Recently, in our joint research with the Indian Institute of Science, we have developed an AI technology called cost-sensitive self-training that can optimize practical real-world metrics which are complex and present it at NeurIPS 2022. In this blog post, we introduce our joint research.
Paper
- Title: Cost-Sensitive Self-Training for Optimizing Non-Decomposable Metrics (Harsh Rangwani, Shrinivas Ramasubramanian, Sho Takemori, Kato Takashi, Yuhei Umeda, Venkatesh Babu Radhakrishnan)
- Conference: Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS 2022)
- link to the accepted paper