This inventor holds 1 USPTO granted patent and 4 published patent applications. Top assignee: Google Inc.. Active years: 2026.
Company Filing History:
Years Active: 2026
Title: Yihe Dong - Innovator in Machine Learning
Introduction
Yihe Dong is an inventor based in New York, NY (US). He is known for his contributions to the field of machine learning, particularly in the areas of temporal counterfactual estimation and multimodal learning. Although he currently holds no granted patents, his innovative ideas are reflected in his latest patent applications.
Latest Patent Applications
Yihe Dong's latest patent applications include "Self-Supervised Learning for Temporal Counterfactual Estimation." This application describes a machine-learned model that features an encoder designed to embed input data into multiple features within an embedding space. The input data comprises various components, including covariate, treatment, and output components. The encoder consists of one or more encoding layers, each containing a temporal attention block and a feature-wise attention block. The temporal attention block is responsible for obtaining the embedded input data and applying temporal causal attention along a time dimension in parallel for each feature, generating temporal embeddings. The feature-wise attention block then uses these temporal embeddings to create component representations, such as covariate, treatment, and output representations.
Another significant application is "Multimodal Learning from Structured and Unstructured Data." This application focuses on a multimodal processing system that can handle both structured and unstructured data. Recognizing that real-world data often varies in form and content, the system includes a model trained to address this inconsistency. It selectively masks data from different modalities during pretraining to learn outputs that remain comparable between masked and unmasked inputs. The model is trained using modality-specific masking objectives and joint modality similarity-based masking objectives, enhancing overall model accuracy.
Conclusion
Yihe Dong is an innovative thinker in the realm of machine learning, with a focus on developing advanced models for data processing. His latest patent applications showcase his commitment to addressing complex challenges in the field. As he continues to explore new ideas, his contributions may significantly impact the future of machine learning.