Tootfinder

ProxyFL: A Proxy-Guided Framework for Federated Semi-Supervised Learning
Duowen Chen, Yan Wang
https://arxiv.org/abs/2602.21078 https://arxiv.org/pdf/2602.21078 https://arxiv.org/html/2602.21078
arXiv:2602.21078v1 Announce Type: new
Abstract: Federated Semi-Supervised Learning (FSSL) aims to collaboratively train a global model across clients by leveraging partially-annotated local data in a privacy-preserving manner. In FSSL, data heterogeneity is a challenging issue, which exists both across clients and within clients. External heterogeneity refers to the data distribution discrepancy across different clients, while internal heterogeneity represents the mismatch between labeled and unlabeled data within clients. Most FSSL methods typically design fixed or dynamic parameter aggregation strategies to collect client knowledge on the server (external) and / or filter out low-confidence unlabeled samples to reduce mistakes in local client (internal). But, the former is hard to precisely fit the ideal global distribution via direct weights, and the latter results in fewer data participation into FL training. To this end, we propose a proxy-guided framework called ProxyFL that focuses on simultaneously mitigating external and internal heterogeneity via a unified proxy. I.e., we consider the learnable weights of classifier as proxy to simulate the category distribution both locally and globally. For external, we explicitly optimize global proxy against outliers instead of direct weights; for internal, we re-include the discarded samples into training by a positive-negative proxy pool to mitigate the impact of potentially-incorrect pseudo-labels. Insight experiments & theoretical analysis show our significant performance and convergence in FSSL.
toXiv_bot_toot

new_zealand_collab: New Zealand scientific collaborations (2015)
A network of scientific collaborations among institutions in New Zealand. Nodes are institutions (universities, organizations, etc.), and two nodes i,j are connected if Scopus lists at least one publication with authors at institutions i and j, in the period 2010-2015. Edges are weighted by the number of such collaborations. Nodes are annotated with the categorical type of institution.
This network has 1511 nodes an…

Read NPR's annotated fact check of President Trump's State of the Union (NPR)
https://www.npr.org/2026/02/24/nx-s1-5716277/trump-state-union-fact-check
http://www.memeorandum.com/260225/p48#a260225p48

blumenau_drug: Blumenau drug interactions (2019)
A network of drug-drug interactions, extracted from 18 months of electronic health records (EHRs) from the city of Blumenau in Southern Brazil. Nodes are annotated with drug information (separate file), and edges are weighted by the severity of the interaction, along with other information.
This network has 75 nodes and 181 edges.
Tags: Biological, Drug interactions, Weighted, Metadata

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

Via the AI4LAM Slack: An Extreme Multi-label Text Classification (XMTC) Library Dataset: What if we took "Use of Practical AI in Digital Libraries" seriously? https://arxiv.org/abs/2603.10876

An Extreme Multi-label Text Classification (XMTC) Library Dataset: What if we took "Use of Practical AI in Digital Libraries" seriously?
Subject indexing is vital for discovery but hard to sustain at scale and across languages. We release a large bilingual (English/German) corpus of catalog records annotated with the Integrated Authority File (GND), plus a machine-actionable GND taxonomy. The resource enables ontology-aware multi-label classification, mapping text to authority terms, and agent-assisted cataloging with reproducible, authority-grounded evaluation. We provide a brief statistical profile and qualitative error analys…

nematode_mammal: Global nematode–mammal interactions (2018)
A global interaction web of interactions between nematodes and their host mammal species, extracted from the helminthR package and dataset. Nodes are annotated with species-level information.
This network has 30516 nodes and 146683 edges.
Tags: Biological, Food web, Unweighted, Metadata

corporate_directors: Global corporate directors (2016)
Bipartite network of directors and the companies on whose boards they sit, spanning 54 countries worldwide, constructed from data collected by the Financial Times (c. Sept. 2016). Person nodes are annotated with age and gender. Company nodes are annotated with their country, sector, industry, and number of employees.
This network has 356638 nodes and 377060 edges.
Tags: Economic, Governance, Unweighted, Metadata

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

eu_procurements: EU procurement contract networks (2008-2016)
A bipartite network of public EU procurement contracts, from 2008 to 2016, between issuing buyers (public institutions such as a ministry or city hall) and supplying winners (a private firm). Contracts are aggregated into annual snapshots, edges are annotated with contract value information. Nodes are annotated with location information, including country of origin.
This network has 839824 nodes and 4098711 edges.