Multilingual generative models obtain remarkable cross-lingual in-context learning capabilities through pre-training on large-scale corpora. However, they still exhibit a performance bias toward high-resource languages and learn isolated distributions of multilingual sentence representations, which may hinder knowledge transfer across languages. To bridge this gap, we propose a simple yet effective cross-lingual alignment framework exploiting pairs of translation sentences. It aligns the internal sentence representations across different languages via multilingual contrastive learning and aligns outputs by following cross-lingual instructions in the target language. Experimental results show that even with less than 0.1 {\textperthousand} of pre-training tokens, our alignment framework significantly boosts the cross-lingual abilities of generative language models and mitigates the performance gap. Further analyses reveal that it results in a better internal multilingual representation distribution of multilingual models.
Few-shot image generation aims to train generative models using a small number of training images. When there are few images available for training (e.g. 10 images), Learning From Scratch (LFS) methods often generate images that closely resemble the training data while Transfer Learning (TL) methods try to improve performance by leveraging prior knowledge from GANs pre-trained on large-scale datasets. However, current TL methods may not allow for sufficient control over the degree of knowledge preservation from the source model, making them unsuitable for setups where the source and target domains are not closely related. To address this, we propose a novel pipeline called Peer is your Pillar (PIP), which combines a target few-shot dataset with a peer dataset to create a data-unbalanced conditional generation. Our approach includes a class embedding method that separates the class space from the latent space, and we use a direction loss based on pre-trained CLIP to improve image diversity. Experiments on various few-shot datasets demonstrate the advancement of the proposed PIP, especially reduces the training requirements of few-shot image generation.
Recently, multi-modal content generation has attracted lots of attention from researchers by investigating the utilization of visual instruction tuning based on large language models (LLMs). To enhance the performance and generalization ability of such LLMs, the practice of distilling knowledge from pretrained multi-modal models (a.k.a. teachers) to more compact multi-modal LLMs (students) has gained considerable interest. However, the prevailing paradigm of instructiontuning in multi-modal LLMs knowledge distillation is resource-intensive and unidirectional, neglecting the potential for mutual feedback between the student and teacher models. Thus, we propose an innovative Competitive Multi-modal Distillation framework (CoMD), which captures bidirectional feedback between teacher and student models and continually updates the multi-modal capabilities that the student model has learned. It comprises two stages: multi-modal pre-training and multi-modal competitive distillation. The first stage pre-trains the student model on a large number of filtered multi-modal datasets. The second stage facilitates a bidirectional knowledge transfer between the student and teacher models. Our experimental analysis of diverse datasets shows that our knowledge transfer method consistently improves the capabilities of the student model. Finally, the 7B-sized student model after four distillations surpassed the current state-of-the-art model LLaVA-13B on the ScienceQA and LLaVA Test dataset, also outperforms other strong baselines in the zero-shot setting.
Motion sensors integrated into wearable and mobile devices provide valuable information about the device users. Machine learning and, recently, deep learning techniques have been used to characterize sensor data. Mostly, a single task, such as recognition of activities, is targeted, and the data is processed centrally at a server or in a cloud environment. However, the same sensor data can be utilized for multiple tasks and distributed machine-learning techniques can be used without the requirement of the transmission of data to a centre. This paper explores Federated Transfer Learning in a Multi-Task manner for both sensor-based human activity recognition and device position identification tasks. The OpenHAR framework is used to train the models, which contains ten smaller datasets. The aim is to obtain model(s) applicable for both tasks in different datasets, which may include only some label types. Multiple experiments are carried in the Flower federated learning environment using the DeepConvLSTM architecture. Results are presented for federated and centralized versions under different parameters and restrictions. By utilizing transfer learning and training a task-specific and personalized federated model, we obtained a similar accuracy with training each client individually and higher accuracy than a fully centralized approach.
Artificial intelligence (AI) has revolutionized software engineering (SE) by enhancing software development efficiency. The advent of pre-trained models (PTMs) leveraging transfer learning has significantly advanced AI for SE. However, existing PTMs that operate on individual code tokens suffer from several limitations: They are costly to train and fine-tune; and they rely heavily on labeled data for fine-tuning on task-specific datasets. In this paper, we present TransformCode, a novel framework that learns code embeddings in a contrastive learning manner. Our framework is encoder-agnostic and language-agnostic, which means that it can leverage any encoder model and handle any programming language. We also propose a novel data-augmentation technique called abstract syntax tree (AST) transformation, which applies syntactic and semantic transformations to the original code snippets, to generate more diverse and robust samples for contrastive learning. Our framework has several advantages over existing methods: (1) It is flexible and adaptable, because it can easily be extended to other downstream tasks that require code representation (such as code-clone detection and classification); (2) it is efficient and scalable, because it does not require a large model or a large amount of training data, and it can support any programming language; (3) it is not limited to unsupervised learning, but can also be applied to some supervised learning tasks by incorporating task-specific labels or objectives; and (4) it can also adjust the number of encoder parameters based on computing resources. We evaluate our framework on several code-related tasks, and demonstrate its effectiveness and superiority over the state-of-the-art methods such as SourcererCC, Code2vec, and InferCode.
Early diagnosis of the cancer cells is necessary for making an effective treatment plan and for the health and safety of a patient. Nowadays, doctors usually use a histological grade that pathologists determine by performing a semi-quantitative analysis of the histopathological and cytological features of hematoxylin-eosin (HE) stained histopathological images. This research contributes a potential classification model for cancer prognosis to efficiently utilize the valuable information underlying the HE-stained histopathological images. This work uses the PatchCamelyon benchmark datasets and trains them in a multi-layer perceptron and convolution model to observe the model's performance in terms of precision, Recall, F1 Score, Accuracy, and AUC Score. The evaluation result shows that the baseline convolution model outperforms the baseline MLP model. Also, this paper introduced ResNet50 and InceptionNet models with data augmentation, where ResNet50 is able to beat the state-of-the-art model. Furthermore, the majority vote and concatenation ensemble were evaluated and provided the future direction of using transfer learning and segmentation to understand the specific features.
Millions of people have died worldwide from COVID-19. In addition to its high death toll, COVID-19 has led to unbearable suffering for individuals and a huge global burden to the healthcare sector. Therefore, researchers have been trying to develop tools to detect symptoms of this human-transmissible disease remotely to control its rapid spread. Coughing is one of the common symptoms that researchers have been trying to detect objectively from smartphone microphone-sensing. While most of the approaches to detect and track cough symptoms rely on machine learning models developed from a large amount of patient data, this is not possible at the early stage of an outbreak. In this work, we present an incremental transfer learning approach that leverages the relationship between healthy peoples' coughs and COVID-19 patients' coughs to detect COVID-19 coughs with reasonable accuracy using a pre-trained healthy cough detection model and a relatively small set of patient coughs, reducing the need for large patient dataset to train the model. This type of model can be a game changer in detecting the onset of a novel respiratory virus.
Fine-tuning pre-trained foundational language models (FLM) for specific tasks is often impractical, especially for resource-constrained devices. This necessitates the development of a Lifelong Learning (L3) framework that continuously adapts to a stream of Natural Language Processing (NLP) tasks efficiently. We propose an approach that focuses on extracting meaningful representations from unseen data, constructing a structured knowledge base, and improving task performance incrementally. We conducted experiments on various NLP tasks to validate its effectiveness, including benchmarks like GLUE and SuperGLUE. We measured good performance across the accuracy, training efficiency, and knowledge transfer metrics. Initial experimental results show that the proposed L3 ensemble method increases the model accuracy by 4% ~ 36% compared to the fine-tuned FLM. Furthermore, L3 model outperforms naive fine-tuning approaches while maintaining competitive or superior performance (up to 15.4% increase in accuracy) compared to the state-of-the-art language model (T5) for the given task, STS benchmark.
Large, pre-trained models are problematic to use in resource constrained applications. Fortunately, task-aware structured pruning methods offer a solution. These approaches reduce model size by dropping structural units like layers and attention heads in a manner that takes into account the end-task. However, these pruning algorithms require more task-specific data than is typically available. We propose a framework which combines structured pruning with transfer learning to reduce the need for task-specific data. Our empirical results answer questions such as: How should the two tasks be coupled? What parameters should be transferred? And, when during training should transfer learning be introduced? Leveraging these insights, we demonstrate that our framework results in pruned models with improved generalization over strong baselines.
While interests in tabular deep learning has significantly grown, conventional tree-based models still outperform deep learning methods. To narrow this performance gap, we explore the innovative retrieval mechanism, a methodology that allows neural networks to refer to other data points while making predictions. Our experiments reveal that retrieval-based training, especially when fine-tuning the pretrained TabPFN model, notably surpasses existing methods. Moreover, the extensive pretraining plays a crucial role to enhance the performance of the model. These insights imply that blending the retrieval mechanism with pretraining and transfer learning schemes offers considerable potential for advancing the field of tabular deep learning.
We present the development of a Named Entity Recognition (NER) dataset for Tagalog. This corpus helps fill the resource gap present in Philippine languages today, where NER resources are scarce. The texts were obtained from a pretraining corpora containing news reports, and were labeled by native speakers in an iterative fashion. The resulting dataset contains ~7.8k documents across three entity types: Person, Organization, and Location. The inter-annotator agreement, as measured by Cohen's $\kappa$, is 0.81. We also conducted extensive empirical evaluation of state-of-the-art methods across supervised and transfer learning settings. Finally, we released the data and processing code publicly to inspire future work on Tagalog NLP.
As a privacy-preserving collaborative machine learning paradigm, federated learning (FL) has attracted significant interest from academia and the industry alike. To allow each data owner (a.k.a., FL clients) to train a heterogeneous and personalized local model based on its local data distribution, system resources and requirements on model structure, the field of model-heterogeneous personalized federated learning (MHPFL) has emerged. Existing MHPFL approaches either rely on the availability of a public dataset with special characteristics to facilitate knowledge transfer, incur high computation and communication costs, or face potential model leakage risks. To address these limitations, we propose a model-heterogeneous personalized Federated learning approach based on feature Extractor Sharing (pFedES). It incorporates a small homogeneous feature extractor into each client's heterogeneous local model. Clients train them via the proposed iterative learning method to enable the exchange of global generalized knowledge and local personalized knowledge. The small local homogeneous extractors produced after local training are uploaded to the FL server and for aggregation to facilitate easy knowledge sharing among clients. We theoretically prove that pFedES can converge over wall-to-wall time. Extensive experiments on two real-world datasets against six state-of-the-art methods demonstrate that pFedES builds the most accurate model, while incurring low communication and computation costs. Compared with the best-performing baseline, it achieves 1.61% higher test accuracy, while reducing communication and computation costs by 99.6% and 82.9%, respectively.
In cross-lingual language understanding, machine translation is often utilized to enhance the transferability of models across languages, either by translating the training data from the source language to the target, or from the target to the source to aid inference. However, in cross-lingual machine reading comprehension (MRC), it is difficult to perform a deep level of assistance to enhance cross-lingual transfer because of the variation of answer span positions in different languages. In this paper, we propose X-STA, a new approach for cross-lingual MRC. Specifically, we leverage an attentive teacher to subtly transfer the answer spans of the source language to the answer output space of the target. A Gradient-Disentangled Knowledge Sharing technique is proposed as an improved cross-attention block. In addition, we force the model to learn semantic alignments from multiple granularities and calibrate the model outputs with teacher guidance to enhance cross-lingual transferability. Experiments on three multi-lingual MRC datasets show the effectiveness of our method, outperforming state-of-the-art approaches.
Text-based Person Search (TBPS) aims to retrieve images of target pedestrian indicated by textual descriptions. It is essential for TBPS to extract fine-grained local features and align them crossing modality. Existing methods utilize external tools or heavy cross-modal interaction to achieve explicit alignment of cross-modal fine-grained features, which is inefficient and time-consuming. In this work, we propose a Vision-Guided Semantic-Group Network (VGSG) for text-based person search to extract well-aligned fine-grained visual and textual features. In the proposed VGSG, we develop a Semantic-Group Textual Learning (SGTL) module and a Vision-guided Knowledge Transfer (VGKT) module to extract textual local features under the guidance of visual local clues. In SGTL, in order to obtain the local textual representation, we group textual features from the channel dimension based on the semantic cues of language expression, which encourages similar semantic patterns to be grouped implicitly without external tools. In VGKT, a vision-guided attention is employed to extract visual-related textual features, which are inherently aligned with visual cues and termed vision-guided textual features. Furthermore, we design a relational knowledge transfer, including a vision-language similarity transfer and a class probability transfer, to adaptively propagate information of the vision-guided textual features to semantic-group textual features. With the help of relational knowledge transfer, VGKT is capable of aligning semantic-group textual features with corresponding visual features without external tools and complex pairwise interaction. Experimental results on two challenging benchmarks demonstrate its superiority over state-of-the-art methods.
Effective training of deep image segmentation models is challenging due to the need for abundant, high-quality annotations. Generating annotations is laborious and time-consuming for human experts, especially in medical image segmentation. To facilitate image annotation, we introduce Physics Informed Contour Selection (PICS) - an interpretable, physics-informed algorithm for rapid image segmentation without relying on labeled data. PICS draws inspiration from physics-informed neural networks (PINNs) and an active contour model called snake. It is fast and computationally lightweight because it employs cubic splines instead of a deep neural network as a basis function. Its training parameters are physically interpretable because they directly represent control knots of the segmentation curve. Traditional snakes involve minimization of the edge-based loss functionals by deriving the Euler-Lagrange equation followed by its numerical solution. However, PICS directly minimizes the loss functional, bypassing the Euler Lagrange equations. It is the first snake variant to minimize a region-based loss function instead of traditional edge-based loss functions. PICS uniquely models the three-dimensional (3D) segmentation process with an unsteady partial differential equation (PDE), which allows accelerated segmentation via transfer learning. To demonstrate its effectiveness, we apply PICS for 3D segmentation of the left ventricle on a publicly available cardiac dataset. While doing so, we also introduce a new convexity-preserving loss term that encodes the shape information of the left ventricle to enhance PICS's segmentation quality. Overall, PICS presents several novelties in network architecture, transfer learning, and physics-inspired losses for image segmentation, thereby showing promising outcomes and potential for further refinement.
We present C-Procgen, an enhanced suite of environments on top of the Procgen benchmark. C-Procgen provides access to over 200 unique game contexts across 16 games. It allows for detailed configuration of environments, ranging from game mechanics to agent attributes. This makes the procedural generation process, previously a black-box in Procgen, more transparent and adaptable for various research needs.The upgrade enhances dynamic context management and individualized assignments, while maintaining computational efficiency. C-Procgen's controllable contexts make it applicable in diverse reinforcement learning research areas, such as learning dynamics analysis, curriculum learning, and transfer learning. We believe that C-Procgen will fill a gap in the current literature and offer a valuable toolkit for future works.
Tactile information is important for robust performance in robotic tasks that involve physical interaction, such as object manipulation. However, with more data included in the reasoning and control process, modeling behavior becomes increasingly difficult. Deep Reinforcement Learning (DRL) produced promising results for learning complex behavior in various domains, including tactile-based manipulation in robotics. In this work, we present our open-source reinforcement learning environments for the TIAGo service robot. They produce tactile sensor measurements that resemble those of a real sensorised gripper for TIAGo, encouraging research in transfer learning of DRL policies. Lastly, we show preliminary training results of a learned force control policy and compare it to a classical PI controller.
Thin-cap fibroatheroma (TCFA) is a prominent risk factor for plaque rupture. Intravascular optical coherence tomography (IVOCT) enables identification of fibrous cap (FC), measurement of FC thicknesses, and assessment of plaque vulnerability. We developed a fully-automated deep learning method for FC segmentation. This study included 32,531 images across 227 pullbacks from two registries. Images were semi-automatically labeled using our OCTOPUS with expert editing using established guidelines. We employed preprocessing including guidewire shadow detection, lumen segmentation, pixel-shifting, and Gaussian filtering on raw IVOCT (r,theta) images. Data were augmented in a natural way by changing theta in spiral acquisitions and by changing intensity and noise values. We used a modified SegResNet and comparison networks to segment FCs. We employed transfer learning from our existing much larger, fully-labeled calcification IVOCT dataset to reduce deep-learning training. Overall, our method consistently delivered better FC segmentation results (Dice: 0.837+/-0.012) than other deep-learning methods. Transfer learning reduced training time by 84% and reduced the need for more training samples. Our method showed a high level of generalizability, evidenced by highly-consistent segmentations across five-fold cross-validation (sensitivity: 85.0+/-0.3%, Dice: 0.846+/-0.011) and the held-out test (sensitivity: 84.9%, Dice: 0.816) sets. In addition, we found excellent agreement of FC thickness with ground truth (2.95+/-20.73 um), giving clinically insignificant bias. There was excellent reproducibility in pre- and post-stenting pullbacks (average FC angle: 200.9+/-128.0 deg / 202.0+/-121.1 deg). Our method will be useful for multiple research purposes and potentially for planning stent deployments that avoid placing a stent edge over an FC.
The growing number of AI-driven applications in mobile devices has led to solutions that integrate deep learning models with the available edge-cloud resources. Due to multiple benefits such as reduction in on-device energy consumption, improved latency, improved network usage, and certain privacy improvements, split learning, where deep learning models are split away from the mobile device and computed in a distributed manner, has become an extensively explored topic. Incorporating compression-aware methods (where learning adapts to compression level of the communicated data) has made split learning even more advantageous. This method could even offer a viable alternative to traditional methods, such as federated learning techniques. In this work, we develop an adaptive compression-aware split learning method ('deprune') to improve and train deep learning models so that they are much more network-efficient, which would make them ideal to deploy in weaker devices with the help of edge-cloud resources. This method is also extended ('prune') to very quickly train deep learning models through a transfer learning approach, which trades off little accuracy for much more network-efficient inference abilities. We show that the 'deprune' method can reduce network usage by 4x when compared with a split-learning approach (that does not use our method) without loss of accuracy, while also improving accuracy over compression-aware split-learning by 4 percent. Lastly, we show that the 'prune' method can reduce the training time for certain models by up to 6x without affecting the accuracy when compared against a compression-aware split-learning approach.
We introduce Florence-2, a novel vision foundation model with a unified, prompt-based representation for a variety of computer vision and vision-language tasks. While existing large vision models excel in transfer learning, they struggle to perform a diversity of tasks with simple instructions, a capability that implies handling the complexity of various spatial hierarchy and semantic granularity. Florence-2 was designed to take text-prompt as task instructions and generate desirable results in text forms, whether it be captioning, object detection, grounding or segmentation. This multi-task learning setup demands large-scale, high-quality annotated data. To this end, we co-developed FLD-5B that consists of 5.4 billion comprehensive visual annotations on 126 million images, using an iterative strategy of automated image annotation and model refinement. We adopted a sequence-to-sequence structure to train Florence-2 to perform versatile and comprehensive vision tasks. Extensive evaluations on numerous tasks demonstrated Florence-2 to be a strong vision foundation model contender with unprecedented zero-shot and fine-tuning capabilities.