Large Language Models (LLMs) have great success in natural language processing tasks such as response generation. However, their use in tabular data has been limited due to their inferior performance compared to traditional machine learning models (TMLs) such as XGBoost. We find that the pre-trained knowledge of LLMs enables them to interpret new variables that appear in a test without additional training, a capability central to the concept of Out-of-Variable (OOV). From the findings, we propose a Language-Based-Classifier (LBC), a classifier that maximizes the benefits of LLMs to outperform TMLs on OOV tasks. LBC employs three key methodological strategies: 1) Categorical changes to adjust data to better fit the model's understanding, 2) Advanced order and indicator to enhance data representation to the model, and 3) Using verbalizer to map logit scores to classes during inference to generate model predictions. These strategies, combined with the pre-trained knowledge of LBC, emphasize the model's ability to effectively handle OOV tasks. We empirically and theoretically validate the superiority of LBC. LBC is the first study to apply an LLM-based model to OOV tasks. The source code is at https://github.com/sksmssh/LBCforOOVGen

Researchers have developed a new approach that can learn how to train itself and learn new things and outperform the current machine learning systems of drug discovery and design, which in turn could accelerate the search for new disease treatments. This method is called transformational ML or machine learning. It was developed by a team of scientists and researchers from the UK, Sweden, India, and the Netherlands. Through this method, the machines can learn from multiple problems and improve their performance. In recent years, artificial intelligence has transformed medical research by revealing data patterns that can be used to predict new diseases and treatment outcomes for individual patients.

Lucca has developed an interesting tool that generates logical queries automatically. We use them for testing query containment in TML. He also embarked on a small project comparing three theorem provers (Namely, Z3, Vampire and CVC4) finding out that Z3 outclassed all of them but also compares favourably with TML. We continue to work on the performance improvements for TML but it's currently more comparable with other logical solvers out there. Murisi has worked more on documenting the safe subset of datalog that TML supports implementing additional safety checking and fixing some unsafe code that was generated automatically for the interpreter.

The TMLS initiative is dedicated to helping promote the development of AI/ML effectively, and responsibly across all Industries. As well, to help data practitioners, researchers and students fast-track their learning process and develop rewarding careers in the field of ML and AI.

TMLS consists of a community comprised of over 6,000 ML researchers, professionals and entrepreneurs. We'd like to welcome you to join us in celebrating the top achievements in AI Research, AI companies, and applications in industry. Expect 1 day of workshops and 2-days of quality networking, food, drinks, workshops, breakouts, keynotes and Exhibitors. Come expand your network with machine learning experts and further your own personal & professional development in this exciting and rewarding field. We believe these events should be as accessible as possible and set our ticket passes accordingly.

Distance metric learning (DML) aims to find an appropriate way to reveal the underlying data relationship. It is critical in many machine learning, pattern recognition and data mining algorithms, and usually require large amount of label information (such as class labels or pair/triplet constraints) to achieve satisfactory performance. However, the label information may be insufficient in real-world applications due to the high-labeling cost, and DML may fail in this case. Transfer metric learning (TML) is able to mitigate this issue for DML in the domain of interest (target domain) by leveraging knowledge/information from other related domains (source domains). Although achieved a certain level of development, TML has limited success in various aspects such as selective transfer, theoretical understanding, handling complex data, big data and extreme cases. In this survey, we present a systematic review of the TML literature. In particular, we group TML into different categories according to different settings and metric transfer strategies, such as direct metric approximation, subspace approximation, distance approximation, and distribution approximation. A summarization and insightful discussion of the various TML approaches and their applications will be presented. Finally, we indicate some challenges and provide possible future directions.