cs.LG

arXiv:2501.00057v1 Announce Type: new Abstract: Although deep learning models have had great success in natural language processing and computer vision, we do not observe comparable improvements in the case of tabular data, which is still the most common data type used in biological, industrial and financial applications. In particular, it is challenging to transfer large-scale pre-trained models to downstream tasks defined on small tabular datasets. To address this, we propose VisTabNet -- a cross-modal transfer learning method, which allows for adapting Vision Transformer (ViT) with pre-trained weights to process tabular data. By projecting tabular inputs to patch embeddings acceptable by ViT, we can directly apply a pre-trained Transformer Encoder to tabular inputs. This approach eliminates the conceptual cost of designing a suitable architecture for processing tabular data, while reducing the computational cost of training the model from scratch. Experimental results on multiple small tabular datasets (less than 1k samples) demonstrate VisTabNet's superiority, outperforming both traditional ensemble methods and recent deep learning models. The proposed method goes beyond conventional transfer learning practice and shows that pre-trained image models can be transferred to solve tabular problems, extending the boundaries of transfer learning.

arXiv:2501.00070v1 Announce Type: new Abstract: Recent work has demonstrated that semantics specified by pretraining data influence how representations of different concepts are organized in a large language model (LLM). However, given the open-ended nature of LLMs, e.g., their ability to in-context learn, we can ask whether models alter these pretraining semantics to adopt alternative, context-specified ones. Specifically, if we provide in-context exemplars wherein a concept plays a different role than what the pretraining data suggests, do models reorganize their representations in accordance with these novel semantics? To answer this question, we take inspiration from the theory of conceptual role semantics and define a toy "graph tracing" task wherein the nodes of the graph are referenced via concepts seen during training (e.g., apple, bird, etc.) and the connectivity of the graph is defined via some predefined structure (e.g., a square grid). Given exemplars that indicate traces of random walks on the graph, we analyze intermediate representations of the model and find that as the amount of context is scaled, there is a sudden re-organization from pretrained semantic representations to in-context representations aligned with the graph structure. Further, we find that when reference concepts have correlations in their semantics (e.g., Monday, Tuesday, etc.), the context-specified graph structure is still present in the representations, but is unable to dominate the pretrained structure. To explain these results, we analogize our task to energy minimization for a predefined graph topology, providing evidence towards an implicit optimization process to infer context-specified semantics. Overall, our findings indicate scaling context-size can flexibly re-organize model representations, possibly unlocking novel capabilities.

arXiv:2501.00050v1 Announce Type: new Abstract: Network intrusion detection systems face significant challenges in identifying emerging attack patterns, especially when limited data samples are available. To address this, we propose a novel Multi-Space Prototypical Learning (MSPL) framework tailored for few-shot attack detection. The framework operates across multiple metric spaces-Euclidean, Cosine, Chebyshev, and Wasserstein distances-integrated through a constrained weighting scheme to enhance embedding robustness and improve pattern recognition. By leveraging Polyak-averaged prototype generation, the framework stabilizes the learning process and effectively adapts to rare and zero-day attacks. Additionally, an episodic training paradigm ensures balanced representation across diverse attack classes, enabling robust generalization. Experimental results on benchmark datasets demonstrate that MSPL outperforms traditional approaches in detecting low-profile and novel attack types, establishing it as a robust solution for zero-day attack detection.

arXiv:2501.00056v1 Announce Type: new Abstract: Air pollution in cities, especially NO\textsubscript{2}, is linked to numerous health problems, ranging from mortality to mental health challenges and attention deficits in children. While cities globally have initiated policies to curtail emissions, real-time monitoring remains challenging due to limited environmental sensors and their inconsistent distribution. This gap hinders the creation of adaptive urban policies that respond to the sequence of events and daily activities affecting pollution in cities. Here, we demonstrate how city CCTV cameras can act as a pseudo-NO\textsubscript{2} sensors. Using a predictive graph deep model, we utilised traffic flow from London's cameras in addition to environmental and spatial factors, generating NO\textsubscript{2} predictions from over 133 million frames. Our analysis of London's mobility patterns unveiled critical spatiotemporal connections, showing how specific traffic patterns affect NO\textsubscript{2} levels, sometimes with temporal lags of up to 6 hours. For instance, if trucks only drive at night, their effects on NO\textsubscript{2} levels are most likely to be seen in the morning when people commute. These findings cast doubt on the efficacy of some of the urban policies currently being implemented to reduce pollution. By leveraging existing camera infrastructure and our introduced methods, city planners and policymakers could cost-effectively monitor and mitigate the impact of NO\textsubscript{2} and other pollutants.

arXiv:2501.00064v1 Announce Type: new Abstract: Respiratory sound classification plays a pivotal role in diagnosing respiratory diseases. While deep learning models have shown success with various respiratory sound datasets, our experiments indicate that models trained on one dataset often fail to generalize effectively to others, mainly due to data collection and annotation \emph{inconsistencies}. To address this limitation, we introduce \emph{Lungmix}, a novel data augmentation technique inspired by Mixup. Lungmix generates augmented data by blending waveforms using loudness and random masks while interpolating labels based on their semantic meaning, helping the model learn more generalized representations. Comprehensive evaluations across three datasets, namely ICBHI, SPR, and HF, demonstrate that Lungmix significantly enhances model generalization to unseen data. In particular, Lungmix boosts the 4-class classification score by up to 3.55\%, achieving performance comparable to models trained directly on the target dataset.

arXiv:2501.00068v1 Announce Type: new Abstract: The exponential growth of data-intensive applications has placed unprecedented demands on modern storage systems, necessitating dynamic and efficient optimization strategies. Traditional heuristics employed for storage performance optimization often fail to adapt to the variability and complexity of contemporary workloads, leading to significant performance bottlenecks and resource inefficiencies. To address these challenges, this paper introduces RL-Storage, a novel reinforcement learning (RL)-based framework designed to dynamically optimize storage system configurations. RL-Storage leverages deep Q-learning algorithms to continuously learn from real-time I/O patterns and predict optimal storage parameters, such as cache size, queue depths, and readahead settings[1]. The proposed framework operates within the storage kernel, ensuring minimal latency and low computational overhead. Through an adaptive feedback mechanism, RL-Storage dynamically adjusts critical parameters, achieving efficient resource utilization across a wide range of workloads. Experimental evaluations conducted on a range of benchmarks, including RocksDB and PostgreSQL, demonstrate significant improvements, with throughput gains of up to 2.6x and latency reductions of 43% compared to baseline heuristics. Additionally, RL-Storage achieves these performance enhancements with a negligible CPU overhead of 0.11% and a memory footprint of only 5 KB, making it suitable for seamless deployment in production environments. This work underscores the transformative potential of reinforcement learning techniques in addressing the dynamic nature of modern storage systems. By autonomously adapting to workload variations in real time, RL-Storage provides a robust and scalable solution for optimizing storage performance, paving the way for next-generation intelligent storage infrastructures.

arXiv:2501.00042v1 Announce Type: new Abstract: This paper describes a memory-efficient transformer model designed to drive a reduction in memory usage and execution time by substantial orders of magnitude without impairing the model's performance near that of the original model. Recently, new architectures of transformers were presented, focused on parameter efficiency and computational optimization; however, such models usually require considerable resources in terms of hardware when deployed in real-world applications on edge devices. This approach addresses this concern by halving embedding size and applying targeted techniques such as parameter pruning and quantization to optimize the memory footprint with minimum sacrifices in terms of accuracy. Experimental results include a 52% reduction in memory usage and a 33% decrease in execution time, resulting in better efficiency than state-of-the-art models. This work compared our model with existing compelling architectures, such as MobileBERT and DistilBERT, and proved its feasibility in the domain of resource-friendly deep learning architectures, mainly for applications in real-time and in resource-constrained applications.

arXiv:2501.00048v1 Announce Type: new Abstract: Every year in the United States, 800,000 individuals suffer a stroke - one person every 40 seconds, with a death occurring every four minutes. While individual factors vary, certain predictors are more prevalent in determining stroke risk. As strokes are the second leading cause of death and disability worldwide, predicting stroke likelihood based on lifestyle factors is crucial. Showing individuals their stroke risk could motivate lifestyle changes, and machine learning offers solutions to this prediction challenge. Neural networks excel at predicting outcomes based on training features like lifestyle factors, however, they're not the only option. Logistic regression models can also effectively compute the likelihood of binary outcomes based on independent variables, making them well-suited for stroke prediction. This analysis will compare both neural networks (dense and convolutional) and logistic regression models for stroke prediction, examining their pros, cons, and differences to develop the most effective predictor that minimizes false negatives.

arXiv:2501.00052v1 Announce Type: new Abstract: Mean Field Control Games (MFCGs) provide a powerful theoretical framework for analyzing systems of infinitely many interacting agents, blending elements from Mean Field Games (MFGs) and Mean Field Control (MFC). However, solving the coupled Hamilton-Jacobi-Bellman and Fokker-Planck equations that characterize MFCG equilibria remains a significant computational challenge, particularly in high-dimensional or complex environments. This paper presents a scalable deep Reinforcement Learning (RL) approach to approximate equilibrium solutions of MFCGs. Building on previous works, We reformulate the infinite-agent stochastic control problem as a Markov Decision Process, where each representative agent interacts with the evolving mean field distribution. We use the actor-critic based algorithm from a previous paper (Angiuli et.al., 2024) as the baseline and propose several versions of more scalable and efficient algorithms, utilizing techniques including parallel sample collection (batching); mini-batching; target network; proximal policy optimization (PPO); generalized advantage estimation (GAE); and entropy regularization. By leveraging these techniques, we effectively improved the efficiency, scalability, and training stability of the baseline algorithm. We evaluate our method on a linear-quadratic benchmark problem, where an analytical solution to the MFCG equilibrium is available. Our results show that some versions of our proposed approach achieve faster convergence and closely approximate the theoretical optimum, outperforming the baseline algorithm by an order of magnitude in sample efficiency. Our work lays the foundation for adapting deep RL to solve more complicated MFCGs closely related to real life, such as large-scale autonomous transportation systems, multi-firm economic competition, and inter-bank borrowing problems.

arXiv:2501.00054v1 Announce Type: new Abstract: Security concerns surrounding text-to-image diffusion models have driven researchers to unlearn inappropriate concepts through fine-tuning. Recent fine-tuning methods typically align the prediction distributions of unsafe prompts with those of predefined text anchors. However, these techniques exhibit a considerable performance trade-off between eliminating undesirable concepts and preserving other concepts. In this paper, we systematically analyze the impact of diverse text anchors on unlearning performance. Guided by this analysis, we propose AdvAnchor, a novel approach that generates adversarial anchors to alleviate the trade-off issue. These adversarial anchors are crafted to closely resemble the embeddings of undesirable concepts to maintain overall model performance, while selectively excluding defining attributes of these concepts for effective erasure. Extensive experiments demonstrate that AdvAnchor outperforms state-of-the-art methods. Our code is publicly available at https://anonymous.4open.science/r/AdvAnchor.

arXiv:2501.00061v1 Announce Type: new Abstract: Model merging has attracted significant attention as a powerful paradigm for model reuse, facilitating the integration of task-specific models into a singular, versatile framework endowed with multifarious capabilities. Previous studies, predominantly utilizing methods such as Weight Average (WA), have shown that model merging can effectively leverage pretrained models without the need for laborious retraining. However, the inherent heterogeneity among models poses a substantial constraint on its applicability, particularly when confronted with discrepancies in model architectures. To overcome this challenge, we propose an innovative model merging framework designed for heterogeneous models, encompassing both depth and width heterogeneity. To address depth heterogeneity, we introduce a layer alignment strategy that harmonizes model layers by segmenting deeper models, treating consecutive layers with similar representations as a cohesive segment, thus enabling the seamless merging of models with differing layer depths. For width heterogeneity, we propose a novel elastic neuron zipping algorithm that projects the weights from models of varying widths onto a common dimensional space, eliminating the need for identical widths. Extensive experiments validate the efficacy of these proposed methods, demonstrating that the merging of structurally heterogeneous models can achieve performance levels comparable to those of homogeneous merging, across both vision and NLP tasks. Our code is publicly available at https://github.com/zju-vipa/training_free_heterogeneous_model_merging.

arXiv:2501.00063v1 Announce Type: new Abstract: The financial industry is increasingly seeking robust methods to address the challenges posed by data scarcity and low signal-to-noise ratios, which limit the application of deep learning techniques in stock market analysis. This paper presents two innovative generative model-based approaches to synthesize stock data, specifically tailored for different scenarios within the A-share market in China. The first method, a sector-based synthesis approach, enhances the signal-to-noise ratio of stock data by classifying the characteristics of stocks from various sectors in China's A-share market. This method employs an Approximate Non-Local Total Variation algorithm to smooth the generated data, a bandpass filtering method based on Fourier Transform to eliminate noise, and Denoising Diffusion Implicit Models to accelerate sampling speed. The second method, a recursive stock data synthesis approach based on pattern recognition, is designed to synthesize data for stocks with short listing periods and limited comparable companies. It leverages pattern recognition techniques and Markov models to learn and generate variable-length stock sequences, while introducing a sub-time-level data augmentation method to alleviate data scarcity issues.We validate the effectiveness of these methods through extensive experiments on various datasets, including those from the main board, STAR Market, Growth Enterprise Market Board, Beijing Stock Exchange, NASDAQ, NYSE, and AMEX. The results demonstrate that our synthesized data not only improve the performance of predictive models but also enhance the signal-to-noise ratio of individual stock signals in price trading strategies. Furthermore, the introduction of sub-time-level data significantly improves the quality of synthesized data.

arXiv:2501.00065v1 Announce Type: new Abstract: Objective: Predicting children's future levels of externalizing problems helps to identify children at risk and guide targeted prevention. Existing studies have shown that mothers providing support in response to children's dysregulation was associated with children's lower levels of externalizing problems. The current study aims to evaluate and improve the accuracy of predicting children's externalizing problems with mother-child interaction dynamics. Method: This study used mother-child interaction dynamics during a challenging puzzle task to predict children's externalizing problems six months later (N=101, 46 boys, Mage=57.41 months, SD=6.58). Performance of the Residual Dynamic Structural Equation Model (RDSEM) was compared with the Attention-based Sequential Behavior Interaction Modeling (ASBIM) model, developed using the deep learning techniques. Results: The RDSEM revealed that children whose mothers provided more autonomy support after increases of child defeat had lower levels of externalizing problems. Five-fold cross-validation showed that the RDSEM had good prediction accuracy. The ASBIM model further improved prediction accuracy, especially after including child inhibitory control as a personalized individual feature. Conclusions: The dynamic process of mother-child interaction provides important information for predicting children's externalizing problems, especially maternal autonomy supportive response to child defeat. The deep learning model is a useful tool to further improve prediction accuracy.

arXiv:2501.00066v1 Announce Type: new Abstract: We investigate the adversarial robustness of LLMs in transfer learning scenarios. Through comprehensive experiments on multiple datasets (MBIB Hate Speech, MBIB Political Bias, MBIB Gender Bias) and various model architectures (BERT, RoBERTa, GPT-2, Gemma, Phi), we reveal that transfer learning, while improving standard performance metrics, often leads to increased vulnerability to adversarial attacks. Our findings demonstrate that larger models exhibit greater resilience to this phenomenon, suggesting a complex interplay between model size, architecture, and adaptation methods. Our work highlights the crucial need for considering adversarial robustness in transfer learning scenarios and provides insights into maintaining model security without compromising performance. These findings have significant implications for the development and deployment of LLMs in real-world applications where both performance and robustness are paramount.

arXiv:2501.00029v1 Announce Type: new Abstract: We review the recent literature (January 2022- October 2024) in South Asian languages on text-based language processing, multimodal models, and speech processing, and provide a spotlight analysis focused on 21 low-resource South Asian languages, namely Saraiki, Assamese, Balochi, Bhojpuri, Bodo, Burmese, Chhattisgarhi, Dhivehi, Gujarati, Kannada, Kashmiri, Konkani, Khasi, Malayalam, Meitei, Nepali, Odia, Pashto, Rajasthani, Sindhi, and Telugu. We identify trends, challenges, and future research directions, using a step-wise approach that incorporates relevance classification and clustering based on large language models (LLMs). Our goal is to provide a breadth-first overview of the recent developments in South Asian language technologies to NLP researchers interested in working with South Asian languages.

arXiv:2501.00032v1 Announce Type: new Abstract: Large language models (LLMs) have transformed the way we think about language understanding and generation, enthralling both researchers and developers. However, deploying LLMs for inference has been a significant challenge due to their unprecedented size and resource requirements. While quantizing model weights to sub-byte precision has emerged as a promising solution to ease memory pressure, the group quantization formats commonly used for LLM quantization have significant compute overheads and a resource-intensive dequantization process. As a result, a higher proportion of compute instructions do not perform multiplies, i.e., real work, rendering them unsuitable for meeting the required latency requirements for LLMs deployed on commodity CPUs. In this work, we propose a set of highly optimized kernels to accelerate LLM inference and unleash the full potential of CPUs, particularly Arm CPUs. These kernels amortize the cost of loading the operands and the cost of weight unpacking across multiple output rows. This, along with the introduction of an optimized interleaved group data layout for weights and decompression path optimizations to reduce unnecessary operations and dequantization overhead while maximizing the use of vector and matrix multiply operations, significantly improves the efficiency of MAC operations. Furthermore, we present a groupwise non-uniform codebook-based quantization method for ultra-low-precision quantization of LLMs to better match non-uniform patterns in their weight distributions, demonstrating better throughput during token generation while ensuring better quality than the state-of-the-art. Applying these improvements to 4-bit LLMs results in a 3-3.2x improvement in prompt processing and a 2x improvement in autoregressive decoding on Arm CPUs, compared to LLaMA.cpp-based solution. The optimized kernels are available at https://github.com/ggerganov/llama.cpp.

arXiv:2501.00045v1 Announce Type: new Abstract: This study investigates the effectiveness of transfer learning in machine translation across diverse linguistic families by evaluating five distinct language pairs. Leveraging pre-trained models on high-resource languages, these models were fine-tuned on low-resource languages, examining variations in hyperparameters such as learning rate, batch size, number of epochs, and weight decay. The research encompasses language pairs from different linguistic backgrounds: Semitic (Modern Standard Arabic - Levantine Arabic), Bantu (Hausa - Zulu), Romance (Spanish - Catalan), Slavic (Slovakian - Macedonian), and language isolates (Eastern Armenian - Western Armenian). Results demonstrate that transfer learning is effective across different language families, although the impact of hyperparameters varies. A moderate batch size (e.g., 32) is generally more effective, while very high learning rates can disrupt model training. The study highlights the universality of transfer learning in multilingual contexts and suggests that consistent hyperparameter settings can simplify and enhance the efficiency of multilingual model training.

arXiv:2501.00046v1 Announce Type: new Abstract: This paper presents a combined approach to enhancing the effectiveness of Jacobian-Free Newton-Krylov (JFNK) method by deep reinforcement learning (DRL) in identifying fixed points within the 2D Kuramoto-Sivashinsky Equation (KSE). JFNK approach entails a good initial guess for improved convergence when searching for fixed points. With a properly defined reward function, we utilise DRL as a preliminary step to enhance the initial guess in the converging process. We report new results of fixed points in the 2D KSE which have not been reported in the literature. Additionally, we explored control optimization for the 2D KSE to navigate the system trajectories between known fixed points, based on parallel reinforcement learning techniques. This combined method underscores the improved JFNK approach to finding new fixed-point solutions within the context of 2D KSE, which may be instructive for other high-dimensional dynamical systems.

arXiv:2501.00051v1 Announce Type: new Abstract: Digital twin (DT) technology has emerged as a transformative approach to simulate, predict, and optimize the behavior of physical systems, with applications that span manufacturing, healthcare, climate science, and more. However, the development of DT models often faces challenges such as high data requirements, integration complexity, and limited adaptability to dynamic changes in physical systems. This paper presents a new method inspired by dynamic data-driven applications systems (DDDAS), called the dynamic data-driven generative of digital twins framework (DDD-GenDT), which combines the physical system with LLM, allowing LLM to act as DT to interact with the physical system operating status and generate the corresponding physical behaviors. We apply DDD-GenDT to the computer numerical control (CNC) machining process, and we use the spindle current measurement data in the NASA milling wear data set as an example to enable LLMs to forecast the physical behavior from historical data and interact with current observations. Experimental results show that in the zero-shot prediction setting, the LLM-based DT can adapt to the change in the system, and the average RMSE of the GPT-4 prediction is 0.479A, which is 4.79% of the maximum spindle motor current measurement of 10A, with little training data and instructions required. Furthermore, we analyze the performance of DDD-GenDT in this specific application and their potential to construct digital twins. We also discuss the limitations and challenges that may arise in practical implementations.

arXiv:2501.00072v1 Announce Type: new Abstract: Neural algorithmic reasoning is an emerging area of machine learning that focuses on building neural networks capable of solving complex algorithmic tasks. Recent advancements predominantly follow the standard supervised learning paradigm -- feeding an individual problem instance into the network each time and training it to approximate the execution steps of a classical algorithm. We challenge this mode and propose a novel open-book learning framework. In this framework, whether during training or testing, the network can access and utilize all instances in the training dataset when reasoning for a given instance. Empirical evaluation is conducted on the challenging CLRS Algorithmic Reasoning Benchmark, which consists of 30 diverse algorithmic tasks. Our open-book learning framework exhibits a significant enhancement in neural reasoning capabilities. Further, we notice that there is recent literature suggesting that multi-task training on CLRS can improve the reasoning accuracy of certain tasks, implying intrinsic connections between different algorithmic tasks. We delve into this direction via the open-book framework. When the network reasons for a specific task, we enable it to aggregate information from training instances of other tasks in an attention-based manner. We show that this open-book attention mechanism offers insights into the inherent relationships among various tasks in the benchmark and provides a robust tool for interpretable multi-task training.