Pre-training exploits public datasets to pre-train an advanced machine learning model, so that the model can be easily tuned to adapt to various downstream tasks. Pre-training has been extensively explored to mitigate computation and communication resource consumption. Inspired by these advantages, we are the first to explore how model pre-training can mitigate noise detriment in differentially private federated learning (DPFL). DPFL is upgraded from federated learning (FL), the de-facto standard for privacy preservation when training the model across multiple clients owning private data. DPFL introduces differentially private (DP) noises to obfuscate model gradients exposed in FL, which however can considerably impair model accuracy. In our work, we compare head fine-tuning (HT) and full fine-tuning (FT), which are based on pre-training, with scratch training (ST) in DPFL through a comprehensive empirical study. Our experiments tune pre-trained models (obtained by pre-training on ImageNet-1K) with CIFAR-10, CHMNIST and Fashion-MNIST (FMNIST) datasets, respectively. The results demonstrate that HT and FT can significantly mitigate noise influence by diminishing gradient exposure times. In particular, HT outperforms FT when the privacy budget is tight or the model size is large. Visualization and explanation study further substantiates our findings. Our pioneering study introduces a new perspective on enhancing DPFL and expanding its practical applications.

Locating the persons moving through an environment without the necessity of them being equipped with special devices has become vital for many applications including security, IoT, healthcare, etc. Existing device-free indoor localization systems commonly rely on the utilization of Received Signal Strength Indicator (RSSI) and WiFi Channel State Information (CSI) techniques. However, the accuracy of RSSI is adversely affected by environmental factors like multi-path interference and fading. Additionally, the lack of standardization in CSI necessitates the use of specialized hardware and software. In this paper, we present TimeSense, a deep learning-based multi-person device-free indoor localization system that addresses these challenges. TimeSense leverages Time of Flight information acquired by the fine-time measurement protocol of IEEE 802.11-2016 standard. Specifically, the measured round trip time between the transmitter and receiver is influenced by the dynamic changes in the environment induced by human presence. TimeSense effectively detects this anomalous behavior using a stacked denoising auto-encoder model, thereby estimating the user's location. The system incorporates a probabilistic approach on top of the deep learning model to ensure seamless tracking of the users. The evaluation of TimeSene in two realistic environments demonstrates its efficacy, achieving a median localization accuracy of 1.57 and 2.65 meters. This surpasses the performance of state-of-the-art techniques by 49% and 103% in the two testbeds.

In recent years, indoor air pollution has posed a significant threat to our society, claiming over 3.2 million lives annually. Developing nations, such as India, are most affected since lack of knowledge, inadequate regulation, and outdoor air pollution lead to severe daily exposure to pollutants. However, only a limited number of studies have attempted to understand how indoor air pollution affects developing countries like India. To address this gap, we present spatiotemporal measurements of air quality from 30 indoor sites over six months during summer and winter seasons. The sites are geographically located across four regions of type: rural, suburban, and urban, covering the typical low to middle-income population in India. The dataset contains various types of indoor environments (e.g., studio apartments, classrooms, research laboratories, food canteens, and residential households), and can provide the basis for data-driven learning model research aimed at coping with unique pollution patterns in developing countries. This unique dataset demands advanced data cleaning and imputation techniques for handling missing data due to power failure or network outages during data collection. Furthermore, through a simple speech-to-text application, we provide real-time indoor activity labels annotated by occupants. Therefore, environmentalists and ML enthusiasts can utilize this dataset to understand the complex patterns of the pollutants under different indoor activities, identify recurring sources of pollution, forecast exposure, improve floor plans and room structures of modern indoor designs, develop pollution-aware recommender systems, etc.

Electroencephalogram (EEG) has emerged as a cost-effective and efficient method for supporting neurologists in assessing Alzheimer's disease (AD). Existing approaches predominantly utilize handcrafted features or Convolutional Neural Network (CNN)-based methods. However, the potential of the transformer architecture, which has shown promising results in various time series analysis tasks, remains underexplored in interpreting EEG for AD assessment. Furthermore, most studies are evaluated on the subject-dependent setup but often overlook the significance of the subject-independent setup. To address these gaps, we present ADformer, a novel multi-granularity transformer designed to capture temporal and spatial features to learn effective EEG representations. We employ multi-granularity data embedding across both dimensions and utilize self-attention to learn local features within each granularity and global features among different granularities. We conduct experiments across 5 datasets with a total of 525 subjects in setups including subject-dependent, subject-independent, and leave-subjects-out. Our results show that ADformer outperforms existing methods in most evaluations, achieving F1 scores of 75.19% and 93.58% on two large datasets with 65 subjects and 126 subjects, respectively, in distinguishing AD and healthy control (HC) subjects under the challenging subject-independent setup.

Piaget's Theory of Cognitive Development (PTC) posits that the development of cognitive levels forms the foundation for human learning across various abilities. As Large Language Models (LLMs) have recently shown remarkable abilities across a wide variety of tasks, we are curious about the cognitive levels of current LLMs: to what extent they have developed and how this development has been achieved. To this end, we construct a benchmark CogLM (Cognitive Ability Evaluation for Language Model) based on PTC to assess the cognitive levels of LLMs. CogLM comprises 1,220 questions spanning 10 cognitive abilities crafted by more than 20 human experts, providing a comprehensive testbed for the cognitive levels of LLMs. Through extensive experiments across multiple mainstream LLMs with CogLM, we find that: (1) Human-like cognitive abilities have emerged in advanced LLMs (GPT-4), comparable to those of a 20-year-old human. (2) The parameter size and optimization objective are two key factors affecting the cognitive levels of LLMs. (3) The performance on downstream tasks is positively correlated with the level of cognitive abilities. These findings fill the gap in research on the cognitive abilities of LLMs, tracing the development of LLMs from a cognitive perspective and guiding the future direction of their evolution.

Cross-Lingual summarization (CLS) is a sophisticated branch in Natural Language Processing that demands models to accurately translate and summarize articles from different source languages. Despite the improvement of the subsequent studies, This area still needs data-efficient solutions along with effective training methodologies. To the best of our knowledge, there is no feasible solution for CLS when there is no available high-quality CLS data. In this paper, we propose a novel data-efficient approach, ConVerSum, for CLS leveraging the power of contrastive learning, generating versatile candidate summaries in different languages based on the given source document and contrasting these summaries with reference summaries concerning the given documents. After that, we train the model with a contrastive ranking loss. Then, we rigorously evaluate the proposed approach against current methodologies and compare it to powerful Large Language Models (LLMs)- Gemini, GPT 3.5, and GPT 4 proving our model performs better for low-resource languages' CLS. These findings represent a substantial improvement in the area, opening the door to more efficient and accurate cross-lingual summarizing techniques.

Background: As Machine Learning (ML) advances rapidly in many fields, it is being adopted by academics and businesses alike. However, ML has a number of different challenges in terms of maintenance not found in traditional software projects. Identifying what causes these maintainability challenges can help mitigate them early and continue delivering value in the long run without degrading ML performance. Aim: This study aims to identify and synthesise the maintainability challenges in different stages of the ML workflow and understand how these stages are interdependent and impact each other's maintainability. Method: Using a systematic literature review, we screened more than 13000 papers, then selected and qualitatively analysed 56 of them. Results: (i) a catalogue of maintainability challenges in different stages of Data Engineering, Model Engineering workflows and the current challenges when building ML systems are discussed; (ii) a map of 13 maintainability challenges to different interdependent stages of ML that impact the overall workflow; (iii) Provided insights to developers of ML tools and researchers. Conclusions: In this study, practitioners and organisations will learn about maintainability challenges and their impact at different stages of ML workflow. This will enable them to avoid pitfalls and help to build a maintainable ML system. The implications and challenges will also serve as a basis for future research to strengthen our understanding of the ML system's maintainability.

This paper introduces and examines the phenomenon of "visual sycophancy" in multimodal language models, a term we propose to describe these models' tendency to disproportionately favor visually presented information, even when it contradicts their prior knowledge or responses. Our study employs a systematic methodology to investigate this phenomenon: we present models with images of multiple-choice questions, which they initially answer correctly, then expose the same model to versions with visually pre-marked options. Our findings reveal a significant shift in the models' responses towards the pre-marked option despite their previous correct answers. Comprehensive evaluations demonstrate that visual sycophancy is a consistent and quantifiable behavior across various model architectures. Our findings highlight potential limitations in the reliability of these models when processing potentially misleading visual information, raising important questions about their application in critical decision-making contexts.

This paper introduces a new hyper-parameter for Retrieval-Augmented Generation (RAG) systems called Context Window Utilization. RAG systems enhance generative models by incorporating relevant information retrieved from external knowledge bases, improving the factual accuracy and contextual relevance of generated responses. The size of the text chunks retrieved and processed is a critical factor influencing RAG performance. This study aims to identify the optimal chunk size that maximizes answer generation quality. Through systematic experimentation, we analyze the effects of varying chunk sizes on the efficiency and effectiveness of RAG frameworks. Our findings reveal that an optimal chunk size balances the trade-off between providing sufficient context and minimizing irrelevant information. These insights are crucial for enhancing the design and implementation of RAG systems, underscoring the importance of selecting an appropriate chunk size to achieve superior performance.

This study investigates the potential of large language models (LLMs) to provide accurate estimates of concreteness, valence and arousal for multi-word expressions. Unlike previous artificial intelligence (AI) methods, LLMs can capture the nuanced meanings of multi-word expressions. We systematically evaluated ChatGPT-4o's ability to predict concreteness, valence and arousal. In Study 1, ChatGPT-4o showed strong correlations with human concreteness ratings (r =.8) for multi-word expressions. In Study 2, these findings were repeated for valence and arousal ratings of individual words, matching or outperforming previous AI models. Study 3 extended the prevalence and arousal analysis to multi-word expressions and showed promising results despite the lack of large-scale human benchmarks. These findings highlight the potential of LLMs for generating valuable psycholinguistic data related to multiword expressions. To help researchers with stimulus selection, we provide datasets with AI norms of concreteness, valence and arousal for 126,397 English single words and 63,680 multi-word expressions.