2025
Continual Quantization-Aware Pre-Training: When to transition from 16-bit to 1.58-bit pre-training for BitNet language models?
CoRR, February, 2025
FlexDeMo: Decoupled Momentum Optimization for Fully and Hybrid Sharded Training.
CoRR, February, 2025
A Transformer-based Autoregressive Decoder Architecture for Hierarchical Text Classification.
CoRR, January, 2025
When Are 1.58 Bits Enough? A Bottom-up Exploration of Quantization-Aware Training with Ternary Weights.
Proceedings of the 17th International Conference on Agents and Artificial Intelligence, 2025
2024
Research topic displacement and the lack of interdisciplinarity: lessons from the scientific response to COVID-19.
Scientometrics, September, 2024
Development of Similarity Measures From Graph-Structured Bibliographic Metadata: An Application to Identify Scientific Convergence.
IEEE Trans. Engineering Management, 2024
Continual Learning for Encoder-only Language Models via a Discrete Key-Value Bottleneck.
CoRR, 2024
Isotropy Matters: Soft-ZCA Whitening of Embeddings for Semantic Code Search.
CoRR, 2024
Hierarchical Text Classification (HTC) vs. eXtreme Multilabel Classification (XML): Two Sides of the Same Medal.
CoRR, 2024
When are 1.58 bits enough? A Bottom-up Exploration of BitNet Quantization.
CoRR, 2024
Tokenization and Morphology in Multilingual Language Models: A Comparative Analysis of mT5 and ByT5.
CoRR, 2024
Emergent communication and learning pressures in language models: a language evolution perspective.
CoRR, 2024
RADAr: A Transformer-Based Autoregressive Decoder Architecture for Hierarchical Text Classification.
Proceedings of the ECAI 2024 - 27th European Conference on Artificial Intelligence, 19-24 October 2024, Santiago de Compostela, Spain, 2024
POWN: Prototypical Open-World Node Classification.
Proceedings of the Conference on Lifelong Learning Agents, 2024
2023
Lifelong learning on evolving graphs under the constraints of imbalanced classes and new classes.
Neural Networks, July, 2023
Representation Learning for Texts and Graphs: A Unified Perspective on Efficiency, Multimodality, and Adaptability.
PhD thesis, 2023
GenCodeSearchNet: A Benchmark Test Suite for Evaluating Generalization in Programming Language Understanding.
CoRR, 2023
What makes a language easy to deep-learn?
CoRR, 2023
Open-World Lifelong Graph Learning.
Proceedings of the International Joint Conference on Neural Networks, 2023
2022
Recommendations for item set completion: on the semantics of item co-occurrence with data sparsity, input size, and input modalities.
Inf. Retr. J., 2022
Emergent Communication for Understanding Human Language Evolution: What's Missing?
CoRR, 2022
Bag-of-Words vs. Sequence vs. Graph vs. Hierarchy for Single- and Multi-Label Text Classification.
CoRR, 2022
General Cross-Architecture Distillation of Pretrained Language Models into Matrix Embeddings.
Proceedings of the International Joint Conference on Neural Networks, 2022
Bag-of-Words vs. Graph vs. Sequence in Text Classification: Questioning the Necessity of Text-Graphs and the Surprising Strength of a Wide MLP.
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2022
2021
Lifelong Learning in Evolving Graphs with Limited Labeled Data and Unseen Class Detection.
CoRR, 2021
New Students on Sesame Street: What Order-Aware Matrix Embeddings Can Learn from BERT.
CoRR, 2021
Forget me not: A Gentle Reminder to Mind the Simple Multi-Layer Perceptron Baseline for Text Classification.
CoRR, 2021
Lifelong Learning of Graph Neural Networks for Open-World Node Classification.
Proceedings of the International Joint Conference on Neural Networks, 2021
COVID-19++: A Citation-Aware Covid-19 Dataset for the Analysis of Research Dynamics.
Proceedings of the 2021 IEEE International Conference on Big Data (Big Data), 2021
2020
Embeddings from "CBOW Is Not All You Need: Combining CBOW with the Compositional Matrix-Space Model".
Dataset, July, 2020
Lifelong Learning of Graph Neural Networks for Open-World Node Classification.
Dataset, April, 2020
Incremental Training of Graph Neural Networks on Temporal Graphs under Distribution Shift.
CoRR, 2020
ORCID for Wikidata. Data enrichment for scientometric applications.
Proceedings of the 1st Wikidata Workshop (Wikidata 2020) co-located with 19th International Semantic Web Conference(OPub 2020), 2020
2019
Can Graph Neural Networks Go "Online"? An Analysis of Pretraining and Inference.
CoRR, 2019
CBOW Is Not All You Need: Combining CBOW with the Compositional Matrix Space Model.
Proceedings of the 7th International Conference on Learning Representations, 2019
Take it Personally - A Python library for data enrichment for infometrical applications.
Proceedings of the Posters and Demo Track of the 15th International Conference on Semantic Systems co-located with 15th International Conference on Semantic Systems (SEMANTiCS 2019), Karlsruhe, Germany, September 9th - to, 2019
Inductive Learning of Concept Representations from Library-Scale Bibliographic Corpora.
Proceedings of the 49. Jahrestagung der Gesellschaft für Informatik, 50 Jahre Gesellschaft für Informatik, 2019
What If We Encoded Words as Matrices and Used Matrix Multiplication as Composition Function?
Proceedings of the 49. Jahrestagung der Gesellschaft für Informatik, 50 Jahre Gesellschaft für Informatik, 2019
2018
Multi-Modal Adversarial Autoencoders for Recommendations of Citations and Subject Labels.
Proceedings of the 26th Conference on User Modeling, Adaptation and Personalization, 2018
Using Adversarial Autoencoders for Multi-Modal Automatic Playlist Continuation.
Proceedings of the ACM Recommender Systems Challenge, 2018
Using Deep Learning for Title-Based Semantic Subject Indexing to Reach Competitive Performance to Full-Text.
Proceedings of the 18th ACM/IEEE on Joint Conference on Digital Libraries, 2018
Linked Open Citation Database: Enabling Libraries to Contribute to an Open and Interconnected Citation Graph.
Proceedings of the 18th ACM/IEEE on Joint Conference on Digital Libraries, 2018
Performance Comparison of Ad-Hoc Retrieval Models over Full-Text vs. Titles of Documents.
Proceedings of the Maturity and Innovation in Digital Libraries, 2018
A Case Study of Closed-Domain Response Suggestion with Limited Training Data.
Proceedings of the Database and Expert Systems Applications, 2018
2017
Comparing Titles vs. Full-text for Multi-Label Classification of Scientific Papers and News Articles.
CoRR, 2017
Using Titles vs. Full-text as Source for Automated Semantic Document Annotation.
Proceedings of the Knowledge Capture Conference, 2017
Word Embeddings for Practical Information Retrieval.
Proceedings of the 47. Jahrestagung der Gesellschaft für Informatik, 2017