Memory-based Temporal Graph Neural Networks are powerful tools in dynami...
Language models pretrained on large collections of tabular data have
dem...
Large language models of code (Code-LLMs) have recently brought tremendo...
Pretrained code language models have enabled great progress towards prog...
The success of self-supervised learning in computer vision and natural
l...
How can we learn effective node representations on textual graphs? Graph...
We introduce STREET, a unified multi-task and multi-domain natural langu...
Large language models (LLMs) have shown impressive performance on comple...
The mixture of Expert (MoE) parallelism is a recent advancement that sca...
Knowledge Graph Question Answering (KGQA) involves retrieving entities a...
For decades, atomistic modeling has played a crucial role in predicting ...
Predicting the responses of a cell under perturbations may bring importa...
Differentially private (DP) optimization is the standard paradigm to lea...
We study the problem of differentially private (DP) fine-tuning of large...
Estimating an individual's potential outcomes under counterfactual treat...
Can we combine heterogenous graph structure with text to learn high-qual...
This paper describes a new method for representing embedding tables of g...
Per-example gradient clipping is a key algorithmic step that enables
pra...
What target labels are most effective for graph neural network (GNN)
tra...
Existing general purpose frameworks for gigantic model training, i.e., m...
Recent work has found that multi-task training with a large number of di...
Sequential recommendation aims to model dynamic user behavior from histo...
Many real world graphs contain time domain information. Temporal Graph N...
This paper studies the item-to-item recommendation problem in recommende...
Graph representation learning has demonstrated improved performance in t...
Graph neural networks (GNN) have shown great success in learning from
gr...
Knowledge Graph Question Answering (KGQA) involves retrieving facts from...
In this work, we benchmark a variety of single- and multi-task graph neu...
The goal of meta-learning is to learn to adapt to a new task with only a...
Consistency training is a popular method to improve deep learning models...
We aim to identify how different components in the KD pipeline affect th...
Many real-world graphs involve different types of nodes and relations be...
Course selection is challenging for students in higher educational
insti...
Collaborative recommendation approaches based on nearest-neighbors are s...
Graph Neural Networks (GNNs) bring the power of deep representation lear...
Graph neural networks (GNNs) constitute a class of deep learning methods...
Graph convolutional network (GCN) based approaches have achieved signifi...
Learning from source code usually requires a large amount of labeled dat...
Recommending relevant items to users is a crucial task on online communi...
Graph representation learning has made major strides over the past decad...
Knowledge tracing (KT) is the problem of modeling each student's mastery...
In recent years, Massive Open Online Courses (MOOCs) have witnessed imme...
Slot-filling refers to the task of annotating individual terms in a quer...
Automated Team Formation is becoming increasingly important for a pletho...
Graph neural networks (GNN) have shown great success in learning from
gr...
As they carry great potential for modeling complex interactions, graph n...
Unsupervised (or self-supervised) graph representation learning is essen...
The coronavirus disease (COVID-19) has claimed the lives of over 350,000...
Learning unsupervised node embeddings facilitates several downstream tas...
Predicting interactions among heterogenous graph structured data has num...