Bo Tang

Linear Order Statistic Neuron

2019

Herein, a generalization of the ordered weighted average (OWA) is put forth relative to pattern recognition. The resultant linear order statistic neuron (LOSN) is unique in that it bridges fuzzy sets, specifically fuzzy data/information aggregation, …

Generalized Federated Learning via Sharpness Aware Minimization

2022 · arXiv (Cornell University)

Federated Learning (FL) is a promising framework for performing privacy-preserving, distributed learning with a set of clients. However, the data distribution among clients often exhibits non-IID, i.e., distribution shift, which makes efficient optimization difficult. To …

Graphene/silicon heterojunction for reconfigurable phase-relevant activation function in coherent optical neural networks

2023 · arXiv (Cornell University)

Optical neural networks (ONNs) herald a new era in information and communication technologies and have implemented various intelligent applications. In an ONN, the activation function (AF) is a crucial component determining the network performances and …

Grimoire is All You Need for Enhancing Large Language Models

2024 · arXiv (Cornell University)

In-context Learning (ICL) is one of the key methods for enhancing the performance of large language models on specific tasks by providing a set of few-shot examples. However, the ICL capability of different types of …

LearnSC: An Efficient and Unified Learning-Based Framework for Subgraph Counting Problem

2024

Graphs are valuable data structures used to represent complex relationships between entities in a wide range of applications, such as social networks and chemical reactions. Subgraph counting problem is a well-known hard problem, as its …

Enhancing Diffusion Policies with Distribution-Matching Generator in Offline Reinforcement Learning

2026 · Proceedings of the AAAI Conference on Artificial Intelligence

Offline reinforcement learning (RL) can learn policies from pre-collected offline datasets without interacting with the environment, but it suffers from the issue of out-of-distribution (OOD). Recent methods use the generative adversarial paradigm to learn policies, …