@article{COSSU2024127960,

title = {Drifting explanations in continual learning},

author = {Andrea Cossu and Francesco Spinnato and Riccardo Guidotti and Davide Bacciu},

url = {https://www.sciencedirect.com/science/article/pii/S0925231224007318},

doi = {https://doi.org/10.1016/j.neucom.2024.127960},

issn = {0925-2312},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

journal = {Neurocomputing},

volume = {597},

pages = {127960},

abstract = {Continual Learning (CL) trains models on streams of data, with the aim of learning new information without forgetting previous knowledge. However, many of these models lack interpretability, making it difficult to understand or explain how they make decisions. This lack of interpretability becomes even more challenging given the non-stationary nature of the data streams in CL. Furthermore, CL strategies aimed at mitigating forgetting directly impact the learned representations. We study the behavior of different explanation methods in CL and propose CLEX (ContinuaL EXplanations), an evaluation protocol to robustly assess the change of explanations in Class-Incremental scenarios, where forgetting is pronounced. We observed that models with similar predictive accuracy do not generate similar explanations. Replay-based strategies, well-known to be some of the most effective ones in class-incremental scenarios, are able to generate explanations that are aligned to the ones of a model trained offline. On the contrary, naive fine-tuning often results in degenerate explanations that drift from the ones of an offline model. Finally, we discovered that even replay strategies do not always operate at best when applied to fully-trained recurrent models. Instead, randomized recurrent models (leveraging on an untrained recurrent component) clearly reduce the drift of the explanations. This discrepancy between fully-trained and randomized recurrent models, previously known only in the context of their predictive continual performance, is more general, including also continual explanations.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{DBLP:journals/corr/abs-2105-06998,

title = {A causal learning framework for the analysis and interpretation of  COVID-19 clinical data},

author = {Elisa Ferrari and Luna Gargani and Greta Barbieri and Lorenzo Ghiadoni and Francesco Faita and Davide Bacciu},

url = {https://arxiv.org/abs/2105.06998, Arxiv},

doi = {doi.org/10.1371/journal.pone.0268327},

year  = {2022},

date = {2022-05-19},

urldate = {2022-05-19},

journal = {Plos One},

volume = {17},

number = {5},

abstract = {We present a workflow for clinical data analysis that relies on Bayesian Structure Learning (BSL), an unsupervised learning approach, robust to noise and biases, that allows to incorporate prior medical knowledge into the learning process and that provides explainable results in the form of a graph showing the causal connections among the analyzed features. The workflow consists in a multi-step approach that goes from identifying the main causes of patient's outcome through BSL, to the realization of a tool suitable for clinical practice, based on a Binary Decision Tree (BDT), to recognize patients at high-risk with information available already at hospital admission time. We evaluate our approach on a feature-rich COVID-19 dataset, showing that the proposed framework provides a schematic overview of the multi-factorial processes that jointly contribute to the outcome. We discuss how these computational findings are confirmed by current understanding of the COVID-19 pathogenesis. Further, our approach yields to a highly interpretable tool correctly predicting the outcome of 85% of subjects based exclusively on 3 features: age, a previous history of chronic obstructive pulmonary disease and the PaO2/FiO2 ratio at the time of arrival to the hospital. The inclusion of additional information from 4 routine blood tests (Creatinine, Glucose, pO2 and Sodium) increases predictive accuracy to 94.5%. },

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Bacciu2022,

title = {Explaining Deep Graph Networks via Input Perturbation},

author = {Davide Bacciu and Danilo Numeroso

},

doi = {10.1109/TNNLS.2022.3165618},

year  = {2022},

date = {2022-04-21},

urldate = {2022-04-21},

journal = {IEEE Transactions on Neural Networks and Learning Systems},

abstract = {Deep Graph Networks are a family of machine learning models for structured data which are finding heavy application in life-sciences (drug repurposing, molecular property predictions) and on social network data (recommendation systems). The privacy and safety-critical nature of such domains motivates the need for developing effective explainability methods for this family of models. So far, progress in this field has been challenged by the combinatorial nature and complexity of graph structures. In this respect, we present a novel local explanation framework specifically tailored to graph data and deep graph networks. Our approach leverages reinforcement learning to generate meaningful local perturbations of the input graph, whose prediction we seek an interpretation for. These perturbed data points are obtained by optimising a multi-objective score taking into account similarities both at a structural level as well as at the level of the deep model outputs. By this means, we are able to populate a set of informative neighbouring samples for the query graph, which is then used to fit an interpretable model for the predictive behaviour of the deep network locally to the query graph prediction. We show the effectiveness of the proposed explainer by a qualitative analysis on two chemistry datasets, TOS and ESOL and by quantitative results on a benchmark dataset for explanations, CYCLIQ.

},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Resta2021,

title = { Occlusion-based Explanations in Deep Recurrent Models for Biomedical Signals },

author = {Michele Resta and Anna Monreale and Davide Bacciu},

editor = {Fabio Aiolli and Mirko Polato},

doi = {10.3390/e23081064},

year  = {2021},

date = {2021-09-01},

urldate = {2021-09-01},

journal = {Entropy},

volume = {23},

number = {8},

pages = {1064},

abstract = { The biomedical field is characterized by an ever-increasing production of sequential data, which often come under the form of biosignals capturing the time-evolution of physiological processes, such as blood pressure and brain activity. This has motivated a large body of research dealing with the development of machine learning techniques for the predictive analysis of such biosignals. Unfortunately, in high-stakes decision making, such as clinical diagnosis, the opacity of machine learning models becomes a crucial aspect to be addressed in order to increase the trust and adoption of AI technology. In this paper we propose a model agnostic explanation method, based on occlusion, enabling the learning of the input influence on the model predictions. We specifically target problems involving the predictive analysis of time-series data and the models which are typically used to deal with data of such nature, i.e. recurrent neural networks. Our approach is able to provide two different kinds of explanations: one suitable for technical experts, who need to verify the quality and correctness of machine learning models, and one suited to physicians, who need to understand the rationale underlying the prediction to take aware decisions. A wide experimentation on different physiological data demonstrate the effectiveness of our approach, both in classification and regression tasks. },

note = {Special issue on Representation Learning},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{BacciuNCA2020,

title = {Topographic mapping for quality inspection and intelligent filtering of smart-bracelet data},

author = {Davide Bacciu and Gioele Bertoncini and Davide Morelli},

doi = {10.1007/s00521-020-05600-4},

year  = {2021},

date = {2021-01-04},

urldate = {2021-01-04},

journal = {Neural Computing Applications},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{aime20Confound,

title = {Measuring the effects of confounders in medical supervised classification problems: the Confounding Index (CI)},

author = {Elisa Ferrari and Alessandra Retico and Davide Bacciu},

url = {https://arxiv.org/abs/1905.08871},

doi = {10.1016/j.artmed.2020.101804},

year  = {2020},

date = {2020-03-01},

journal = {Artificial Intelligence in Medicine},

volume = {103},

abstract = {Over the years, there has been growing interest in using Machine Learning techniques for biomedical data processing. When tackling these tasks, one needs to bear in mind that biomedical data depends on a variety of characteristics, such as demographic aspects (age, gender, etc) or the acquisition technology, which might be unrelated with the target of the analysis. In supervised tasks, failing to match the ground truth targets with respect to such characteristics, called confounders, may lead to very misleading estimates of the predictive performance. Many strategies have been proposed to handle confounders, ranging from data selection, to normalization techniques, up to the use of training algorithm for learning with imbalanced data. However, all these solutions require the confounders to be known a priori. To this aim, we introduce a novel index that is able to measure the confounding effect of a data attribute in a bias-agnostic way. This index can be used to quantitatively compare the confounding effects of different variables and to inform correction methods such as normalization procedures or ad-hoc-prepared learning algorithms. The effectiveness of this index is validated on both simulated data and real-world neuroimaging data. },

keywords = {},

pubstate = {published},

tppubtype = {article}

}