The primary challenge in Federated Learning (FL) is to model non-IID distributions across clients, whose fine-grained structure is important to improve knowledge sharing. For example, some knowledge is globally shared across all clients, some is only transferable within a subgroup of clients, and some are client-specific. To capture and exploit this structure, we train models organized in a multi-level structure, called ``Multi-level Additive Models (MAM)'', for better knowledge-sharing across heterogeneous clients and their personalization. In federated MAM (FeMAM), each client is assigned to at most one model per level and its personalized prediction sums up the outputs of models assigned to it across all levels. For the top level, FeMAM trains one global model shared by all clients as FedAvg. For every mid-level, it learns multiple models each assigned to a subgroup of clients, as clustered FL. Every bottom-level model is trained for one client only. In the training objective, each model aims to minimize the residual of the additive predictions by the other models assigned to each client. To approximate the arbitrary structure of non-IID across clients, FeMAM introduces more flexibility and adaptivity to FL by incrementally adding new models to the prediction of each client and reassigning another if necessary, automatically optimizing the knowledge-sharing structure. Extensive experiments show that FeMAM surpasses existing clustered FL and personalized FL methods in various non-IID settings. Our code is available at https://github.com/shutong043/FeMAM.

Federated Learning (FL) has emerged as a solution for distributed systems that allow clients to train models on their data and only share models instead of local data. Generative Models are designed to learn the distribution of a dataset and generate new data samples that are similar to the original data. Many prior works have tried proposing Federated Generative Models. Using Federated Learning and Generative Models together can be susceptible to attacks, and designing the optimal architecture remains challenging. This survey covers the growing interest in the intersection of FL and Generative Models by comprehensively reviewing research conducted from 2019 to 2024. We systematically compare nearly 100 papers, focusing on their FL and Generative Model methods and privacy considerations. To make this field more accessible to newcomers, we highlight the state-of-the-art advancements and identify unresolved challenges, offering insights for future research in this evolving field.

In this paper, we introduce the Dependent Noise-based Inaccurate Label Distribution Learning (DN-ILDL) framework to tackle the challenges posed by noise in label distribution learning, which arise from dependencies on instances and labels. We start by modeling the inaccurate label distribution matrix as a combination of the true label distribution and a noise matrix influenced by specific instances and labels. To address this, we develop a linear mapping from instances to their true label distributions, incorporating label correlations, and decompose the noise matrix using feature and label representations, applying group sparsity constraints to accurately capture the noise. Furthermore, we employ graph regularization to align the topological structures of the input and output spaces, ensuring accurate reconstruction of the true label distribution matrix. Utilizing the Alternating Direction Method of Multipliers (ADMM) for efficient optimization, we validate our method's capability to recover true labels accurately and establish a generalization error bound. Extensive experiments demonstrate that DN-ILDL effectively addresses the ILDL problem and outperforms existing LDL methods.

This paper aims to develop a new deep learning-inspired gaming approach for early detection of dementia. This research integrates a robust convolutional neural network (CNN)-based model for early dementia detection using health metrics data as well as facial image data through a cognitive assessment-based gaming application. We have collected 1000 data samples of health metrics dataset from Apollo Diagnostic Center Kolkata that is labeled as either demented or non-demented for the training of MOD-1D-CNN for the game level 1 and another dataset of facial images containing 1800 facial data that are labeled as either demented or non-demented is collected by our research team for the training of MOD-2D-CNN model in-game level 2. In our work, the loss for the proposed MOD-1D-CNN model is 0.2692 and the highest accuracy is 70.50% for identifying the dementia traits using real-life health metrics data. Similarly, the proposed MOD-2D-CNN model loss is 0.1755 and the highest accuracy is obtained here 95.72% for recognizing the dementia status using real-life face-based image data. Therefore, a rule-based weightage method is applied to combine both the proposed methods to achieve the final decision. The MOD-1D-CNN and MOD-2D-CNN models are more lightweight and computationally efficient alternatives because they have a significantly lower number of parameters when compared to the other state-of-the-art models. We have compared their accuracies and parameters with the other state-of-the-art deep learning models.

Knowledge tracing has been widely used in online learning systems to guide the students' future learning. However, most existing KT models primarily focus on extracting abundant information from the question sets and explore the relationships between them, but ignore the personalized student behavioral information in the learning process. This will limit the model's ability to accurately capture the personalized knowledge states of students and reasonably predict their performances. To alleviate this limitation, we explicitly models the personalized learning process by incorporating the emotions, a representative personalized behavior in the learning process, into KT framework. Specifically, we present a novel Dual-State Personalized Knowledge Tracing with Emotional Incorporation model to achieve this goal: Firstly, we incorporate emotional information into the modeling process of knowledge state, resulting in the Knowledge State Boosting Module. Secondly, we design an Emotional State Tracing Module to monitor students' personalized emotional states, and propose an emotion prediction method based on personalized emotional states. Finally, we apply the predicted emotions to enhance students' response prediction. Furthermore, to extend the generalization capability of our model across different datasets, we design a transferred version of DEKT, named Transfer Learning-based Self-loop model (T-DEKT). Extensive experiments show our method achieves the state-of-the-art performance.

Voice activity detection (VAD) is the task of detecting speech in an audio stream, which is challenging due to numerous unseen noises and low signal-to-noise ratios in real environments. Recently, neural network-based VADs have alleviated the degradation of performance to some extent. However, the majority of existing studies have employed excessively large models and incorporated future context, while neglecting to evaluate the operational efficiency and latency of the models. In this paper, we propose a lightweight and real-time neural network called MagicNet, which utilizes casual and depth separable 1-D convolutions and GRU. Without relying on future features as input, our proposed model is compared with two state-of-the-art algorithms on synthesized in-domain and out-domain test datasets. The evaluation results demonstrate that MagicNet can achieve improved performance and robustness with fewer parameter costs.

Social recommendation models weave social interactions into their design to provide uniquely personalized recommendation results for users. However, social networks not only amplify the popularity bias in recommendation models, resulting in more frequent recommendation of hot items and fewer long-tail items, but also include a substantial amount of redundant information that is essentially meaningless for the model's performance. Existing social recommendation models fail to address the issues of popularity bias and the redundancy of social information, as they directly characterize social influence across the entire social network without making targeted adjustments. In this paper, we propose a Condition-Guided Social Recommendation Model (named CGSoRec) to mitigate the model's popularity bias by denoising the social network and adjusting the weights of user's social preferences. More specifically, CGSoRec first includes a Condition-Guided Social Denoising Model (CSD) to remove redundant social relations in the social network for capturing users' social preferences with items more precisely. Then, CGSoRec calculates users' social preferences based on denoised social network and adjusts the weights in users' social preferences to make them can counteract the popularity bias present in the recommendation model. At last, CGSoRec includes a Condition-Guided Diffusion Recommendation Model (CGD) to introduce the adjusted social preferences as conditions to control the recommendation results for a debiased direction. Comprehensive experiments on three real-world datasets demonstrate the effectiveness of our proposed method. The code is in: https://github.com/hexin5515/CGSoRec.

Large Language Models (LLMs) demonstrate remarkable potential across various domains; however, they exhibit a significant performance gap in Information Extraction (IE). Note that high-quality instruction data is the vital key for enhancing the specific capabilities of LLMs, while current IE datasets tend to be small in scale, fragmented, and lack standardized schema. To this end, we introduce IEPile, a comprehensive bilingual (English and Chinese) IE instruction corpus, which contains approximately 0.32B tokens. We construct IEPile by collecting and cleaning 33 existing IE datasets, and introduce schema-based instruction generation to unearth a large-scale corpus. Experimentally, IEPile enhance the performance of LLMs for IE, with notable improvements in zero-shot generalization. We open-source the resource and pre-trained models, hoping to provide valuable support to the NLP community.

We employ Large language models (LLMs) such as GPT-fine-tuning on the LLaMa-2, Mixtral 8 7B, 4 (OpenAI, 2023), BLOOM (Le Scao et al, Gemma, and conduct a comprehensive evaluation 2023), LLaMa-2 (Touvron et al, 2023), Mistral of Vietnamese LLMs across various scenarios and (Jiang et al., 2023), Mixtral (Jiang et al., 2024), settings. Throughout the thorough evaluation process, Gemma (Team et al., 2024) have made significant we observe the following: (i) larger language contributions to the field of natural language processing models exhibit unseen capabilities compared to (NLP). Despite their advancements, a gap smaller counterparts; (ii) larger language models remains in their specialization for many languages, tend to manifest more biases, produce uncalibrated including Vietnamese. This paper addresses the results, and are more susceptible to the influence development and evaluation of Vietnamese-centric of input prompts; (iii) the quality of training or LLMs. Vietnam, with a population surpassing 100 fine-tuning datasets is the key for unlocking LLM million, ranks as the 16th most populous country performance. Our key contributions include: globally.

Recommender Systems (RSs) provide personalized recommendation Recommender Systems (RSs) [1, 2] which provide personalized service based on user interest, which are widely used in various recommendation service based on user interest are widely used in platforms. However, there are lots of users with sparse interest various platforms such as short video platforms [3, 7, 14], video due to lacking consumption behaviors, which leads to poor recommendation platforms [4, 5], E-commerce platforms [6, 8-11] and social networks results for them. This problem is widespread in [12, 13], serving billions of users. In RSs, Ranking typically large-scale RSs and is particularly difficult to address. To solve uses a Multi-Task Learning model (MTL) [4, 8, 16-21] and lots this problem, we propose a novel solution named User Interest of features to finely predict the scores of various user behaviors Enhancement (UIE) which enhances user interest including user such as click, watching time, fast slide, like and sharing for thousands profile and user history behavior sequences using the enhancement of candidates. The accuracy of the scores outputted by MTL vectors and personalized enhancement vector generated with is crucial for RSs [4]. In RSs, user interest includes user profile the help of other similar users and relevant items based on stream and user history behavior sequences, as shown in Figure 1 and clustering and memory networks from different perspectives. UIE Figure 2, which determines the upper limit of ranking model's not only remarkably improves model performance on the users performance. However, lots of users only have sparse interest due with sparse interest but also significantly enhance model performance to lacking consumption behaviors.