Injecting Domain Knowledge in Neural Networks: A Controlled Experiment on a Constrained Problem

Silvestri, Mattia; Lombardi, Michele; Milano, Michela

doi:10.1007/978-3-030-78230-6_17

Cited by 12 publications

(7 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Injecting domain knowledge in DNNs has been proved to be an effective way to learn complex input-output relations with high accuracy when the available data happen to be scarce and limited [14], such as found in our case.…”

Section: Approachmentioning

confidence: 86%

Deep Learning Based Source Separation Applied To Choir Ensembles

Petermann¹,

Chandna²,

Cuesta³

et al. 2020

Preprint

View full text Add to dashboard Cite

Choral singing is a widely practiced form of ensemble singing wherein a group of people sing simultaneously in polyphonic harmony. The most commonly practiced setting for choir ensembles consists of four parts; Soprano, Alto, Tenor and Bass (SATB), each with its own range of fundamental frequencies (F0s). The task of source separation for this choral setting entails separating the SATB mixture into the constituent parts. Source separation for musical mixtures is well studied and many deep learning based methodologies have been proposed for the same. However, most of the research has been focused on a typical case which consists in separating vocal, percussion and bass sources from a mixture, each of which has a distinct spectral structure. In contrast, the simultaneous and harmonic nature of ensemble singing leads to high structural similarity and overlap between the spectral components of the sources in a choral mixture, making source separation for choirs a harder task than the typical case. This, along with the lack of an appropriate consolidated dataset has led to a dearth of research in the field so far. In this paper we first assess how well some of the recently developed methodologies for musical source separation perform for the case of SATB choirs. We then propose a novel domain-specific adaptation for conditioning the recently proposed U-Net architecture for musical source separation using the fundamental frequency contour of each of the singing groups and demonstrate that our proposed approach surpasses results from domain-agnostic architectures.

show abstract

Section: Approachmentioning

confidence: 86%

Deep Learning Based Source Separation Applied To Choir Ensembles

Petermann¹,

Chandna²,

Cuesta³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Background knowledge has been considered as an indispensable part of language understanding ( (Zhang et al, 2021a;Zhang et al, 2019a;Zhang et al, 2021b;Chen et al, 2021;Zhang et al, 2022b;Silvestri et al, 2021;Zhang et al, 2021c;Yao et al, 2022;Zhang et al, 2022a)), which has inspired knowledge-enhanced models including ERNIE (Tsinghua) (Zhang et al ( Inspired by these works, we propose OntoProtein that integrates external knowledge graphs into protein pre-training. To the best of our knowledge, we are the first to inject gene ontology knowledge into protein language models.…”

Section: Knowledge-enhanced Language Modelsmentioning

confidence: 99%

OntoProtein: Protein Pretraining With Gene Ontology Embedding

Zhang¹,

Bi²,

Liang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Self-supervised protein language models have proved their effectiveness in learning the proteins representations. With the increasing computational power, current protein language models pre-trained with millions of diverse sequences can advance the parameter scale from million-level to billion-level and achieve remarkable improvement. However, those prevailing approaches rarely consider incorporating knowledge graphs (KGs), which can provide rich structured knowledge facts for better protein representations. We argue that informative biology knowledge in KGs can enhance protein representation with external knowledge. In this work, we propose OntoProtein, the first general framework that makes use of structure in GO (Gene Ontology) into protein pre-training models. We construct a novel large-scale knowledge graph that consists of GO and its related proteins, and gene annotation texts or protein sequences describe all nodes in the graph. We propose novel contrastive learning with knowledge-aware negative sampling to jointly optimize the knowledge graph and protein embedding during pre-training. Experimental results show that OntoProtein can surpass state-of-the-art methods with pre-trained protein language models in TAPE benchmark and yield better performance compared with baselines in protein-protein interaction and protein function prediction 1 .

show abstract

“…It is always advisable for scoring systems to provide an explanation of how the score was arrived at. Previous works like (Demajo, Vella, and Dingli 2020;Sokolovska, Chevaleyre, and Zucker 2018) incorporate explainability into scoring systems by combining multiple AI techniques to cater differently for each of the features, learning binning strategies on the features, and perturbing the features so as to compare the variation in the score.…”

Section: Related Workmentioning

confidence: 99%

I Know Therefore I Score: Label-Free Crafting of Scoring Functions using Constraints Based on Domain Expertise

Palakkadavath¹,

Sivaprasad²,

Karande³

et al. 2022

Preprint

View full text Add to dashboard Cite

Several real-life applications require crafting concise, quantitative scoring functions (also called rating systems) from measured observations. For example, an effectiveness score needs to be created for advertising campaigns using a number of engagement metrics. Experts often need to create such scoring functions in the absence of labelled data, where the scores need to reflect business insights and rules as understood by the domain experts. Without a way to capture these inputs systematically, this becomes a time-consuming process involving trial and error. In this paper, we introduce a label-free practical approach to learn a scoring function from multi-dimensional numerical data. The approach incorporates insights and business rules from domain experts in the form of easily observable and specifiable constraints, which are used as weak supervision by a machine learning model. We convert such constraints into loss functions that are optimized simultaneously while learning the scoring function. We examine the efficacy of the approach using a synthetic dataset as well as four real-life datasets, and also compare how it performs vis-a-vis supervised learning models.

show abstract

Injecting Domain Knowledge in Neural Networks: A Controlled Experiment on a Constrained Problem

Cited by 12 publications

References 21 publications

Deep Learning Based Source Separation Applied To Choir Ensembles

Deep Learning Based Source Separation Applied To Choir Ensembles

OntoProtein: Protein Pretraining With Gene Ontology Embedding

I Know Therefore I Score: Label-Free Crafting of Scoring Functions using Constraints Based on Domain Expertise

Contact Info

Product

Resources

About