Inventor

LIU TIE-YAN

CN50 patents

⚠️ This page may combine multiple inventors who share the name “LIU TIE-YAN”. Patents are grouped by organization below to help distinguish them — per-person disambiguation is on the roadmap.

LIU TIE-YAN

MICROSOFT CORP

Learning a document ranking using a loss function with a rank pair or a query parameter

Distributed hierarchical text classification framework

Co-clustering objects of heterogeneous types

Co-clustering objects of heterogeneous types

Learning a document ranking function using fidelity-based error measurements

Calculating importance of documents factoring historical importance

Method and system for generating a classifier using inter-sample relationships

Predicting community members based on evolution of heterogeneous networks using a best community classifier and a multi-class community classifier

Feature selection for ranking

Correlating categories using taxonomy distance and term space distance

Hierarchy-based propagation of contribution of documents

Supervised rank aggregation based on rankings

Event detection based on evolution of click-through data

Projecting queries and images into a similarity space

Active spam testing system

Ranking of web sites by aggregating web page ranks

Supervised ranking of vertices of a directed graph

Look-ahead document ranking system

Topic distillation via subsite retrieval

Calculating web page importance based on a conditional Markov random walk

Augmenting a training set for document categorization

Calculating global importance of documents based on global hitting times

Supervised rank aggregation based on rankings

Calculating a webpage importance from a web browsing graph

Spectral clustering using sequential matrix compression

Anti-spam tool for browser

Method and system for detecting black frames in a sequence of frames

Listwise ranking

LIU TIE-YAN

Multi-ranker for search

Augmenting a training set for document categorization

Ranking documents based on a series of document graphs

Efficient query clustering using multi-partite graphs

Calculating web page importance based on a conditional markov random walk

Topic distillation via subsite retrieval

Look-ahead document ranking system

Optimizing ranking of documents using continuous conditional random fields

MICROSOFT TECHNOLOGY LICENSING LLC

Learning word embedding using morphological knowledge

Mixed proposal based model training system

Image super-resolution reconstructing

Asychronous training of machine learning model

Optimization of neural network in equivalent class space

WANG TAIFENG

Graph-processing techniques for a MapReduce engine

Data caching for distributed execution computing

User information needs based data selection

Page selection for indexing

GAO BIN

Calculating web page importance

Calculating web page importance based on web behavior model

Forum mining for suspicious link spam sites detection

Active prediction of diverse search intent based upon user browsing behavior

XU JUN

Directly optimizing evaluation measures in learning to rank