LARS and LAMB have emerged as prominent techniques in Large Batch Learning (LBL), ensuring the stability of AI training. One of the primary challenges in LBL is convergence stability, where the AI agent usually gets trapped into the sharp minimizer. Addressing this challenge, a relatively recent technique, known as warm-up, has been employed. However, warm-up lacks a strong theoretical foundation, leaving the door open for further exploration of more efficacious algorithms. In light of this situation, we conduct empirical experiments to analyze the behaviors of the two most popular optimizers in the LARS family: LARS and LAMB, with and without a warm-up strategy. Our analyses give us a comprehension of the novel LARS, LAMB, and the necessity of a warm-up technique in LBL. Building upon these insights, we propose a novel algorithm called Time Varying LARS (TVLARS), which facilitates robust training in the initial phase without the need for warm-up. Experimental evaluation demonstrates that TVLARS achieves competitive results with LARS and LAMB when warm-up is utilized while surpassing their performance without the warm-up technique.
相關內容
The NLP community typically relies on performance of a model on a held-out test set to assess generalization. Performance drops observed in datasets outside of official test sets are generally attributed to "out-of-distribution'' effects. Here, we explore the foundations of generalizability and study the various factors that affect it, articulating generalizability lessons from clinical studies. In clinical research generalizability depends on (a) internal validity of experiments to ensure controlled measurement of cause and effect, and (b) external validity or transportability of the results to the wider population. We present the need to ensure internal validity when building machine learning models in natural language processing, especially where results may be impacted by spurious correlations in the data. We demonstrate how spurious factors, such as the distance between entities in relation extraction tasks, can affect model internal validity and in turn adversely impact generalization. We also offer guidance on how to analyze generalization failures.
Line attributes such as width and dashing are commonly used to encode information. However, many questions on the perception of line attributes remain, such as how many levels of attribute variation can be distinguished or which line attributes are the preferred choices for which tasks. We conducted three studies to develop guidelines for using stylized lines to encode scalar data. In our first study, participants drew stylized lines to encode uncertainty information. Uncertainty is usually visualized alongside other data. Therefore, alternative visual channels are important for the visualization of uncertainty. Additionally, uncertainty -- e.g., in weather forecasts -- is a familiar topic to most people. Thus, we picked it for our visualization scenarios in study 1. We used the results of our study to determine the most common line attributes for drawing uncertainty: Dashing, luminance, wave amplitude, and width. While those line attributes were especially common for drawing uncertainty, they are also commonly used in other areas. In studies 2 and 3, we investigated the discriminability of the line attributes determined in study 1. Studies 2 and 3 did not require specific application areas; thus, their results apply to visualizing any scalar data in line attributes. We evaluated the just-noticeable differences (JND) and derived recommendations for perceptually distinct line levels. We found that participants could discriminate considerably more levels for the line attribute width than for wave amplitude, dashing, or luminance.
With the rapid development of Artificial Intelligent Internet of Things (AIoT), the image data from AIoT devices has been witnessing the explosive increasing. In this paper, a novel deep image semantic communication model is proposed for the efficient image communication in AIoT. Particularly, at the transmitter side, a high-precision image semantic segmentation algorithm is proposed to extract the semantic information of the image to achieve significant compression of the image data. At the receiver side, a semantic image restoration algorithm based on Generative Adversarial Network (GAN) is proposed to convert the semantic image to a real scene image with detailed information. Simulation results demonstrate that the proposed image semantic communication model can improve the image compression ratio and recovery accuracy by 71.93% and 25.07% on average in comparison with WebP and CycleGAN, respectively. More importantly, our demo experiment shows that the proposed model reduces the total delay by 95.26% in the image communication, when comparing with the original image transmission.
In this work we consider the hybrid Data-Driven Computational Mechanics (DDCM) approach, in which a smooth constitutive manifold is reconstructed to obtain a well-behaved nonlinear optimization problem (NLP) rather than the much harder discrete-continous NLP (DCNLP) of the direct DDCM approach. The key focus is on the addition of geometric inequality constraints to the hybrid DDCM formulation. Therein, the required constraint force leads to a contact problem in the form of a mathematical program with complementarity constraints (MPCC), a problem class that is still less complex than the DCNLP. For this MPCC we propose a heuristic quick-shot solution approach, which can produce verifiable solutions by solving up to four NLPs. We perform various numerical experiments on three different contact problems of increasing difficulty to demonstrate the potential and limitations of this approach.
Training Generative Adversarial Networks (GANs) remains a challenging problem. The discriminator trains the generator by learning the distribution of real/generated data. However, the distribution of generated data changes throughout the training process, which is difficult for the discriminator to learn. In this paper, we propose a novel method for GANs from the viewpoint of online continual learning. We observe that the discriminator model, trained on historically generated data, often slows down its adaptation to the changes in the new arrival generated data, which accordingly decreases the quality of generated results. By treating the generated data in training as a stream, we propose to detect whether the discriminator slows down the learning of new knowledge in generated data. Therefore, we can explicitly enforce the discriminator to learn new knowledge fast. Particularly, we propose a new discriminator, which automatically detects its retardation and then dynamically masks its features, such that the discriminator can adaptively learn the temporally-vary distribution of generated data. Experimental results show our method outperforms the state-of-the-art approaches.
The integration of Artificial Intelligence (AI) into education is a recent development, with chatbots emerging as a noteworthy addition to this transformative landscape. As online learning platforms rapidly advance, students need to adapt swiftly to excel in this dynamic environment. Consequently, understanding the acceptance of chatbots, particularly those employing Large Language Model (LLM) such as Chat Generative Pretrained Transformer (ChatGPT), Google Bard, and other interactive AI technologies, is of paramount importance. However, existing research on chatbots in education has overlooked key behavior-related aspects, such as Optimism, Innovativeness, Discomfort, Insecurity, Transparency, Ethics, Interaction, Engagement, and Accuracy, creating a significant literature gap. To address this gap, this study employs Partial Least Squares Structural Equation Modeling (PLS-SEM) to investigate the determinant of chatbots adoption in education among students, considering the Technology Readiness Index (TRI) and Technology Acceptance Model (TAM). Utilizing a five-point Likert scale for data collection, we gathered a total of 185 responses, which were analyzed using R-Studio software. We established 12 hypotheses to achieve its objectives. The results showed that Optimism and Innovativeness are positively associated with Perceived Ease of Use (PEOU) and Perceived Usefulness (PU). Conversely, Discomfort and Insecurity negatively impact PEOU, with only Insecurity negatively affecting PU. These findings provide insights for future technology designers, elucidating critical user behavior factors influencing chatbots adoption and utilization in educational contexts.
Large Language Models (LLMs) have emerged as powerful tools in the field of Natural Language Processing (NLP) and have recently gained significant attention in the domain of Recommendation Systems (RS). These models, trained on massive amounts of data using self-supervised learning, have demonstrated remarkable success in learning universal representations and have the potential to enhance various aspects of recommendation systems by some effective transfer techniques such as fine-tuning and prompt tuning, and so on. The crucial aspect of harnessing the power of language models in enhancing recommendation quality is the utilization of their high-quality representations of textual features and their extensive coverage of external knowledge to establish correlations between items and users. To provide a comprehensive understanding of the existing LLM-based recommendation systems, this survey presents a taxonomy that categorizes these models into two major paradigms, respectively Discriminative LLM for Recommendation (DLLM4Rec) and Generative LLM for Recommendation (GLLM4Rec), with the latter being systematically sorted out for the first time. Furthermore, we systematically review and analyze existing LLM-based recommendation systems within each paradigm, providing insights into their methodologies, techniques, and performance. Additionally, we identify key challenges and several valuable findings to provide researchers and practitioners with inspiration.
Knowledge plays a critical role in artificial intelligence. Recently, the extensive success of pre-trained language models (PLMs) has raised significant attention about how knowledge can be acquired, maintained, updated and used by language models. Despite the enormous amount of related studies, there still lacks a unified view of how knowledge circulates within language models throughout the learning, tuning, and application processes, which may prevent us from further understanding the connections between current progress or realizing existing limitations. In this survey, we revisit PLMs as knowledge-based systems by dividing the life circle of knowledge in PLMs into five critical periods, and investigating how knowledge circulates when it is built, maintained and used. To this end, we systematically review existing studies of each period of the knowledge life cycle, summarize the main challenges and current limitations, and discuss future directions.
The dominating NLP paradigm of training a strong neural predictor to perform one task on a specific dataset has led to state-of-the-art performance in a variety of applications (eg. sentiment classification, span-prediction based question answering or machine translation). However, it builds upon the assumption that the data distribution is stationary, ie. that the data is sampled from a fixed distribution both at training and test time. This way of training is inconsistent with how we as humans are able to learn from and operate within a constantly changing stream of information. Moreover, it is ill-adapted to real-world use cases where the data distribution is expected to shift over the course of a model's lifetime. The first goal of this thesis is to characterize the different forms this shift can take in the context of natural language processing, and propose benchmarks and evaluation metrics to measure its effect on current deep learning architectures. We then proceed to take steps to mitigate the effect of distributional shift on NLP models. To this end, we develop methods based on parametric reformulations of the distributionally robust optimization framework. Empirically, we demonstrate that these approaches yield more robust models as demonstrated on a selection of realistic problems. In the third and final part of this thesis, we explore ways of efficiently adapting existing models to new domains or tasks. Our contribution to this topic takes inspiration from information geometry to derive a new gradient update rule which alleviate catastrophic forgetting issues during adaptation.
ASR (automatic speech recognition) systems like Siri, Alexa, Google Voice or Cortana has become quite popular recently. One of the key techniques enabling the practical use of such systems in people's daily life is deep learning. Though deep learning in computer vision is known to be vulnerable to adversarial perturbations, little is known whether such perturbations are still valid on the practical speech recognition. In this paper, we not only demonstrate such attacks can happen in reality, but also show that the attacks can be systematically conducted. To minimize users' attention, we choose to embed the voice commands into a song, called CommandSong. In this way, the song carrying the command can spread through radio, TV or even any media player installed in the portable devices like smartphones, potentially impacting millions of users in long distance. In particular, we overcome two major challenges: minimizing the revision of a song in the process of embedding commands, and letting the CommandSong spread through the air without losing the voice "command". Our evaluation demonstrates that we can craft random songs to "carry" any commands and the modify is extremely difficult to be noticed. Specially, the physical attack that we play the CommandSongs over the air and record them can success with 94 percentage.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191