Tootfinder

Opt-in global Mastodon full text search. Join the index!

No exact results. Similar results found.
@netzschleuder@social.skewed.de
2026-02-24 13:00:05

at_migrations: Austrian internal migrations (2002-2022)
A network of migrations between municipalities in Austria, from 2002 to 2022. A weighted directed link from source to target indicates a migration flow from these two municipalities. Edges are annotated with migration volume (number of people), nationality, sex, and year.
This network has 2115 nodes and 2908569 edges.
Tags: Social, Economic, Travel, Weighted, Politlcal, Timestamps, Metadata

at_migrations: Austrian internal migrations (2002-2022). 2115 nodes, 2908569 edges. https://networks.skewed.de/net/at_migrations
@netzschleuder@social.skewed.de
2026-02-24 19:00:04

windsurfers: Windsurfers network (1986)
A network of interpersonal contacts among windsurfers in southern California during the Fall of 1986. The edge weights indicate the perception of social affiliations majored by the tasks in which each individual was asked​ to sort cards with other surfer’s name in the order of closeness.
This network has 43 nodes and 336 edges.
Tags: Social, Offline, Weighted

windsurfers: Windsurfers network (1986). 43 nodes, 336 edges. https://networks.skewed.de/net/windsurfers
@arXiv_csLG_bot@mastoxiv.page
2026-02-25 10:38:31

From Isolation to Integration: Building an Adaptive Expert Forest for Pre-Trained Model-based Class-Incremental Learning
Ruiqi Liu, Boyu Diao, Hangda Liu, Zhulin An, Fei Wang, Yongjun Xu
arxiv.org/abs/2602.20911 arxiv.org/pdf/2602.20911 arxiv.org/html/2602.20911
arXiv:2602.20911v1 Announce Type: new
Abstract: Class-Incremental Learning (CIL) requires models to learn new classes without forgetting old ones. A common method is to freeze a pre-trained model and train a new, lightweight adapter for each task. While this prevents forgetting, it treats the learned knowledge as a simple, unstructured collection and fails to use the relationships between tasks. To this end, we propose the Semantic-guided Adaptive Expert Forest (SAEF), a new method that organizes adapters into a structured hierarchy for better knowledge sharing. SAEF first groups tasks into conceptual clusters based on their semantic relationships. Then, within each cluster, it builds a balanced expert tree by creating new adapters from merging the adapters of similar tasks. At inference time, SAEF finds and activates a set of relevant experts from the forest for any given input. The final prediction is made by combining the outputs of these activated experts, weighted by how confident each expert is. Experiments on several benchmark datasets show that SAEF achieves SOTA performance.
toXiv_bot_toot

@netzschleuder@social.skewed.de
2025-12-24 07:00:04

spanish_highschools: Spanish high schools (2023)
Directed networks of friendships obtained through a social survey of spanish high school students.
This network has 378 nodes and 3267 edges.
Tags: Social, Offline, Weighted, Metadata
networks.skewed.de/net/spanish

spanish_highschools: Spanish high schools (2023). 378 nodes, 3267 edges. https://networks.skewed.de/net/spanish_highschools#11_8
@netzschleuder@social.skewed.de
2026-02-22 09:00:06

at_migrations: Austrian internal migrations (2002-2022)
A network of migrations between municipalities in Austria, from 2002 to 2022. A weighted directed link from source to target indicates a migration flow from these two municipalities. Edges are annotated with migration volume (number of people), nationality, sex, and year.
This network has 2115 nodes and 2908569 edges.
Tags: Social, Economic, Travel, Weighted, Politlcal, Timestamps, Metadata

at_migrations: Austrian internal migrations (2002-2022). 2115 nodes, 2908569 edges. https://networks.skewed.de/net/at_migrations
@netzschleuder@social.skewed.de
2025-12-23 01:00:04

advogato: Advogato trust network (2009)
A network of trust relationships among users on Advogato, an online community of open source software developers. Edge direction indicates that node i trusts node j, and edge weight denotes one of four increasing levels of declared trust from i to j: observer (0.4), apprentice (0.6), journeyer (0.8), and master (1.0).
This network has 6541 nodes and 51127 edges.
Tags: Social, Online, Weighted

advogato: Advogato trust network (2009). 6541 nodes, 51127 edges. https://networks.skewed.de/net/advogato
@netzschleuder@social.skewed.de
2026-01-23 13:00:05

foodweb_baywet: Florida cypress wetlands food web (1998)
Networks of carbon exchanges among species in the cypress wetlands of South Florida. One network covers the wet and the other the dry season. Each node represents a taxon (similar to a species), and a directed edge indicates that one taxon uses another as food.
This network has 128 nodes and 2106 edges.
Tags: Biological, Food web, Weighted

foodweb_baywet: Florida cypress wetlands food web (1998). 128 nodes, 2106 edges. https://networks.skewed.de/net/foodweb_baywet
@netzschleuder@social.skewed.de
2026-02-20 23:00:05

residence_hall: ANU Residence Hall network
A network of friendships among students living in a residence hall at Australian National University (date unknown). Edge direction indicates that resident i named resident j as a friend, and edge weight indicates the level of friendship: 5 (best friend), 4 (close friend), 3 (friend), 2, 1.
This network has 217 nodes and 2672 edges.
Tags: Social, Offline, Weighted

residence_hall: ANU Residence Hall network. 217 nodes, 2672 edges. https://networks.skewed.de/net/residence_hall
@netzschleuder@social.skewed.de
2026-01-20 01:00:05

cintestinalis: Tadpole larva brain (C. intestinalis)
Entire connectivity matrix for the complete brain of a larva of Ciona intestinalis. Each directed edge represents a synaptic connection from pre-synaptic cell i to post-synaptic cell j (may not be a neuron). Edge weights represent the cumulative depth of presynaptic contacts in µm.
This network has 205 nodes and 2903 edges.
Tags: Biological, Connectome, Weighted

cintestinalis: Tadpole larva brain (C. intestinalis). 205 nodes, 2903 edges. https://networks.skewed.de/net/cintestinalis
@netzschleuder@social.skewed.de
2026-02-22 02:00:04

advogato: Advogato trust network (2009)
A network of trust relationships among users on Advogato, an online community of open source software developers. Edge direction indicates that node i trusts node j, and edge weight denotes one of four increasing levels of declared trust from i to j: observer (0.4), apprentice (0.6), journeyer (0.8), and master (1.0).
This network has 6541 nodes and 51127 edges.
Tags: Social, Online, Weighted

advogato: Advogato trust network (2009). 6541 nodes, 51127 edges. https://networks.skewed.de/net/advogato