Related papers: Enabling tabular deep learning when $d \gg n$ with…
Relational databases store much of the world's structured information, and they are essential for driving complex predictive applications. However, deep learning progress on relational data remains limited, as conventional approaches…
The remarkable success of Deep Learning approaches is often based and demonstrated on large public datasets. However, when applying such approaches to internal, private datasets, one frequently faces challenges arising from structural…
Recent advancements in tabular deep learning (DL) have led to substantial performance improvements, surpassing the capabilities of traditional models. With the adoption of techniques from natural language processing (NLP), such as language…
Recent methods based on pre-trained language models have exhibited superior performance over tabular tasks (e.g., tabular NLI), despite showing inherent problems such as not using the right evidence and inconsistent predictions across…
Table reasoning, a task to answer questions by reasoning over data presented in tables, is an important topic due to the prevalence of knowledge stored in tabular formats. Recent solutions use Large Language Models (LLMs), exploiting the…
Today, there are two major understandings for graph convolutional networks, i.e., in the spectral and spatial domain. But both lack transparency. In this work, we introduce a new understanding for it -- data augmentation, which is more…
Recently deep learning has been successfully applied to unsupervised active learning. However, current method attempts to learn a nonlinear transformation via an auto-encoder while ignoring the sample relation, leaving huge room to design…
Knowledge graphs often suffer from incompleteness issues, which can be alleviated through information completion. However, current state-of-the-art deep knowledge convolutional embedding models rely on external convolution kernels and…
Preference learning extends the performance of Code LLMs beyond traditional supervised fine-tuning by leveraging relative quality comparisons. In existing approaches, a set of n candidate solutions is evaluated based on test case success…
Recent deep reinforcement learning (DRL) successes rely on end-to-end learning from fixed-size observational inputs (e.g. image, state-variables). However, many challenging and interesting problems in decision making involve observations or…
In recent years, the parameters of backbones of Video Understanding tasks continue to increase and even reach billion-level. Whether fine-tuning a specific task on the Video Foundation Model or pre-training the model designed for the…
The quality of graph-structured data is fundamental to the success of modern graph analysis techniques such as Graph Neural Networks (GNNs). However, real-world graph data is often suboptimal, suffering from issues such as noise and…
Prediction over tabular data is an essential and fundamental problem in many important downstream tasks. However, existing methods either take a data instance of the table independently as input or do not fully utilize the multi-rows…
Tabular data underpins numerous high-impact applications of machine learning from fraud detection to genomics and healthcare. Classical approaches to solving tabular problems, such as gradient boosting and random forests, are widely used by…
Foundation models for tabular data, like TabPFN, achieve strong performance on small datasets when pre-trained solely on synthetic data. We show that this performance can be significantly boosted by a targeted continued pre-training phase.…
The use of automated guided vehicles (AGVs) has played a pivotal role in manufacturing and distribution operations, providing reliable and efficient product handling. In this project, we constructed a deep learning-based pallets detection…
Recent advancements in graph unlearning models have enhanced model utility by preserving the node representation essentially invariant, while using gradient ascent on the forget set to achieve unlearning. However, this approach causes a…
Pretrained deep-learning models are the go-to solution for images or text. However, for tabular data the standard is still to train tree-based models. Indeed, transfer learning on tables hits the challenge of data integration: finding…
Materials data, especially those related to high-temperature properties, pose significant challenges for machine learning models due to extreme skewness, wide feature ranges, modality, and complex relationships. While traditional models…
For many years, link prediction on knowledge graphs (KGs) has been a purely transductive task, not allowing for reasoning on unseen entities. Recently, increasing efforts are put into exploring semi- and fully inductive scenarios, enabling…