Socially Fair Mitigation of Misinformation on Social Networks via Constraint Stochastic Optimization

Abouzeid, Abdel-Zaher M.; Granmo, Ole‐Christoffer; Webersik, Christian; Goodwin, Morten

doi:10.1609/aaai.v36i11.21436

Cited by 3 publications

(1 citation statement)

References 23 publications

(31 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Theoretical proof of TM's capability to solve complex pattern recognition problems and derivations of propositional formulas and its alignment with Nash equilibrium can be found in [18]. Interested readers can find the proof of convergence of TM in [25], [26] and further details on theoretical aspects of TM in [27], [28], [29], [30]. In this section, we visualize the details of the working principle and actual implementation of TM algorithm.…”

Section: Tsetlin Machinesmentioning

confidence: 99%

REDRESS: Generating Compressed Models for Edge Inference Using Tsetlin Machines

Maheshwari

Rahman

Member

et al. 2023

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

Inference at-the-edge using embedded machine learning models is associated with challenging trade-offs between resource metrics, such as energy and memory footprint, and the performance metrics, such as computation time and accuracy. In this work, we go beyond the conventional Neural Network based approaches to explore Tsetlin Machine (TM), an emerging machine learning algorithm, that uses learning automata to create propositional logic for classification. We use algorithm-hardware co-design to propose a novel methodology for training and inference of TM. The methodology, called REDRESS, comprises independent TM training and inference techniques to reduce the memory footprint of the resulting automata to target low and ultra-low power applications. The array of Tsetlin Automata (TA) holds learned information in the binary form as bits: {0, 1}, called excludes and includes, respectively. REDRESS proposes a lossless TA compression method, called the include-encoding, that stores only the information associated with includes to achieve over 99% compression. This is enabled by a novel computationally minimal training procedure, called the Tsetlin Automata Re-profiling, to improve the accuracy and increase the sparsity of TA to reduce the number of includes, hence, the memory footprint. Finally, REDRESS includes an inherently bit-parallel inference algorithm that operates on the optimally trained TA in the compressed domain, that does not require decompression during runtime, to obtain high speedups when compared with the state-of-the-art Binary Neural Network (BNN) models. In this work, we demonstrate that using REDRESS approach, TM outperforms BNN models on all design metrics for five benchmark datasets viz. MNIST, CIFAR2, KWS6, Fashion-MNIST and Kuzushiji-MNIST. When implemented on an STM32F746G-DISCO microcontroller, REDRESS obtained speedups and energy savings ranging 5-5700× compared with different BNN models.

show abstract

Section: Tsetlin Machinesmentioning

confidence: 99%

REDRESS: Generating Compressed Models for Edge Inference Using Tsetlin Machines

Maheshwari

Rahman

Member

et al. 2023

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

show abstract

Towards misinformation mitigation on social media: novel user activity representation for modeling societal acceptance

Abouzeid,

Granmo,

Goodwin

et al. 2024

J Comput Soc Sc

View full text Add to dashboard Cite

Intervention-based mitigation methods have become a common way to fight misinformation on Social Media (SM). However, these methods depend on how information spreads are modeled in a diffusion model. Unfortunately, there are no realistic diffusion models or enough diverse datasets to train diffusion prediction functions. In particular, there is an urgent need for mitigation methods and labeled datasets that capture the mutual temporal incidences of societal bias and societal engagement that drive the spread of misinformation. To that end, this paper proposes a novel representation of users’ activity on SM. We further embed these in a knapsack-based mitigation optimization approach. The optimization task is to find ways to mitigate political manipulation by incentivizing users to propagate factual information. We have created PEGYPT, a novel Twitter dataset to train a novel multiplex diffusion model with political bias, societal engagement, and propaganda events. Our approach aligns with recent theoretical findings on the importance of societal acceptance of information spread on SM as proposed by Olan et al. (Inf Syst Front 1–16, 2022). Our empirical results show significant differences from traditional representations, where the latter assume users’ exposure to misinformation can be mitigated despite their political bias and societal acceptance. Hence, our work opens venues for more realistic misinformation mitigation.

show abstract