Interpretable image recognition by constructing transparent embedding space

J Wang, H Liu, X Wang, L Jing - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
Humans usually explain their reasoning (eg classification) by dissecting the image and
pointing out the evidence from these parts to the concepts in their minds. Inspired by this …

Multinomial random forest

J Bai, Y Li, J Li, X Yang, Y Jiang, ST Xia - Pattern Recognition, 2022 - Elsevier
Despite the impressive performance of random forests (RF), its theoretical properties have
not been thoroughly understood. In this paper, we propose a novel RF framework, dubbed …

Mousika: Enable general in-network intelligence in programmable switches by knowledge distillation

G Xie, Q Li, Y Dong, G Duan, Y Jiang… - IEEE INFOCOM 2022 …, 2022 - ieeexplore.ieee.org
Given the power efficiency and Tbps throughput of packet processing, several works are
proposed to offload the decision tree (DT) to programmable switches, ie, in-network …

Towards faithful xai evaluation via generalization-limited backdoor watermark

M Ya, Y Li, T Dai, B Wang, Y Jiang… - The Twelfth International …, 2023 - openreview.net
Saliency-based representation visualization (SRV)($ eg $, Grad-CAM) is one of the most
classical and widely adopted explainable artificial intelligence (XAI) methods for its simplicity …

Born-again tree ensembles

T Vidal, M Schiffer - International conference on machine …, 2020 - proceedings.mlr.press
The use of machine learning algorithms in finance, medicine, and criminal justice can
deeply impact human lives. As a consequence, research into interpretable machine learning …

Training interpretable convolutional neural networks by differentiating class-specific filters

H Liang, Z Ouyang, Y Zeng, H Su, Z He, ST Xia… - Computer Vision–ECCV …, 2020 - Springer
Convolutional neural networks (CNNs) have been successfully used in a range of tasks.
However, CNNs are often viewed as “black-box” and lack of interpretability. One main …

Fast sparse decision tree optimization via reference ensembles

H McTavish, C Zhong, R Achermann… - Proceedings of the …, 2022 - ojs.aaai.org
Sparse decision tree optimization has been one of the most fundamental problems in AI
since its inception and is a challenge at the core of interpretable machine learning. Sparse …

Optimizing deep learning inference on embedded systems through adaptive model selection

VS Marco, B Taylor, Z Wang, Y Elkhatib - ACM Transactions on …, 2020 - dl.acm.org
Deep neural networks (DNNs) are becoming a key enabling technique for many application
domains. However, on-device inference on battery-powered, resource-constrained …

Tnt: An interpretable tree-network-tree learning framework using knowledge distillation

J Li, Y Li, X Xiang, ST Xia, S Dong, Y Cai - Entropy, 2020 - mdpi.com
Deep Neural Networks (DNNs) usually work in an end-to-end manner. This makes the
trained DNNs easy to use, but they remain an ambiguous decision process for every test …

Empowering in-network classification in programmable switches by binary decision tree and knowledge distillation

G Xie, Q Li, G Duan, J Lin, Y Dong… - IEEE/ACM …, 2023 - ieeexplore.ieee.org
Given the high packet processing efficiency of programmable switches (eg, P4 switches of
Tbps), several works are proposed to offload the decision tree (DT) to P4 switches for in …