Search

Introduction Interpretation inflexibility has been implicated in a range of mental health problems, including depression, social anxiety, and paranoia. Inflexible interpretation of social situations may be particularly important as it can set the stage for problems in social functioning, a symptom cutting across all three groups of disorders. Methods This study aimed to examine the interrelations among interpretation inflexibility, social functioning impairment, and affective and psychotic symptoms. The study also explored the potential moderating effects of COVID-related preoccupation, as an example of a major stressor, on these relationships. Results Based on a sample recruited from the general population (N = 247), interpretation inflexibility was found to be associated with social functioning impairment, with affective symptoms and paranoia as statistical mediators of the association. These relationships were magnified by ambient stress during the COVID-19 pandemic—a moderated mediation that was found only in relation to affective symptoms but not paranoia. A parallel network analysis further confirmed the moderating effects of COVID-related preoccupation on the relation between interpretation inflexibility and depression. Limitations Measuring ambient stress with a self-report question on COVID-related preoccupation may not be representative of the amount of distress an individual experienced during the pandemic. Also, our mediation models were performed on cross-sectional data, thus not necessarily implying a feed-forward causal mediational relationship. Conclusions These findings highlight the importance of examining social functioning as a crucial outcome, as well as the differential role of stress in modulating social interpretation flexibility with respect to affective vs. psychotic symptoms.

We propose a novel approach for the approximation and transfer of signals across 3D shapes. The proposed solution is based on taking pointwise polynomials of the Fourier-like Laplacian eigenbasis, which provides a compact and expressive representation for general signals defined on the surface. Key to our approach is the construction of a new orthonormal basis upon the set of these linearly dependent polynomials. We analyze the properties of this representation, and further provide a complete analysis of the involved parameters. Our technique results in accurate approximation and transfer of various families of signals between near-isometric and non-isometric shapes, even under poor initialization. Our experiments, showcased on a selection of downstream tasks such as filtering and detail transfer, show that our method is more robust to discretization artifacts, deformation and noise as compared to alternative approaches.

Interpretation bias and inflexibility have been implicated in a wide range of psychopathologies, including affective disorders and disorders involving persecutory ideation. Existing tasks that measure both interpretation bias and inflexibility (which is essential as bias can make individuals appear inflexible) rely heavily on verbal stimuli, which may be suboptimal for certain applications, including neuroimaging and developmental studies. To overcome these limitations, a picture-based task, the Interpretation Inflexibility Task (IIT) was developed to simultaneously assess interpretation bias and inflexibility. The present manuscript demonstrates the strong convergent validity of the IIT and an existing, verbal measure of interpretation bias and inflexibility (the Emotional BADE task), in a general population sample (N = 247). Across both tasks, inflexible negative interpretations (above and beyond interpretation bias) were associated with symptoms of depression, social anxiety, and paranoia. The consistency of this association across stimulus modalities suggests the existence of higher-level cognitive deficits that increase interpretation inflexibility and thereby increase risk for both affective and psychotic symptoms. The IIT provides an innovative and reliable paradigm to investigate this transdiagnostic factor, particularly given its superior suitability for neuroimaging studies.

The pairwise interaction paradigm of graph machine learning has predominantlygoverned the modelling of relational systems. However, graphs alone cannotcapture the multi-level interactions present in many complex systems and theexpressive power of such schemes was proven to be limited. To overcome theselimitations, we propose Message Passing Simplicial Networks (MPSNs), a class ofmodels that perform message passing on simplicial complexes (SCs). Totheoretically analyse the expressivity of our model we introduce a SimplicialWeisfeiler-Lehman (SWL) colouring procedure for distinguishing non-isomorphicSCs. We relate the power of SWL to the problem of distinguishing non-isomorphicgraphs and show that SWL and MPSNs are strictly more powerful than the WL testand not less powerful than the 3-WL test. We deepen the analysis by comparingour model with traditional graph neural networks (GNNs) with ReLU activationsin terms of the number of linear regions of the functions they can represent.We empirically support our theoretical claims by showing that MPSNs candistinguish challenging strongly regular graphs for which GNNs fail and, whenequipped with orientation equivariant layers, they can improve classificationaccuracy in oriented SCs compared to a GNN baseline.

The workshop features presentations of accepted contributions to the RecSys Challenge 2021, organized by Politecnico di Bari, ETH Zürich, Jönköping University, and the data set is provided by Twitter. The challenge focuses on a real-world task of tweet engagement prediction in a dynamic environment. For 2021, the challenge considers four different engagement types: Likes, Retweet, Quote, and replies. This year's challenge brings the problem even closer to Twitter's real recommender systems by introducing latency constraints. We also increases the data size to encourage novel methods. Also, the data density is increased in terms of the graph where users are considered to be nodes and interactions as edges. The goal is twofold: to predict the probability of different engagement types of a target user for a set of Tweets based on heterogeneous input data while providing fair recommendations. In fact, multi-goal optimization considering accuracy and fairness is particularly challenging. However, we believed that the recommendation community was nowadays mature enough to face the challenge of providing accurate and, at the same time, fair recommendations. To this end, Twitter has released a public dataset of close to 1 billion data points, > 40 million each day over 28 days. Week 1-3 will be used for training and week 4 for evaluation and testing. Each datapoint contains the tweet along with engagement features, user features, and tweet features. A peculiarity of this challenge is related to keeping the dataset updated with the platform: if a user deletes a Tweet, or their data from Twitter, the dataset is promptly updated. Moreover, each change in the dataset implied new evaluations of all submissions and the update of the leaderboard metrics. The challenge was well received with 578 registered users, and 386 submissions.

The use of Laplacian eigenfunctions is ubiquitous in a wide range of computer graphics and geometry processing applications. In particular, Laplacian eigenbases allow generalizing the classical Fourier analysis to manifolds. A key drawback of such bases is their inherently global nature, as the Laplacian eigenfunctions carry geometric and topological structure of the entire manifold. In this paper, we introduce a new framework for local spectral shape analysis. We show how to efficiently construct localized orthogonal bases by solving an optimization problem that in turn can be posed as the eigendecomposition of a new operator obtained by a modification of the standard Laplacian. We study the theoretical and computational aspects of the proposed framework and showcase our new construction on the classical problems of shape approximation and correspondence. We obtain significant improvement compared to classical Laplacian eigenbases as well as other alternatives for constructing localized bases.

In this paper, we consider the problem of information transfer across shapes and propose an extension to the widely used functional map representation. Our main observation is that in addition to the vector space structure of the functional spaces, which has been heavily exploited in the functional map framework, the functional algebra (i.e., the ability to take pointwise products of functions) can significantly extend the power of this framework. Equipped with this observation, we show how to improve one of the key applications of functional maps, namely transferring real-valued functions without conversion to point-to-point correspondences. We demonstrate through extensive experiments that by decomposing a given function into a linear combination consisting not only of basis functions but also of their pointwise products, both the representation power and the quality of the function transfer can be improved significantly. Our modification, while computationally simple, allows us to achieve higher transfer accuracy while keeping the size of the basis and the functional map fixed. We also analyze the computational complexity of optimally representing functions through linear combinations of products in a given basis and prove NP-completeness in some general cases. Finally, we argue that the use of function products can have a wide-reaching effect in extending the power of functional maps in a variety of applications, in particular by enabling the transfer of highfrequency functions without changing the representation size or complexity.

We introduce GFrames, a novel local reference frame (LRF) construction for 3D meshes and point clouds. GFrames are based on the computation of the intrinsic gradient of a scalar field defined on top of the input shape. The resulting tangent vector field defines a repeatable tangent direction of the local frame at each point; importantly, it directly inherits the properties and invariance classes of the underlying scalar function, making it remarkably robust under strong sampling artifacts, vertex noise, as well as non-rigid deformations. Existing local descriptors can directly benefit from our repeatable frames, as we showcase in a selection of 3D vision and shape analysis applications where we demonstrate state-of-the-art performance in a variety of challenging settings.