226 citations · 763 across the 25 of their papers we have counts for
25 papers
STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases
Shirley Wu, Shiyu Zhao, Michihiro Yasunaga +7
Answering real-world complex queries, such as complex product search, often requires accurate retrieval from semi-structured knowledge bases that involve blend of unstructured (e.g…
PyTorch Frame: A Modular Framework for Multi-Modal Tabular Learning
Weihua Hu, Yiwen Yuan, Zecheng Zhang +6
We present PyTorch Frame, a PyTorch-based framework for deep learning over multi-modal tabular data. PyTorch Frame makes tabular deep learning easy by providing a PyTorch-based dat…
GraphMETRO: Mitigating Complex Graph Distribution Shifts via Mixture of Aligned Experts
Shirley Wu, Kaidi Cao, Bruno Ribeiro +2
Graph data are inherently complex and heterogeneous, leading to a high natural diversity of distributional shifts. However, it remains unclear how to build machine learning archite…
Communication-Free Distributed GNN Training with Vertex Cut
Kaidi Cao, Rui Deng, Shirley Wu +3
Training Graph Neural Networks (GNNs) on real-world graphs consisting of billions of nodes and edges is quite challenging, primarily due to the substantial memory needed to store t…
TpuGraphs: A Performance Prediction Dataset on Large Tensor Computational Graphs
Phitchaya Mangpo Phothilimthana, Sami Abu-El-Haija, Kaidi Cao +4
Precise hardware performance models play a crucial role in code optimizations. They can assist compilers in making heuristic decisions or aid autotuners in identifying the optimal…
Learning Large Graph Property Prediction via Graph Segment Training
Kaidi Cao, Phitchaya Mangpo Phothilimthana, Sami Abu-El-Haija +5
Learning to predict properties of large graphs is challenging because each prediction requires the knowledge of an entire graph, while the amount of memory available during trainin…
AutoTransfer: AutoML with Knowledge Transfer -- An Application to Graph Neural Networks
Kaidi Cao, Jiaxuan You, Jiaju Liu +1
AutoML has demonstrated remarkable success in finding an effective neural architecture for a given machine learning task defined by a specific dataset and an evaluation metric. How…
Relational Multi-Task Learning: Modeling Relations between Data and Tasks
Kaidi Cao, Jiaxuan You, Jure Leskovec
A key assumption in multi-task learning is that at the inference time the multi-task model only has access to a given data point but not to the data point's labels from other tasks…
TuneUp: A Simple Improved Training Strategy for Graph Neural Networks
Weihua Hu, Kaidi Cao, Kexin Huang +4
Despite recent advances in Graph Neural Networks (GNNs), their training strategies remain largely under-explored. The conventional training strategy learns over all nodes in the or…
Learning Large-scale Subsurface Simulations with a Hybrid Graph Network Simulator
Tailin Wu, Qinchen Wang, Yinan Zhang +7
Subsurface simulations use computational models to predict the flow of fluids (e.g., oil, water, gas) through porous media. These simulations are pivotal in industrial applications…
Learning Backward Compatible Embeddings
Weihua Hu, Rajas Bansal, Kaidi Cao +3
Embeddings, low-dimensional vector representation of objects, are fundamental in building modern machine learning systems. In industrial settings, there is usually an embedding tea…
Open-World Semi-Supervised Learning
Kaidi Cao, Maria Brbic, Jure Leskovec
A fundamental limitation of applying semi-supervised learning in real-world settings is the assumption that unlabeled test data contains only classes previously encountered in the…
Coresets for Robust Training of Neural Networks against Noisy Labels
Baharan Mirzasoleiman, Kaidi Cao, Jure Leskovec
Modern neural networks have the capacity to overfit noisy labels frequently found in real-world datasets. Although great progress has been made, existing techniques are limited in…
Concept Learners for Few-Shot Learning
Kaidi Cao, Maria Brbic, Jure Leskovec
Developing algorithms that are able to generalize to a novel task given only a few labeled examples represents a fundamental challenge in closing the gap between machine- and human…
Heteroskedastic and Imbalanced Deep Learning with Adaptive Regularization
Kaidi Cao, Yining Chen, Junwei Lu +3
Real-world large-scale datasets are heteroskedastic and imbalanced -- labels have varying levels of uncertainty and label distributions are long-tailed. Heteroskedasticity and imba…
Learning Temporal Action Proposals With Fewer Labels
Jingwei Ji, Kaidi Cao, Juan Carlos Niebles
Temporal action proposals are a common module in action detection pipelines today. Most current methods for training action proposal modules rely on fully supervised approaches tha…
Delving Deep Into Hybrid Annotations for 3D Human Recovery in the Wild
Yu Rong, Ziwei Liu, Cheng Li +2
Though much progress has been achieved in single-image 3D human recovery, estimating 3D model for in-the-wild images remains a formidable challenge. The reason lies in the fact tha…
Few-Shot Video Classification via Temporal Alignment
Kaidi Cao, Jingwei Ji, Zhangjie Cao +2
There is a growing interest in learning a model which could recognize novel classes with only a few labeled examples. In this paper, we propose Temporal Alignment Module (TAM), a n…
Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss
Kaidi Cao, Colin Wei, Adrien Gaidon +2
Deep learning algorithms can fare poorly when the training dataset suffers from heavy class-imbalance but the testing criterion requires good generalization on less frequent classe…
Disentangling Content and Style via Unsupervised Geometry Distillation
Wayne Wu, Kaidi Cao, Cheng Li +2
It is challenging to disentangle an object into two orthogonal spaces of content and style since each can influence the visual observation differently and unpredictably. It is rare…
TransGaGa: Geometry-Aware Unsupervised Image-to-Image Translation
Wayne Wu, Kaidi Cao, Cheng Li +2
Unsupervised image-to-image translation aims at learning a mapping between two visual domains. However, learning a translation across large geometry variations always ends up with…
CariGANs: Unpaired Photo-to-Caricature Translation
Kaidi Cao, Jing Liao, Lu Yuan
Facial caricature is an art form of drawing faces in an exaggerated way to convey humor or sarcasm. In this paper, we propose the first Generative Adversarial Network (GAN) for unp…
Interstellar: Using Halide's Scheduling Language to Analyze DNN Accelerators
Xuan Yang, Mingyu Gao, Qiaoyi Liu +9
We show that DNN accelerator micro-architectures and their program mappings represent specific choices of loop order and hardware parallelism for computing the seven nested loops o…
Pose-Robust Face Recognition via Deep Residual Equivariant Mapping
Kaidi Cao, Yu Rong, Cheng Li +2
Face recognition achieves exceptional success thanks to the emergence of deep learning. However, many contemporary face recognition models still perform relatively poor in processi…