Remove sub research directions

Author: RSTZZZ

_posts/papers/2020-10-03-2010.01408.md

@@ -9,7 +9,7 @@ webpage: https://mila.quebec/en/article/flight-seir-incorporating-flight-data-to
 author: Shenyang Huang
 categories: 
 - Publications
-- TGA
+- TGL
 excerpt: In this paper, we introduce a significant enhancement to the standard SEIR (Susceptible, Exposed, Infectious, Recovered) epidemiological model by integrating dynamic flight networks to better capture the mobility of populations, particularly in the context of disease spread like COVID-19. The authors propose a modified model called Flight-SEIR, which accounts for the movement of individuals through air travel, thereby estimating imported cases based on air traffic volume and test positive rates. This modification allows for more accurate modeling of disease transmission between populations, enabling early detection of outbreaks, more precise estimation of the reproduction number, and better evaluation of the impact of travel restrictions. By incorporating real-world flight data, Flight-SEIR provides a more realistic and comprehensive approach to epidemiological modeling, crucial for navigating pandemics in an interconnected world.
 
 

_posts/papers/2021-01-01-10.1007-978-3-030-75762-5_3.md

@@ -10,7 +10,7 @@ code: https://github.com/fpour/SigTran
 author: Farimah Poursafaei
 categories: 
 - Publications
-- TGA
+- TGL
 excerpt: SigTran is an efficient graph-based method for identifying illicit nodes in blockchain networks. SigTran constructs a graph from blockchain transaction records, representing nodes based on their structural and transactional characteristics to differentiate between legitimate and illicit activities. This method is versatile and can be applied to various blockchain networks. 
 
 ---

_posts/papers/2021-04-14-2104.06952.md

@@ -8,7 +8,7 @@ link: https://arxiv.org/abs/2104.06952
 author: Kellin Pelrine
 categories: 
 - Publications
-- information-integrity
+- poli-sci
 excerpt: While many sophisticated detection models have been proposed in the literature, they were often compared with older NLP baselines such as SVMs, CNNs, and LSTMs. We showed that with basic fine-tuning, BERT-type language models were competitive with and could even significantly outperform state-of-the-art methods of the time. We further studied a comprehensive set of benchmark datasets, and discuss potential data leakage and the need for careful design of the experiments and understanding of datasets to account for confounding variables. 
 
 

_posts/papers/2022-01-01-10.1137-1.9781611977172.73.md

@@ -9,7 +9,7 @@ code: https://github.com/fpour/TGBase
 author: Farimah Poursafaei
 categories: 
 - Publications
-- TGA
+- TGL
 excerpt: Here we introduce a robust and effective baseline method for node classification in temporal graphs, serving as a benchmark for evaluating more complex models. This approach is characterized by its simplicity and strong performance in categorizing nodes based on their evolving characteristics within the graph. By addressing the unique challenges posed by temporal graphs, the method provides a clear point of comparison for researchers and practitioners, enhancing the understanding and development of advanced techniques in temporal graph analysis. Its relevance spans various applications, including link prediction and node attribute inference in dynamic networks.
 
 

_posts/papers/2022-07-20-2207.10128.md

@@ -9,7 +9,7 @@ code: https://github.com/fpour/DGB
 author: Farimah Poursafaei
 categories: 
 - Publications
-- TGB
+- TGL
 excerpt: In this work, we introduce new, more rigorous evaluation procedures for link prediction in dynamic graphs, addressing the challenges and real-world considerations that are often overlooked in static graph analysis. The authors propose tools to enhance the evaluation process, including new datasets, innovative negative sampling strategies, and a strong baseline model. These contributions aim to better compare the strengths and weaknesses of different methods, highlighting the importance of robust evaluation frameworks in advancing the field of dynamic graph learning
 
 

_posts/papers/2023-01-01-10.18653-v1-2023.emnlp-industry.26.md

@@ -23,4 +23,4 @@ excerpt: "Identity biases arise commonly from annotated datasets, can be propaga
 
 ## Abstract
 
-,
+Identity biases arise commonly from annotated datasets, can be propagated in language models and can cause further harm to marginal groups. Existing bias benchmarking datasets are mainly focused on gender or racial biases and are made to pinpoint which class the model is biased towards. They also are not designed for the gaming industry, a concern for models built for toxicity detection in videogames’ chat. We propose a dataset and a method to highlight oversensitive terms using reactivity analysis and the model’s performance. We test our dataset against ToxBuster, a language model developed by Ubisoft fine-tuned for toxicity detection on multiplayer videogame’s written chat, and Perspective API. We find that these toxicity models often automatically tag terms related to a community’s identity as toxic, which prevents members of already marginalized groups to make their presence known or have a mature / normal conversation. Through this process, we have generated an interesting list of terms that trigger the models to varying degrees, along with insights on establishing a baseline through human annotations.

_posts/papers/2023-05-15-2305.08750.md

@@ -9,7 +9,7 @@ code: https://github.com/shenyangHuang/SCPD
 author: Shenyang Huang
 categories: 
 - Publications
-- TGA
+- TGL
 excerpt: We introduce a novel spectral method called Scalable Change Point Detection (SCPD) to address the limitations of current solutions in detecting anomalous change points in dynamic graphs. SCPD generates an embedding for each graph snapshot by efficiently approximating the distribution of the Laplacian spectrum, and it can capture shifts in node attributes by tracking correlations between attributes and eigenvectors. Through extensive experiments using synthetic and real-world data, the authors demonstrate that SCPD achieves state-of-the-art performance, is significantly faster than existing methods, can handle large quantities of node attributes, additions, or deletions, and effectively discovers interesting events in large real-world graphs
 
 ---

_posts/papers/2023-05-24-2305.14928.md

@@ -9,7 +9,7 @@ link: https://arxiv.org/abs/2305.14928
 author: Kellin Pelrine
 categories: 
 - Publications
-- information-integrity
+- poli-sci
 excerpt: We propose focusing on generalization, uncertainty, and how to leverage recent large language models, in order to create more practical tools to evaluate information veracity in contexts where perfect classification is impossible. This was one of the first works to study post-ChatGPT models in this domain. We first demonstrated they can outperform prior methods in multiple settings and languages, exhibit differences in failure modes, can quantify uncertainty, and other aspects of their usage. We also published the LIAR-New dataset with novel paired English and French misinformation data, and Possibility labels that indicate if there is sufficient context for veracity evaluation. 
 
 

_posts/papers/2023-07-03-2307.01026.md

@@ -12,7 +12,7 @@ code: https://github.com/shenyangHuang/TGB
 author: Shenyang Huang
 categories: 
 - Publications
-- TGB
+- TGL
 excerpt: In this paper, we introduce the Temporal Graph Benchmark (TGB), a comprehensive collection of large-scale, diverse datasets designed for the realistic, reproducible, and robust evaluation of machine learning models on temporal graphs. These datasets span multiple years and domains, including social, trade, transaction, and transportation networks, and encompass both node and edge-level prediction tasks. The research highlights significant variability in the performance of common models across different datasets and demonstrates that simple methods often outperform existing temporal graph models in dynamic node property prediction tasks. Additionally, TGB provides an automated machine learning pipeline for data loading, experiment setup, and performance evaluation, fostering reproducible and accessible research. 
 
 

_posts/papers/2024-01-13-2401.08694.md

@@ -9,7 +9,7 @@ link: https://arxiv.org/abs/2401.08694
 author: Reihaneh Rabbany
 categories: 
 - Publications
-- information-integrity
+- poli-sci
 excerpt: LLMs struggle with hallucinations and overconfident predictions. Uncertainty quantification can improve their reliability and helpfulness. We proposed an uncertainty quantification framework that leverages both direct confidence elicitation and sampled-based consistency methods to provide better calibration for NLP misinformation mitigation solutions.