The GH-EXIN neural network for hierarchical clustering

Cirrincione, Giansalvo; Ciravegna, Gabriele; Barbiero, Pietro; Randazzo, Vincenzo; Pasero, Eros

doi:10.1016/j.neunet.2019.07.018

Cited by 26 publications

(22 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first index used for assessing the clustering performances is the Peak Signal-to-Noise Ratio (P SN R) [130], which is one of the most famous and widely used measures of the fidelity of a representation (i.e., a clustering) w.r.t. the original signal.…”

Section: Quality Indicesmentioning

confidence: 99%

“…where a(i) is the average distance of the ith sample from the samples in the same cluster, b(i) is the minimum among the mean distances of the ith sample from the samples in the other clusters, and C is the cardinality of the current dataset. While DB checks compactness and cluster separation, the S index estimates if, on average, samples are correctly assigned to the nearest neighbouring cluster [130]. Because of Eq.…”

Section: Quality Indicesmentioning

confidence: 99%

“…9, S ∈ [−1, 1], where a high value indicates a good clustering. The last metric used in the experiments was the harmonic mean (PE ) between cluster efficiency and purity [130]. The two metrics were computed, averaging their scores obtained for each predicted cluster and for each groundtruth label.…”

Section: Quality Indicesmentioning

confidence: 99%

See 2 more Smart Citations

A survey on data integration for multi-omics sample clustering

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Quality Indicesmentioning

confidence: 99%

Section: Quality Indicesmentioning

confidence: 99%

See 1 more Smart Citation

A survey on data integration for multi-omics sample clustering

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…PersLay extends the neural network DeepSet [21] and introduces new layers to accept as an input any diagram of unordered points. In other related work, deep learning was recently applied to outputs of hierarchical clustering [22][23][24] and to 0-dimensional persistence [25,26].…”

Section: Related Work On Isometry Shape Recognition and Topological Data Analysismentioning

confidence: 99%

“…PersLay extends the neural network DeepSet [19] for unordered sets and introduces new layers to specifically handle persistence diagrams, as well as a new form of representing such permutationinvariant layers. In other related work deep learning was recently applied to outputs of hierarchical clustering [20], [21], [22] and to 0-dimensional persistence [23], [24].…”

Section: Single-linkage Clustering and The Invariant Mergegram Of A Dendrogrammentioning

confidence: 99%

Isometry Invariant Shape Recognition of Projectively Perturbed Point Clouds by the Mergegram Extending 0D Persistence

Yury

Kurlin

2021

Mathematics

View full text Add to dashboard Cite

Rigid shapes should be naturally compared up to rigid motion or isometry, which preserves all inter-point distances. The same rigid shape can be often represented by noisy point clouds of different sizes. Hence, the isometry shape recognition problem requires methods that are independent of a cloud size. This paper studies stable-under-noise isometry invariants for the recognition problem stated in the harder form when given clouds can be related by affine or projective transformations. The first contribution is the stability proof for the invariant mergegram, which completely determines a single-linkage dendrogram in general position. The second contribution is the experimental demonstration that the mergegram outperforms other invariants in recognizing isometry classes of point clouds extracted from perturbed shapes in images.

show abstract

Generating Neural Archetypes to Instruct Fast and Interpretable Decisions

Barbiero

Ciravegna

Cirrincione

et al. 2020

Advances in Intelligent Systems and Computing

Self Cite

View full text Add to dashboard Cite

Deep learning methods are highly accurate, yet their opaque decision process prevents them from earning full human trust. Concept-based models aim to address this issue by learning tasks based on a set of human-understandable concepts. However, state-of-the-art concept-based models rely on high-dimensional concept embedding representations which lack a clear semantic meaning, thus questioning the interpretability of their decision process. To overcome this limitation, we propose the Deep Concept Reasoner (DCR), the first interpretable concept-based model that builds upon concept embeddings. In DCR, neural networks do not make task predictions directly, but they build syntactic rule structures using concept embeddings. DCR then executes these rules on meaningful concept truth degrees to provide a final interpretable and semantically-consistent prediction in a differentiable manner. Our experiments show that DCR: (i) improves up to +25% w.r.t. state-of-the-art interpretable concept-based models on challenging benchmarks (ii) discovers meaningful logic rules matching known ground truths even in the absence of concept supervision during training, and (iii), facilitates the generation of counterfactual examples providing the learnt rules as guidance.

show abstract

The GH-EXIN neural network for hierarchical clustering

Cited by 26 publications

References 21 publications

A survey on data integration for multi-omics sample clustering

A survey on data integration for multi-omics sample clustering

Isometry Invariant Shape Recognition of Projectively Perturbed Point Clouds by the Mergegram Extending 0D Persistence

Generating Neural Archetypes to Instruct Fast and Interpretable Decisions

Contact Info

Product

Resources

About