Related papers: Revisiting the field normalization approaches/prac…
Nonnegative matrix factorization (NMF) is widely used for clustering with strong interpretability. Among general NMF problems, symmetric NMF is a special one that plays an important role in graph clustering where each element measures the…
In real-world scenarios, the number of training samples across classes usually subjects to a long-tailed distribution. The conventionally trained network may achieve unexpected inferior performance on the rare class compared to the frequent…
Clustering scientific publications can reveal underlying research structures within bibliographic databases. Graph-based clustering methods, such as spectral, Louvain, and Leiden algorithms, are frequently utilized due to their capacity to…
Label Smoothing (LS) improves model generalization through penalizing models from generating overconfident output distributions. For each training sample the LS strategy smooths the one-hot encoded training signal by distributing its…
Scientometrics is the study of the quantitative aspects of the process of science as a communication system. It is centrally, but not only, concerned with the analysis of citations in the academic literature. In recent years it has come to…
Normalization techniques have been widely used in the field of deep learning due to their capability of enabling higher learning rates and are less careful in initialization. However, the effectiveness of popular normalization technologies…
The journal Impact Factor (IF) is not comparable among fields of Science and Social Science because of systematic differences in publication and citation behaviour across disciplines. In this work, a decomposing of the field aggregate…
Citation analysis of the scientific literature has been used to study and define disciplinary boundaries, to trace the dissemination of knowledge, and to estimate impact. Co-citation, the frequency with which pairs of publications are…
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 evaluation standards for…
The role of semantics in zero-shot learning is considered. The effectiveness of previous approaches is analyzed according to the form of supervision provided. While some learn semantics independently, others only supervise the semantic…
Lighting normalization is a crucial but underexplored restoration task with broad applications. However, existing works often simplify this task within the context of shadow removal, limiting the light sources to one and oversimplifying the…
Code translation is one of the core capabilities of LLMs. However, evaluating the correctness of translations remains difficult, as commonly used metrics such as BLEU measure only syntactic similarity, disregarding program semantics. We…
Despite huge successes on a wide range of tasks, neural networks are known to sometimes struggle to generalise to unseen data. Many approaches have been proposed over the years to promote the generalisation ability of neural networks,…
Deep convolutional neural networks are known to be unstable during training at high learning rate unless normalization techniques are employed. Normalizing weights or activations allows the use of higher learning rates, resulting in faster…
Bibliometrics is successful in measuring impact, because the target is clearly defined: the publishing scientist who is still active and working. Thus, citations are a target-oriented metric which measures impact on science. In contrast,…
Current face recognition systems achieve high progress on several benchmark tests. Despite this progress, recent works showed that these systems are strongly biased against demographic sub-groups. Consequently, an easily integrable solution…
This paper provides a new regularization method which is particularly suitable for linear exponentially ill-posed problems. Under logarithmic source conditions (which have a natural interpretation in terms of Sobolev spaces in the…
In all nontrivial cases renormalization, as it is usually formulated, is not a change of integration variables in the functional integral, plus parameter redefinitions, but a set of replacements, of actions and/or field variables and…
We present a general analysis of the field theoretical properties which guarantee the recovery, at the renormalized level, of symmetries broken by regularization. We also discuss the anomalous case.
Domain generalization methods aim to learn models robust to domain shift with data from a limited number of source domains and without access to target domain samples during training. Popular domain alignment methods for domain…