1 code implementation • NeurIPS 2023 • Mononito Goswami, Vedant Sanil, Arjun Choudhry, Arvind Srinivasan, Chalisa Udompanyawit, Artur Dubrawski
We hope that our proposed design space and benchmark enable practitioners to choose the right tools to improve their label quality and that our benchmark enables objective and rigorous evaluation of machine learning tools facing mislabeled data.
no code implementations • 27 Feb 2023 • Zijian Ding, Arvind Srinivasan, Stephen MacNeil, Joel Chan
Cross-domain analogical reasoning is a core creative ability that can be challenging for humans.
1 code implementation • 18 Oct 2022 • Lingxiao Zhao, Saurabh Sawlani, Arvind Srinivasan, Leman Akoglu
This work aims to fill two gaps in the literature: We (1) design GLAM, an end-to-end graph-level anomaly detection model based on GNNs, and (2) focus on unsupervised model selection, which is notoriously hard due to lack of any labels, yet especially critical for deep NN based models with a long list of hyper-parameters.
1 code implementation • 4 Nov 2020 • Arvind Srinivasan, Aprameya Bharadwaj, Aveek Saha, Subramanyam Natarajan
The node features of this graph are used in the task of video retrieval.
no code implementations • 4 Apr 2020 • Arvind Srinivasan, Aprameya Bharadwaj, Manasa Sathyan, S. Natarajan
In this paper we improve the image embeddings generated in the graph neural network solution for few shot learning.