Histoires Morales: A French Dataset for Assessing Moral Alignment

Aligning language models with human values is crucial, especially as they become more integrated into everyday life. While models are often adapted to user preferences, it is equally important to ensure they align with moral norms and behaviours in real-world social situations. Despite significant progress in languages like English and Chinese, French has seen little attention in this area, leaving a gap in understanding how LLMs handle moral reasoning in this language. To address this gap, we introduce Histoires Morales, a French dataset derived from Moral Stories, created through translation and subsequently refined with the assistance of native speakers to guarantee grammatical accuracy and adaptation to the French cultural context. We also rely on annotations of the moral values within the dataset to ensure their alignment with French norms. Histoires Morales covers a wide range of social situations, including differences in tipping practices, expressions of honesty in relationships, and responsibilities toward animals. To foster future research, we also conduct preliminary experiments on the alignment of multilingual models on French and English data and the robustness of the alignment. We find that while LLMs are generally aligned with human moral norms by default, they can be easily influenced with user-preference optimization for both moral and immoral data.

End-to-end Supervised Prediction of Arbitrary-size Graphs with Partially-Masked Fused Gromov-Wasserstein Matching

We present a novel end-to-end deep learning-based approach for Supervised Graph Prediction (SGP). We introduce an original Optimal Transport (OT)-based loss, the Partially-Masked Fused Gromov-Wasserstein loss (PM-FGW), that allows to directly leverage graph representations such as adjacency and feature matrices. PM-FGW exhibits all the desirable properties for SGP: it is node permutation invariant, sub-differentiable and handles graphs of different sizes by comparing their padded representations as well as their masking vectors. Moreover, we present a flexible transformer-based architecture that easily adapts to different types of input data. In the experimental section, three different tasks, a novel and challenging synthetic dataset (image2graph) and two real-world tasks, image2map and fingerprint2molecule - showcase the efficiency and versatility of the approach compared to competitors.

An investigation of structures responsible for gender bias in BERT and DistilBERT

In recent years, large Transformer-based Pre-trained Language Models (PLM) have changed the Natural Language Processing (NLP) landscape, by pushing the performance boundaries of the state-of-the-art on a wide variety of tasks. However, this performance gain goes along with an increase in complexity, and as a result, the size of such models (up to billions of parameters) represents a constraint for their deployment on embedded devices or short-inference time tasks. To cope with this situation, compressed models emerged (e.g. DistilBERT), democratizing their usage in a growing number of applications that impact our daily lives. A crucial issue is the fairness of the predictions made by both PLMs and their distilled counterparts. In this paper, we propose an empirical exploration of this problem by formalizing two questions: (1) Can we identify the neural mechanism(s) responsible for gender bias in BERT (and by extension DistilBERT)? (2) Does distillation tend to accentuate or mitigate gender bias (e.g. is DistilBERT more prone to gender bias than its uncompressed version, BERT)? Our findings are the following: (I) one cannot identify a specific layer that produces bias; (II) every attention head uniformly encodes bias; except in the context of underrepresented classes with a high imbalance of the sensitive attribute; (III) this subset of heads is different as we re-fine tune the network; (IV) bias is more homogeneously produced by the heads in the distilled model.

Fair Text Classification with Wasserstein Independence

Group fairness is a central research topic in text classification, where reaching fair treatment between sensitive groups (e.g. women vs. men) remains an open challenge. This paper presents a novel method for mitigating biases in neural text classification, agnostic to the model architecture. Considering the difficulty to distinguish fair from unfair information in a text encoder, we take inspiration from adversarial training to induce Wasserstein independence between representations learned to predict our target label and the ones learned to predict some sensitive attribute. Our approach provides two significant advantages. Firstly, it does not require annotations of sensitive attributes in both testing and training data. This is more suitable for real-life scenarios compared to existing methods that require annotations of sensitive attributes at train time. Second, our approach exhibits a comparable or better fairness-accuracy trade-off compared to existing methods.

Understanding deep neural networks through the lens of their non-linearity

The remarkable success of deep neural networks (DNN) is often attributed to their high expressive power and their ability to approximate functions of arbitrary complexity. Indeed, DNNs are highly non-linear models, and activation functions introduced into them are largely responsible for this. While many works studied the expressive power of DNNs through the lens of their approximation capabilities, quantifying the non-linearity of DNNs or of individual activation functions remains an open problem. In this paper, we propose the first theoretically sound solution to track non-linearity propagation in deep neural networks with a specific focus on computer vision applications. Our proposed affinity score allows us to gain insights into the inner workings of a wide range of different architectures and learning paradigms. We provide extensive experimental results that highlight the practical utility of the proposed affinity score and its potential for long-reaching applications.

Mixture of segmentation for heterogeneous functional data

In this paper we consider functional data with heterogeneity in time and in population. We propose a mixture model with segmentation of time to represent this heterogeneity while keeping the functional structure. Maximum likelihood estimator is considered, proved to be identifiable and consistent. In practice, an EM algorithm is used, combined with dynamic programming for the maximization step, to approximate the maximum likelihood estimator. The method is illustrated on a simulated dataset, and used on a real dataset of electricity consumption.

A Survey on Fairness for Machine Learning on Graphs

Nowadays, the analysis of complex phenomena modeled by graphs plays a crucial role in many real-world application domains where decisions can have a strong societal impact. However, numerous studies and papers have recently revealed that machine learning models could lead to potential disparate treatment between individuals and unfair outcomes. In that context, algorithmic contributions for graph mining are not spared by the problem of fairness and present some specific challenges related to the intrinsic nature of graphs: (1) graph data is non-IID, and this assumption may invalidate many existing studies in fair machine learning, (2) suited metric definitions to assess the different types of fairness with relational data and (3) algorithmic challenge on the difficulty of finding a good trade-off between model accuracy and fairness. This survey is the first one dedicated to fairness for relational data. It aims to present a comprehensive review of state-of-the-art techniques in fairness on graph mining and identify the open challenges and future trends. In particular, we start by presenting several sensible application domains and the associated graph mining tasks with a focus on edge prediction and node classification in the sequel. We also recall the different metrics proposed to evaluate potential bias at different levels of the graph mining process; then we provide a comprehensive overview of recent contributions in the domain of fair machine learning for graphs, that we classify into pre-processing, in-processing and post-processing models. We also propose to describe existing graph data, synthetic and real-world benchmarks. Finally, we present in detail five potential promising directions to advance research in studying algorithmic fairness on graphs.

Learning over No-Preferred and Preferred Sequence of Items for Robust Recommendation (Extended Abstract)

This paper is an extended version of [Burashnikova et al., 2021, arXiv: 2012.06910], where we proposed a theoretically supported sequential strategy for training a large-scale Recommender System (RS) over implicit feedback, mainly in the form of clicks. The proposed approach consists in minimizing pairwise ranking loss over blocks of consecutive items constituted by a sequence of non-clicked items followed by a clicked one for each user. We present two variants of this strategy where model parameters are updated using either the momentum method or a gradient-based approach. To prevent updating the parameters for an abnormally high number of clicks over some targeted items (mainly due to bots), we introduce an upper and a lower threshold on the number of updates for each user. These thresholds are estimated over the distribution of the number of blocks in the training set. They affect the decision of RS by shifting the distribution of items that are shown to the users. Furthermore, we provide a convergence analysis of both algorithms and demonstrate their practical efficiency over six large-scale collections with respect to various ranking measures.

Learning over no-Preferred and Preferred Sequence of items for Robust Recommendation

In this paper, we propose a theoretically founded sequential strategy for training large-scale Recommender Systems (RS) over implicit feedback, mainly in the form of clicks. The proposed approach consists in minimizing pairwise ranking loss over blocks of consecutive items constituted by a sequence of non-clicked items followed by a clicked one for each user. We present two variants of this strategy where model parameters are updated using either the momentum method or a gradient-based approach. To prevent from updating the parameters for an abnormally high number of clicks over some targeted items (mainly due to bots), we introduce an upper and a lower threshold on the number of updates for each user. These thresholds are estimated over the distribution of the number of blocks in the training set. The thresholds affect the decision of RS and imply a shift over the distribution of items that are shown to the users. Furthermore, we provide a convergence analysis of both algorithms and demonstrate their practical efficiency over six large-scale collections, both regarding different ranking measures and computational time.

All of the Fairness for Edge Prediction with Optimal Transport

Machine learning and data mining algorithms have been increasingly used recently to support decision-making systems in many areas of high societal importance such as healthcare, education, or security. While being very efficient in their predictive abilities, the deployed algorithms sometimes tend to learn an inductive model with a discriminative bias due to the presence of this latter in the learning sample. This problem gave rise to a new field of algorithmic fairness where the goal is to correct the discriminative bias introduced by a certain attribute in order to decorrelate it from the model's output. In this paper, we study the problem of fairness for the task of edge prediction in graphs, a largely underinvestigated scenario compared to a more popular setting of fair classification. To this end, we formulate the problem of fair edge prediction, analyze it theoretically, and propose an embedding-agnostic repairing procedure for the adjacency matrix of an arbitrary graph with a trade-off between the group and individual fairness. We experimentally show the versatility of our approach and its capacity to provide explicit control over different notions of fairness and prediction accuracy.