Related papers: Database Normalization via Dual-LLM Self-Refinemen…

The cost of manual data labeling can be a significant obstacle in supervised learning. Data programming (DP) offers a weakly supervised solution for training dataset creation, wherein the outputs of user-defined programmatic labeling…

User and item features of side information are crucial for accurate recommendation. However, the large number of feature dimensions, e.g., usually larger than 10^7, results in expensive storage and computational cost. This prohibits fast…

Fine-tuning Large Language Models (LLMs) adapts a trained model to specific downstream tasks, significantly improving task-specific performance. Supervised Fine-Tuning (SFT) is a common approach, where an LLM is trained to produce desired…

Large language models (LLMs) have significantly advanced the field of natural language processing, while the expensive memory and computation consumption impede their practical deployment. Quantization emerges as one of the most effective…

We propose a simple but effective multi-source domain generalization technique based on deep neural networks by incorporating optimized normalization layers that are specific to individual domains. Our approach employs multiple…

We propose Deep Feature Interpolation (DFI), a new data-driven baseline for automatic high-resolution image transformation. As the name suggests, it relies only on simple linear interpolation of deep convolutional features from pre-trained…

Data normalization is a crucial preprocessing step for enhancing model performance and training stability. In federated learning (FL), where data remains distributed across multiple parties during collaborative model training, normalization…

Large Language Models (LLMs) have made significant progress in assisting users to query databases in natural language. While LLM-based techniques provide state-of-the-art results on many standard benchmarks, their performance significantly…

In the era of big data, ensuring the quality of datasets has become increasingly crucial across various domains. We propose a comprehensive framework designed to automatically assess and rectify data quality issues in any given dataset,…

The re-identification or de-anonymization of users from anonymized data through matching with publicly available correlated user data has raised privacy concerns, leading to the complementary measure of obfuscation in addition to…

ML Data Curation process typically consist of heterogeneous & federated source systems with varied schema structures; requiring curation process to standardize metadata from different schemas to an inter-operable schema. This manual process…

The standard way to teach models is by feeding them lots of data. However, this approach often teaches models incorrect ideas because they pick up on misleading signals in the data. To prevent such misconceptions, we must necessarily…

Data modeling is one of the most difficult tasks in application engineering. The engineer must be aware of the use cases and the required application services and at a certain point of time he has to fix the data model which forms the base…

Database theory and database practice are typically the domain of computer scientists who adopt what may be termed an algorithmic perspective on their data. This perspective is very different than the more statistical perspective adopted by…

In this paper a tool called RDBNorma is proposed, that uses a novel approach to represent a relational database schema and its functional dependencies in computer memory using only one linked list and used for semi-automating the process of…

Machine Learning (ML) based prognostics and health monitoring (PHM) tools provide new opportunities for manufacturers to operate and maintain their equipment in a risk-optimized manner and utilize it more sustainably along its lifecycle.…

Large language models (LLMs) have advanced Text-to-SQL, yet existing solutions still fall short of system-level reliability. The limitation is not merely in individual modules -- e.g., schema linking, reasoning, and verification -- but more…

Denoising Diffusion Probabilistic Models (DDPMs) have significantly advanced generative AI, achieving impressive results in high-quality image and data generation. However, enhancing fidelity without compromising semantic content remains a…

Data-driven applications rely on the correctness of their data to function properly and effectively. Errors in data can be incredibly costly and disruptive, leading to loss of revenue, incorrect conclusions, and misguided policy decisions.…

Normalizing Flows (NFs) have been established as a principled framework for generative modeling. Standard NFs consist of a forward process and a reverse process: the forward process maps data to noise, while the reverse process generates…