Hyperdimensional Computing for Fake News Detection: A High-Efficiency Approach for Large-Scale Data
Resumo
The massive spread of misinformation, intensified during the COVID-19 pandemic, has heightened the need for fake news detection systems that operate at scale. However, the state of the art is dominated by Transformer and Large Language Model architectures with high computational cost, energy consumption, and limited edge applicability. This paper investigates Hyperdimensional Computing (HDC) as an alternative paradigm, framing the problem as a trade-off between accuracy and energy efficiency. We evaluate five HDC variants against classical Machine Learning baselines and Transformers (BERT, RoBERTa) across three benchmarks (ISOT, COVID-19, and a binarized FEVER), totaling 160,051 instances. Transformers achieve the highest F1-score in all three datasets, reaching 99.80% on ISOT, whereas the best HDC configuration achieves 95.77%. Despite this accuracy gap, HDC substantially reduces training time, with reductions of approximately 5.5× to 13× relative to BERT. Under the TDP-based energy estimation adopted in this study, these time reductions translate directly into equivalent estimated energy reductions. The results suggest that HDC is not a direct replacement for Transformer models when maximum predictive performance is the primary objective, but rather a promising efficiency-oriented alternative for large-scale and resource-constrained misinformation detection.
Referências
Alghamdi, J., Lin, Y., and Luo, S. (2023). Towards covid-19 fake news detection using transformer-based models. Knowledge-Based Systems, 274:110642.
Alghamdi, J., Luo, S., and Lin, Y. (2024). A comprehensive survey on machine learning approaches for fake news detection. Multimedia Tools and Applications, 83(17):51009–51067.
Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2019). Bert: Pre-training of deep bidirectional transformers for language understanding. In Proc. NAACL-HLT, pages 4171–4186. Association for Computational Linguistics.
Ge, L. and Parhi, K. K. (2020). Classification using hyperdimensional computing: A review. IEEE Circuits and Systems Magazine, 20(2):30–47.
Heddes, M., Nunes, I., Vergés, P., Kleyko, D., Abraham, D., Givargis, T., Nicolau, A., and Veidenbaum, A. (2023). Torchhd: An open source python library to support research on hyperdimensional computing and vector symbolic architectures. Journal of Machine Learning Research, 24(255):1–10.
Hernández-Cano, A., Matsumoto, N., Ping, E., and Imani, M. (2021). Onlinehd: Robust, efficient, and single-pass online learning using hyperdimensional system. In 2021 Design, Automation & Test in Europe Conference & Exhibition (DATE), pages 56–61.
Hu, B., Sheng, Q., Cao, J., Shi, Y., Li, Y., Wang, D., and Qi, P. (2024). Bad actor, good advisor: Exploring the role of large language models in fake news detection. In Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, AAAI’24. AAAI Press.
Imani, M., Morris, J., Bosch, S., Shu, H., De Micheli, G., and Rosing, T. (2019). Adapthd: Adaptive efficient training for brain-inspired hyperdimensional computing. In 2019 IEEE Biomedical Circuits and Systems Conference (BioCAS), pages 1–4.
Kanerva, P. (2009). Hyperdimensional computing: An introduction to computing in distributed representation with high-dimensional random vectors. Cognitive Computation, 1:139–159.
Li, T., Zhong, H., Wu, J., Kämpfe, T., Ni, K., Narayanan, V., Yang, H., and Li, X. (2024). Cafehd: A charge-domain fefet-based compute-in-memory hyperdimensional encoder with hypervector merging. In 2024 Design, Automation & Test in Europe Conference & Exhibition (DATE), pages 1–6.
Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., and Stoyanov, V. (2019). Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692.
Olan, F., Jayawickrama, U., Arakpogun, E. O., Suklan, J., and Liu, S. (2024). Fake news on social media: The impact on society. Information Systems Frontiers, 26(2):443–458.
Patwa, P., Sharma, S., Pykl, S., Guptha, V., Kumari, G., Akhtar, M. S., Ekbal, A., Das, A., and Chakraborty, T. (2021). Fighting an infodemic: Covid-19 fake news dataset. In Combating Online Hostile Posts in Regional Languages during Emergency Situation, pages 21–29, Cham. Springer International Publishing.
Ruchansky, N., Seo, S., and Liu, Y. (2017). Csi: A hybrid deep model for fake news detection. In Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, CIKM ’17, pages 797–806, New York, NY, USA. Association for Computing Machinery.
Shahi, G. K., Dirkson, A., and Majchrzak, T. A. (2021). An exploratory study of covid-19 misinformation on twitter. Online Social Networks and Media, 22:100104.
Strubell, E., Ganesh, A., and McCallum, A. (2019). Energy and policy considerations for deep learning in nlp. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3645–3650, Florence, Italy. Association for Computational Linguistics.
Thorne, J., Vlachos, A., Christodoulopoulos, C., and Mittal, A. (2018). FEVER: A large-scale dataset for fact extraction and VERification. In Proc. NAACL-HLT, pages 809–819. Association for Computational Linguistics.
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., and Polosukhin, I. (2017). Attention is all you need. In Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS’17, pages 6000–6010, Red Hook, NY, USA. Curran Associates Inc.
Wang, J., Huang, S., and Imani, M. (2023). Disthd: A learner-aware dynamic encoding method for hyperdimensional classification. In 2023 60th ACM/IEEE Design Automation Conference (DAC), pages 1–6.
Zou, Z., Kim, Y., Imani, F., Alimohamadi, H., Cammarota, R., and Imani, M. (2021). Scalable edge-based hyperdimensional learning system with brain-like neural adaptation. In SC21: Int. Conf. for High Performance Computing, Networking, Storage and Analysis, pages 1–15.
