Chao Ma

Global Convergence of Gradient Descent for Deep Linear Residual Networks

2019 · arXiv (Cornell University)

We analyze the global convergence of gradient descent for deep linear residual networks by proposing a new initialization: zero-asymmetric (ZAS) initialization. It is motivated by avoiding stable manifolds of saddle points. We prove that under …

DGL-KE: Training Knowledge Graph Embeddings at Scale

2020 · arXiv (Cornell University)

Knowledge graphs have emerged as a key abstraction for organizing information in diverse domains and their embeddings are increasingly used to harness their information in various information retrieval and machine learning tasks. However, the ever …

Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks

2019 · arXiv (Cornell University)

Advancing research in the emerging field of deep graph learning requires new tools to support tensor computation over graphs. In this paper, we present the design principles and implementation of Deep Graph Library (DGL). DGL …

A new structure for representing and tracking version information in a deep time knowledge graph

2020 · Computers & Geosciences

Ontologies and vocabularies are an effective way to promote data interoperability in open data and open science. The deep time knowledge graph is one of the most discussed and studied topics in geoscience ontologies and …

Understanding Causality with Large Language Models: Feasibility and Opportunities

2023 · arXiv (Cornell University)

We assess the ability of large language models (LLMs) to answer causal questions by analyzing their strengths and weaknesses against three types of causal question. We believe that current LLMs can answer causal questions with …

Reflection Invariance Learning for Few-shot Semantic Segmentation

2023 · arXiv (Cornell University)

Few-shot semantic segmentation (FSS) aims to segment objects of unseen classes in query images with only a few annotated support images. Existing FSS algorithms typically focus on mining category representations from the single-view support to …

Domain-Controlled Prompt Learning

2023 · arXiv (Cornell University)

Large pre-trained vision-language models, such as CLIP, have shown remarkable generalization capabilities across various tasks when appropriate text prompts are provided. However, adapting these models to specific domains, like remote sensing images (RSIs), medical images, …

Refined Meteorological Forecasting of Power Grid based on Numerical Analysis

2025

Meteorological disasters were one of the natural factors that were most likely to cause serious accidents in the power grid, so the demand for the accuracy, accuracy and timeliness of meteorological service early warning in …

Person-Job Fit

2018 · ACM Transactions on Management Information Systems

Person-Job Fit is the process of matching the right talent for the right job by identifying talent competencies that are required for the job. While many qualitative efforts have been made in related fields, it …