Ting Chen

Doubly Sparse: Sparse Mixture of Sparse Experts for Efficient Softmax Inference

2019 · arXiv (Cornell University)

Computations for the softmax function are significantly expensive when the number of output classes is large. In this paper, we present a novel softmax inference speedup method, Doubly Sparse Softmax (DS-Softmax), that leverages sparse mixture …

The Origins and Prevalence of Texture Bias in Convolutional Neural Networks

2019 · arXiv (Cornell University)

Recent work has indicated that, unlike humans, ImageNet-trained CNNs tend to classify images by texture rather than by shape. How pervasive is this bias, and where does it come from? We find that, when trained …

Differentiable Product Quantization for End-to-End Embedding Compression

2020 · International Conference on Machine Learning

Embedding layers are commonly used to map discrete symbols into continuous embedding vectors that reflect their semantic meanings. Despite their effectiveness, the number of parameters in an embedding layer increases linearly with the number of …

Big Self-Supervised Models Advance Medical Image Classification

2021 · arXiv (Cornell University)

Self-supervised pretraining followed by supervised fine-tuning has seen success in image recognition, especially when labeled examples are scarce, but has received limited attention in medical image analysis. This paper studies the effectiveness of self-supervised learning …

Intriguing Properties of Contrastive Losses

2020 · arXiv (Cornell University)

We study three intriguing properties of contrastive learning. First, we generalize the standard contrastive loss to a broader family of losses, and we find that various instantiations of the generalized loss perform similarly under the …

RiskProp: Account Risk Rating on Ethereum via De-anonymous Score and Network Propagation

2023 · arXiv (Cornell University)

As one of the most popular blockchain platforms supporting smart contracts, Ethereum has caught the interest of both investors and criminals. Differently from traditional financial scenarios, executing Know Your Customer verification on Ethereum is rather …

SCVHunter: Smart Contract Vulnerability Detection Based on Heterogeneous Graph Attention Network

2024

Smart contracts are integral to blockchain's growth, but their vulnerabilities pose a significant threat. Traditional vulnerability detection methods rely heavily on expert-defined complex rules that are labor-intensive and dificult to adapt to the explosive expansion …

Design and Application of English Oral Online Dialogue System Based on Reinforcement Learning Algorithm

2025 · Procedia Computer Science

In view of the lack of personalization and interactivity in current oral English learning, a dialogue system based on reinforcement learning is introduced, aiming to improve users’ oral expression ability by dynamically adjusting the learning …

Confidence Fusion With Representation Distribution and Mixture of Experts for Multimodal Radar Target Recognition

2025 · IEEE Transactions on Aerospace and Electronic Systems

Radar target recognition technology based on multimodal fusion provides a comprehensive target description that encompasses not only the target's echo structure but also its physical motion characteristics or other attributes, thereby enhancing recognition performance. However, …

Demystifying and Detecting Cryptographic Defects in Ethereum Smart Contracts

2025

Ethereum has officially provided a set of system-level cryptographic APIs to enhance smart contracts with cryptographic capabilities. These APIs have been utilized in over 10% of Ethereum transactions, motivating developers to implement various on-chain cryptographic …

Task-oriented Dialogue System for Automatic Diagnosis

2018

Zhongyu Wei, Qianlong Liu, Baolin Peng, Huaixiao Tou, Ting Chen, Xuanjing Huang, Kam-fai Wong, Xiangying Dai. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). 2018.

Service Recommendation Based on Attentional Factorization Machine

2019

With the increasing popularity of SOA (Service Oriented Architecture), a large body of innovative applications emerge on the Internet with mashup (e.g., composition of multiple Web APIs is a representative). Recommending suitable Web APIs to …

Graph Contrastive Learning with Augmentations

2020 · arXiv (Cornell University)

Generalizable, transferrable, and robust representation learning on graph-structured data remains a challenge for current graph neural networks (GNNs). Unlike what has been developed for convolutional neural networks (CNNs) for image data, self-supervised learning and pre-training …