce Tiny Time Mixers (TTM), a compact model (starting from 1M parameters) with effective transfer learning capabilities, trained exclusively on public TS datasets. TTM, based on the light-weight TSMixer architecture, incorporates innovations like adaptive patching, diverse resolution sampling, and resolution prefix tuning to handle pre-training on varied dataset resolutions with minimal model capacity. Additionally, it employs multi-level modeling to capture channel correlations and infuse exogenous signals during fine-tuning. TTM outperforms existing popular benchmarks in zero/few-shot forecasting by (4-40%), while reducing computational requirements significantly. Moreover, TTMs are lightweight and can be executed even on CPU-only machines, enhancing usability and fostering wider adoption in resource-constrained environments. The model weights for reproducibility and research use are available at https://huggingface.co/ibm/ttm-research-r2/, while enterprise-use weights under the Apache license can be accessed as follows: the initial TTM-Q variant at https://huggingface.co/ibm-granite/granite-timeseries-ttm-r1, and the latest variants (TTM-B, TTM-E, TTM-A) weights are available at https://huggingface.co/ibm-granite/granite-timeseries-ttm-r2.
Providing high-quality video with efficient bitrate is a main challenge in video industry. The traditional one-size-fits-all scheme for bitrate ladders is inefficient and reaching the best content-aware decision computationally impractical due to extensive encodings required. To mitigate this, we propose a bitrate and complexity efficient bitrate ladder prediction method using transfer learning and spatio-temporal features. We propose: (1) using feature maps from well-known pre-trained DNNs to predict rate-quality behavior with limited training data; and (2) improving highest quality rung efficiency by predicting minimum bitrate for top quality and using it for the top rung. The method tested on 102 video scenes demonstrates 94.1% reduction in complexity versus brute-force at 1.71% BD-Rate expense. Additionally, transfer learning was thoroughly studied through four networks and ablation studies.
The assessment of breast density is crucial in the context of breast cancer screening, especially in populations with a higher percentage of dense breast tissues. This study introduces a novel data augmentation technique termed Attention-Guided Erasing (AGE), devised to enhance the downstream classification of four distinct breast density categories in mammography following the BI-RADS recommendation in the Vietnamese cohort. The proposed method integrates supplementary information during transfer learning, utilizing visual attention maps derived from a vision transformer backbone trained using the self-supervised DINO method. These maps are utilized to erase background regions in the mammogram images, unveiling only the potential areas of dense breast tissues to the network. Through the incorporation of AGE during transfer learning with varying random probabilities, we consistently surpass classification performance compared to scenarios without AGE and the traditional random erasing transformation. We validate our methodology using the publicly available VinDr-Mammo dataset. Specifically, we attain a mean F1-score of 0.5910, outperforming values of 0.5594 and 0.5691 corresponding to scenarios without AGE and with random erasing (RE), respectively. This superiority is further substantiated by t-tests, revealing a p-value of p<0.0001, underscoring the statistical significance of our approach.
Short Text Classification (STC) is crucial for processing and understanding the brief but substantial content prevalent on contemporary digital platforms. The STC encounters difficulties in grasping the semantic and syntactic intricacies, an issue that is apparent in traditional pre-trained language models. Although Graph Convolutional Networks enhance performance by integrating external knowledge bases, these methods are limited by the quality and extent of the knowledge applied. Recently, the emergence of Large Language Models (LLMs) and Chain-of-Thought (CoT) has significantly improved the performance of complex reasoning tasks. However, some studies have highlighted the limitations of their application in fundamental NLP tasks. Consequently, this study first employs CoT to investigate and enhance the capabilities of LLMs in STC tasks. We propose the Syntactic and Semantic Enrichment CoT (SSE-CoT) method, effectively decomposing the STC tasks into four distinct steps: (i) essential concept identification, (ii) common-sense knowledge retrieval, (iii) text rewriting, and (iv) classification. Furthermore, recognizing resource constraints in sectors like finance and healthcare, we then introduce the CoT-Driven Multi-Task Learning (CDMT) framework to extend these capabilities to smaller models. This framework begins by extracting rationales from LLMs and subsequently fine-tunes smaller models to optimize their performance. Extensive experimentation across six short-text benchmarks validated the efficacy of the proposed methods. In particular, SSE-CoT achieved state-of-the-art performance with substantial improvements on all datasets, particularly on the Ohsumed and TagMyNews datasets.
The CLIP and Segment Anything Model (SAM) are remarkable vision foundation models (VFMs). SAM excels in segmentation tasks across diverse domains, whereas CLIP is renowned for its zero-shot recognition capabilities. This paper presents an in-depth exploration of integrating these two models into a unified framework. Specifically, we introduce the Open-Vocabulary SAM, a SAM-inspired model designed for simultaneous interactive segmentation and recognition, leveraging two unique knowledge transfer modules: SAM2CLIP and CLIP2SAM. The former adapts SAM's knowledge into the CLIP via distillation and learnable transformer adapters, while the latter transfers CLIP knowledge into SAM, enhancing its recognition capabilities. Extensive experiments on various datasets and detectors show the effectiveness of Open-Vocabulary SAM in both segmentation and recognition tasks, significantly outperforming the na\"{i}ve baselines of simply combining SAM and CLIP. Furthermore, aided with image classification data training, our method can segment and recognize approximately 22,000 classes.
Background: Type 2 diabetes (T2D) is a prevalent chronic disease with a significant risk of serious health complications and negative impacts on the quality of life. Given the impact of individual characteristics and lifestyle on the treatment plan and patient outcomes, it is crucial to develop precise and personalized management strategies. Artificial intelligence (AI) provides great promise in combining patterns from various data sources with nurses' expertise to achieve optimal care. Methods: This is a 6-month ancillary study among T2D patients (n = 20, age = 57 +- 10). Participants were randomly assigned to an intervention (AI, n=10) group to receive daily AI-generated individualized feedback or a control group without receiving the daily feedback (non-AI, n=10) in the last three months. The study developed an online nurse-in-the-loop predictive control (ONLC) model that utilizes a predictive digital twin (PDT). The PDT was developed using a transfer-learning-based Artificial Neural Network. The PDT was trained on participants self-monitoring data (weight, food logs, physical activity, glucose) from the first three months, and the online control algorithm applied particle swarm optimization to identify impactful behavioral changes for maintaining the patient's glucose and weight levels for the next three months. The ONLC provided the intervention group with individualized feedback and recommendations via text messages. The PDT was re-trained weekly to improve its performance. Findings: The trained ONLC model achieved >=80% prediction accuracy across all patients while the model was tuned online. Participants in the intervention group exhibited a trend of improved daily steps and stable or improved total caloric and total carb intake as recommended.
Utilizing well-trained representations in transfer learning often results in superior performance and faster convergence compared to training from scratch. However, even if such good representations are transferred, a model can easily overfit the limited training dataset and lose the valuable properties of the transferred representations. This phenomenon is more severe in ViT due to its low inductive bias. Through experimental analysis using attention maps in ViT, we observe that the rich representations deteriorate when trained on a small dataset. Motivated by this finding, we propose a novel and simple regularization method for ViT called Guided Transfer of spatial Attention (GTA). Our proposed method regularizes the self-attention maps between the source and target models. A target model can fully exploit the knowledge related to object localization properties through this explicit regularization. Our experimental results show that the proposed GTA consistently improves the accuracy across five benchmark datasets especially when the number of training data is small.
As the global population continues to expand, the demand for natural resources increases. Unfortunately, human activities account for 23% of greenhouse gas emissions. On a positive note, remote sensing technologies have emerged as a valuable tool in managing our environment. These technologies allow us to monitor land use, plan urban areas, and drive advancements in areas such as agriculture, climate change mitigation, disaster recovery, and environmental monitoring. Recent advances in AI, computer vision, and earth observation data have enabled unprecedented accuracy in land use mapping. By using transfer learning and fine-tuning with RGB bands, we achieved an impressive 99.19% accuracy in land use analysis. Such findings can be used to inform conservation and urban planning policies.
Physics-informed neural network (PINN) is a data-driven solver for partial and ordinary differential equations(ODEs/PDEs). It provides a unified framework to address both forward and inverse problems. However, the complexity of the objective function often leads to training failures. This issue is particularly prominent when solving high-frequency and multi-scale problems. We proposed using transfer learning to boost the robustness and convergence of training PINN, starting training from low-frequency problems and gradually approaching high-frequency problems. Through two case studies, we discovered that transfer learning can effectively train PINN to approximate solutions from low-frequency problems to high-frequency problems without increasing network parameters. Furthermore, it requires fewer data points and less training time. We elaborately described our training strategy, including optimizer selection, and suggested guidelines for using transfer learning to train neural networks for solving more complex problems.
This research paper addresses the critical challenge of diabetic retinopathy (DR), a severe complication of diabetes leading to potential blindness. The proposed methodology leverages transfer learning with convolutional neural networks (CNNs) for automatic DR detection using a single fundus photograph, demonstrating high effectiveness with a quadratic weighted kappa score of 0.92546 in the APTOS 2019 Blindness Detection Competition. The paper reviews existing literature on DR detection, spanning classical computer vision methods to deep learning approaches, particularly focusing on CNNs. It identifies gaps in the research, emphasizing the lack of exploration in integrating pretrained large language models with segmented image inputs for generating recommendations and understanding dynamic interactions within a web application context.Objectives include developing a comprehensive DR detection methodology, exploring model integration, evaluating performance through competition ranking, contributing significantly to DR detection methodologies, and identifying research gaps.The methodology involves data preprocessing, data augmentation, and the use of a U-Net neural network architecture for segmentation. The U-Net model efficiently segments retinal structures, including blood vessels, hard and soft exudates, haemorrhages, microaneurysms, and the optical disc. High evaluation scores in Jaccard, F1, recall, precision, and accuracy underscore the model's potential for enhancing diagnostic capabilities in retinal pathology assessment.The outcomes of this research hold promise for improving patient outcomes through timely diagnosis and intervention in the fight against diabetic retinopathy, marking a significant contribution to the field of medical image analysis.
The metaverse is expected to provide immersive entertainment, education, and business applications. However, virtual reality (VR) transmission over wireless networks is data- and computation-intensive, making it critical to introduce novel solutions that meet stringent quality-of-service requirements. With recent advances in edge intelligence and deep learning, we have developed a novel multi-view synthesizing framework that can efficiently provide computation, storage, and communication resources for wireless content delivery in the metaverse. We propose a three-dimensional (3D)-aware generative model that uses collections of single-view images. These single-view images are transmitted to a group of users with overlapping fields of view, which avoids massive content transmission compared to transmitting tiles or whole 3D models. We then present a federated learning approach to guarantee an efficient learning process. The training performance can be improved by characterizing the vertical and horizontal data samples with a large latent feature space, while low-latency communication can be achieved with a reduced number of transmitted parameters during federated learning. We also propose a federated transfer learning framework to enable fast domain adaptation to different target domains. Simulation results have demonstrated the effectiveness of our proposed federated multi-view synthesizing framework for VR content delivery.
Although deep learning-based algorithms have demonstrated excellent performance in automated emotion recognition via electroencephalogram (EEG) signals, variations across brain signal patterns of individuals can diminish the model's effectiveness when applied across different subjects. While transfer learning techniques have exhibited promising outcomes, they still encounter challenges related to inadequate feature representations and may overlook the fact that source subjects themselves can possess distinct characteristics. In this work, we propose a multi-source domain adaptation approach with a transformer-based feature generator (MSDA-TF) designed to leverage information from multiple sources. The proposed feature generator retains convolutional layers to capture shallow spatial, temporal, and spectral EEG data representations, while self-attention mechanisms extract global dependencies within these features. During the adaptation process, we group the source subjects based on correlation values and aim to align the moments of the target subject with each source as well as within the sources. MSDA-TF is validated on the SEED dataset and is shown to yield promising results.
Surfactants are of high importance in different industrial sectors such as cosmetics, detergents, oil recovery and drug delivery systems. Therefore, many quantitative structure-property relationship (QSPR) models have been developed for surfactants. Each predictive model typically focuses on one surfactant class, mostly nonionics. Graph Neural Networks (GNNs) have exhibited a great predictive performance for property prediction of ionic liquids, polymers and drugs in general. Specifically for surfactants, GNNs can successfully predict critical micelle concentration (CMC), a key surfactant property associated with micellization. A key factor in the predictive ability of QSPR and GNN models is the data available for training. Based on extensive literature search, we create the largest available CMC database with 429 molecules and the first large data collection for surface excess concentration ($\Gamma$$_{m}$), another surfactant property associated with foaming, with 164 molecules. Then, we develop GNN models to predict the CMC and $\Gamma$$_{m}$ and we explore different learning approaches, i.e., single- and multi-task learning, as well as different training strategies, namely ensemble and transfer learning. We find that a multi-task GNN with ensemble learning trained on all $\Gamma$$_{m}$ and CMC data performs best. Finally, we test the ability of our CMC model to generalize on industrial grade pure component surfactants. The GNN yields highly accurate predictions for CMC, showing great potential for future industrial applications.
Evolutionary Multitasking (EMT) paradigm, an emerging research topic in evolutionary computation, has been successfully applied in solving high-dimensional feature selection (FS) problems recently. However, existing EMT-based FS methods suffer from several limitations, such as a single mode of multitask generation, conducting the same generic evolutionary search for all tasks, relying on implicit transfer mechanisms through sole solution encodings, and employing single-objective transformation, which result in inadequate knowledge acquisition, exploitation, and transfer. To this end, this paper develops a novel EMT framework for multiobjective high-dimensional feature selection problems, namely MO-FSEMT. In particular, multiple auxiliary tasks are constructed by distinct formulation methods to provide diverse search spaces and information representations and then simultaneously addressed with the original task through a multi-slover-based multitask optimization scheme. Each task has an independent population with task-specific representations and is solved using separate evolutionary solvers with different biases and search preferences. A task-specific knowledge transfer mechanism is designed to leverage the advantage information of each task, enabling the discovery and effective transmission of high-quality solutions during the search process. Comprehensive experimental results demonstrate that our MO-FSEMT framework can achieve overall superior performance compared to the state-of-the-art FS methods on 26 datasets. Moreover, the ablation studies verify the contributions of different components of the proposed MO-FSEMT.
This work offers a heuristic evaluation of the effects of variations in machine learning training regimes and learning paradigms on the energy consumption of computing, especially HPC hardware with a life-cycle aware perspective. While increasing data availability and innovation in high-performance hardware fuels the training of sophisticated models, it also fosters the fading perception of energy consumption and carbon emission. Therefore, the goal of this work is to raise awareness about the energy impact of general training parameters and processes, from learning rate over batch size to knowledge transfer. Multiple setups with different hyperparameter configurations are evaluated on three different hardware systems. Among many results, we have found out that even with the same model and hardware to reach the same accuracy, improperly set training hyperparameters consume up to 5 times the energy of the optimal setup. We also extensively examined the energy-saving benefits of learning paradigms including recycling knowledge through pretraining and sharing knowledge through multitask training.
Federated Learning (FL) enables collaborative model training among participants while guaranteeing the privacy of raw data. Mainstream FL methodologies overlook the dynamic nature of real-world data, particularly its tendency to grow in volume and diversify in classes over time. This oversight results in FL methods suffering from catastrophic forgetting, where the trained models inadvertently discard previously learned information upon assimilating new data. In response to this challenge, we propose a novel Federated Class-Incremental Learning (FCIL) method, named \underline{Fed}erated \underline{C}lass-Incremental \underline{L}earning with New-Class \underline{A}ugmented \underline{S}elf-Di\underline{S}tillation (FedCLASS). The core of FedCLASS is to enrich the class scores of historical models with new class scores predicted by current models and utilize the combined knowledge for self-distillation, enabling a more sufficient and precise knowledge transfer from historical models to current models. Theoretical analyses demonstrate that FedCLASS stands on reliable foundations, considering scores of old classes predicted by historical models as conditional probabilities in the absence of new classes, and the scores of new classes predicted by current models as the conditional probabilities of class scores derived from historical models. Empirical experiments demonstrate the superiority of FedCLASS over four baseline algorithms in reducing average forgetting rate and boosting global accuracy.
Federated learning (FL) underpins advancements in privacy-preserving distributed computing by collaboratively training neural networks without exposing clients' raw data. Current FL paradigms primarily focus on uni-modal data, while exploiting the knowledge from distributed multimodal data remains largely unexplored. Existing multimodal FL (MFL) solutions are mainly designed for statistical or modality heterogeneity from the input side, however, have yet to solve the fundamental issue,"modality imbalance", in distributed conditions, which can lead to inadequate information exploitation and heterogeneous knowledge aggregation on different modalities.In this paper, we propose a novel Cross-Modal Infiltration Federated Learning (FedCMI) framework that effectively alleviates modality imbalance and knowledge heterogeneity via knowledge transfer from the global dominant modality. To avoid the loss of information in the weak modality due to merely imitating the behavior of dominant modality, we design the two-projector module to integrate the knowledge from dominant modality while still promoting the local feature exploitation of weak modality. In addition, we introduce a class-wise temperature adaptation scheme to achieve fair performance across different classes. Extensive experiments over popular datasets are conducted and give us a gratifying confirmation of the proposed framework for fully exploring the information of each modality in MFL.
Early cancer detection is crucial for prognosis, but many cancer types lack large labelled datasets required for developing deep learning models. This paper investigates self-supervised learning (SSL) as an alternative to the standard supervised pre-training on ImageNet for scenarios with limited training data using a deep learning model (ResNet-50). We first demonstrate that SSL pre-training on ImageNet (via the Barlow Twins SSL algorithm) outperforms supervised pre-training (SL) using a skin lesion dataset with limited training samples. We then consider \textit{further} SSL pre-training (of the two ImageNet pre-trained models) on task-specific datasets, where our implementation is motivated by supervised transfer learning. This approach significantly enhances initially SL pre-trained models, closing the performance gap with initially SSL pre-trained ones. Surprisingly, further pre-training on just the limited fine-tuning data achieves this performance equivalence. Linear probe experiments reveal that improvement stems from enhanced feature extraction. Hence, we find that minimal further SSL pre-training on task-specific data can be as effective as large-scale SSL pre-training on ImageNet for medical image classification tasks with limited labelled data. We validate these results on an oral cancer histopathology dataset, suggesting broader applicability across medical imaging domains facing labelled data scarcity.
Learning from demonstration is a powerful method for teaching robots new skills, and having more demonstration data often improves policy learning. However, the high cost of collecting demonstration data is a significant bottleneck. Videos, as a rich data source, contain knowledge of behaviors, physics, and semantics, but extracting control-specific information from them is challenging due to the lack of action labels. In this work, we introduce a novel framework, Any-point Trajectory Modeling (ATM), that utilizes video demonstrations by pre-training a trajectory model to predict future trajectories of arbitrary points within a video frame. Once trained, these trajectories provide detailed control guidance, enabling the learning of robust visuomotor policies with minimal action-labeled data. Across over 130 language-conditioned tasks we evaluated in both simulation and the real world, ATM outperforms strong video pre-training baselines by 80% on average. Furthermore, we show effective transfer learning of manipulation skills from human videos and videos from a different robot morphology. Visualizations and code are available at: \url{https://xingyu-lin.github.io/atm}.