paper-with-me

Papers

DeepKnowledge: Generalisation-Driven Deep Learning Testing

2024-03-25 · Sondess Missaoui, Simos Gerasimou, Nikolaos Matragkas

Despite their unprecedented success, DNNs are notoriously fragile to small shifts in data distribution, demanding effective testing techniques that can assess their dependability. Despite recent advances in DNN testing, there is a lack of systematic testing approaches that assess the DNN's capability to generalise and operate comparably beyond data in their training distribution. We address this gap with DeepKnowledge, a systematic testing methodology for DNN-based systems founded on the theory of knowledge generalisation, which aims to enhance DNN robustness and reduce the residual risk of 'black box' models. Conforming to this theory, DeepKnowledge posits that core computational DNN units, termed Transfer Knowledge neurons, can generalise under domain shift. DeepKnowledge provides an objective confidence measurement on testing activities of DNN given data distribution shifts and uses this information to instrument a generalisation-informed test adequacy criterion to check the transfer knowledge capacity of a test set. Our empirical evaluation of several DNNs, across multiple datasets and state-of-the-art adversarial generation techniques demonstrates the usefulness and effectiveness of DeepKnowledge and its ability to support the engineering of more dependable DNNs. We report improvements of up to 10 percentage points over state-of-the-art coverage criteria for detecting adversarial attacks on several benchmarks, including MNIST, SVHN, and CIFAR.

📄 PDF Abstract BibTeX arXiv:2403.16768

Code (0)

등록된 구현이 없습니다.

Tasks

Deep LearningDNN Testing

Similar Papers 제목 키워드 기반

Out-of-distribution generalisation in spoken language understanding

2024-07-10 · Dejan Porjazovski, Anssi Moisio, Mikko Kurimo

Test data is said to be out-of-distribution (OOD) when it unexpectedly differs from the training data, a common challenge in real-world use cases of machine learning. Although OOD generalisation has gained interest in re…

Spoken Language Understanding

Quantifying Generalisation in Imitation Learning

2025-09-29 · Nathan Gavenski, Odinaldo Rodrigues arxiv

Imitation learning benchmarks often lack sufficient variation between training and evaluation, limiting meaningful generalisation assessment. We introduce Labyrinth, a benchmarking environment designed to test generalisa…

State-of-the-art generalisation research in NLP: A taxonomy and review

2022-10-06 · Dieuwke Hupkes, Mario Giulianelli, Verna Dankers, Mikel Artetxe 외

The ability to generalise well is one of the primary desiderata of natural language processing (NLP). Yet, what 'good generalisation' entails and how it should be evaluated is not well understood, nor are there any evalu…

How Ensembles of Distilled Policies Improve Generalisation in Reinforcement Learning

2025-05-22 · Max Weltevrede, Moritz A. Zanger, Matthijs T. J. Spaan, Wendelin Böhmer

In the zero-shot policy transfer setting in reinforcement learning, the goal is to train an agent on a fixed set of training environments so that it can generalise to similar, but unseen, testing environments. Previous w…

Investigating Generalisation in Continuous Deep Reinforcement Learning

2019-02-19 · Chenyang Zhao, Olivier Sigaud, Freek Stulp, Timothy M. Hospedales

Deep Reinforcement Learning has shown great success in a variety of control tasks. However, it is unclear how close we are to the vision of putting Deep RL into practice to solve real world problems. In particular, commo…

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)