Deep learning models often struggle to maintain performance when the training and testing data come from different distributions. Test-time adaptation (TTA) addresses this by adapting a pre-trained model to an unlabeled target domain under distribution shifts. A more challenging setting is open-set TTA (OSTTA), where the target domain may contain unknown samples outside the source classes. Existing OSTTA methods primarily detect and discard such unknowns, relying only on known samples for adaptation. In this work, we argue that unknown samples can also provide valuable cues for improving adaptation. We propose LU-OSTTA (learning from unknown for OSTTA), a simple yet effective framework that leverages both in-distribution and semantically useful out-of-distribution samples. Our approach introduces: (i) a class-conditioned dynamic energy threshold to separate OOD samples more reliably, (ii) an optimal transport–based pseudo-label refinement to mitigate noise under distribution shifts, and (iii) an adaptive prototype weighting strategy that emphasizes semantically aligned target samples while down-weighting harmful ones. Experimental results demonstrate that our LUOSTTA consistently outperforms state-of-the-art TTA and OSTTA methods, highlighting the benefits of utilizing rather than discarding unknown samples. Our code is available at: https://github.com/takihasan/LU-OSTTA.

Examining Drug-Drug Interactions (DDIs) is a pivotal element in the process of drug development. DDIs occur when one drug's properties are affected by the inclusion of other drugs. Detecting favorable DDIs has the potential to pave the way for creating and advancing innovative medications applicable in practical settings. However, existing DDI prediction models continue to face challenges related to generalization in extreme cases, robust feature extraction, and real-life application possibilities. We aim to address these challenges by leveraging the effectiveness of context-aware deep graph learning by introducing a novel framework named CADGL. Based on a customized variational graph autoencoder (VGAE), we capture critical structural and physio-chemical information using two context pre-processors for feature extraction from two different perspectives- local neighborhood and molecular context, in a heterogeneous graphical structure. Our customized VGAE consists of a graph encoder, a latent information encoder, and an MLP decoder. CADGL surpasses other state-of-the-art DDI prediction models, excelling in predicting clinically valuable novel DDIs, supported by rigorous case studies. Our code is available at: https://github.com/azminewasi/CADGL.

Samuel Cahyawijaya, Holy Lovenia, Joel Ruben Antony Moniz, Tack Hwa Wong, Mohammad Rifqi Farhansyah, Thant Thiri Maung, Frederikus Hudi, David Anugraha, Muhammad Ravi Shulthan Habibi, Muhammad Reza Qorib, Amit Agarwal, Joseph Marvin Imperial, Hitesh Laxmichand Patel, Vicky Feliren, Bahrul Ilmi Nasution, Manuel Antonio Rufino, Genta Indra Winata, Rian Adam Rajagede, Carlos Rafael Catalan, Mohamed Fazli Mohamed Imam, Priyaranjan Pattnayak, Salsabila Zahirah Pranida, Kevin Pratama, Yeshil Bangera, Adisai Na-Thalang, Patricia Nicole Monderin, Yueqi Song, Christian Simon, Lynnette Hui Xian Ng, Richardy Lobo Sapan, Taki Hasan Rafi, Bin Wang, Supryadi, Kanyakorn Veerakanjana, Piyalitt Ittichaiwong, Matthew Theodore Roque, Karissa Vincentio, Takdanai Kreangphet, Phakphum Artkaew, Kadek Hendrawan Palgunadi, Yanzhi Yu, Rochana Prih Hastuti, William Nixon, Mithil Bangera, Adrian Xuan Wei Lim, Aye Hninn Khine, Hanif Muhammad Zhafran, Teddy Ferdinan, Audra Aurora Izzani, Ayushman Singh, Evan Evan, Jauza Akbar Krito, Michael Anugraha, Fenal Ashokbhai Ilasariya, Haochen Li, John Amadeo Daniswara, Filbert Aurelian Tjiaranata, Eryawan Presma Yulianrifat, Can Udomcharoenchaikit, Fadil Risdian Ansori, Mahardika Krisna Ihsani, Giang Nguyen, Anab Maulana Barik, Dan John Velasco, Rifo Ahmad Genadi, Saptarshi Saha, Chengwei Wei, Isaiah Edri W. Flores, Kenneth Chen Ko Han, Anjela Gail D. Santos, Wan Shen Lim, Kaung Si Phyo, Tim Santos, Meisyarah Dwiastuti, Jiayun Luo, Jan Christian Blaise Cruz, Ming Shan Hee, Ikhlasul Akmal Hanif, M.Alif Al Hakim, Muhammad Rizky Sya’ban, Kun Kerdthaisong, Lester James Validad Miranda, Fajri Koto, Tirana Noor Fatyanosa, Alham Fikri Aji, Jostin Jerico Rosal, Jun Kevin, Robert Wijaya, Onno P. Kampman, Ruochen Zhang, Börje F. Karlsson, Peerat Limkonchotiwat. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Test-Time Adaptation (TTA) aims to adapt an unseen target domain utilizing the unlabeled target data using a pre-trained source model. Continual TTA is a more challenging paradigm that deals with non-stationary environments during the test data adaptation. Most existing continual TTA methods are based on pseudo-labeling, but often (1) rely on overconfident pseudo-labels and (2) remain unstable under continual distribution shifts leading to error accumulation and catastrophic forgetting. To tackle these limitations, we propose Neighbor-Filtration based Continual Test-Time Adaptation (NF-CTTA), a reliable and memory-aware adaptation framework that addresses these challenges. NF-CTTA first calibrates pseudo-labels using class-conditional calibration error to correct over/under-confidence of the model. To further ensure reliability, we introduce an OOD Neighbor Filtration technique that selects a subset of high-confidence samples based on entropy and neighbor similarity, ensuring consistency within the semantic neighborhood. Finally, we propose a priority-guided memory buffer that retains the most informative low-entropy samples for replay, mitigating catastrophic forgetting across evolving test distributions. Extensive experiments across multiple domain shift benchmarks demonstrate that NF-CTTA achieves superior performance and stability compared to existing TTA and CTTA methods. The code is available at: https://github.com/takihasan/NF-CTTA.

Knowledge Graphs (KGs) have proven essential in information processing and reasoning applications because they link related entities and give context-rich information, supporting efficient information retrieval and knowledge discovery; presenting information flow in a very effective manner. Despite being widely used globally, Bangla is relatively underrepresented in KGs due to a lack of comprehensive datasets, encoders, NER (named entity recognition) models, POS (part-of-speech) taggers, and lemmatizers, hindering efficient information processing and reasoning applications in the language. Addressing the KG scarcity in Bengali, we propose BanglaAutoKG, a pioneering framework that is able to automatically construct Bengali KGs from any Bangla text. We utilize multilingual LLMs to understand various languages and correlate entities and relations universally. By employing a translation dictionary to identify English equivalents and extracting word features from pre-trained BERT models, we construct the foundational KG. To reduce noise and align word embeddings with our goal, we employ graph-based polynomial filters. Lastly, we implement a GNN-based semantic filter, which elevates contextual understanding and trims unnecessary edges, culminating in the formation of the definitive KG. Empirical findings and case studies demonstrate the universal effectiveness of our model, capable of autonomously constructing semantically enriched KGs from any text. Data and code are available here: https://github.com/azminewasi/BanglaAutoKG

Every year, doctors diagnose skin cancer in around 3 million or more patients across the globe. Currently, it is one of the most widely recognized kinds of cancers for human health. Hence, we need an early diagnosis to prevail any critical condition of the infected patients. Apparently, it can treat with topical drugs, if it diagnoses in an early stage. Hence as an outcome, skin cancer is responsible for less than 1% of all cancer deaths. There are two types of tumors in the skin cancer diseases domain, such as benign and malignant. To develop a robust and early screening system to diagnose skin cancer, it requires an efficient algorithm for prediction, trained with a large dataset. The primary aim of this research is to develop an efficient skin cancer screening process using a robust deep neural network with a large dataset. In this paper, we intend to determine considerate and dangerous types of skin cancer tumors using dermoscopic images from a publicly available dataset. We proposed an efficient and fast scaled 2D-CNN based on EfficientNet-B7 deep neural architecture with image preprocessing. This paper also uses two different pre-trained deep neural architectures, such as VGG19, and ResNet-50 to compare the performance with the proposed architecture. The proposed architecture outperformed the other pre-trained CNN models whereas the proposed architecture achieved higher AUC and accuracy compared to other architectures.

Novel coronavirus began in Wuhan, China back in December 2019. It has now outspread all over the world. Around 23 million people are currently affected by the novel coronavirus. It causes around 800,000 deaths globally. There are just about 300,000 people contaminated by COVID-19 in Bangladesh too. As it is an exceptional new pandemic infection, its diagnosis is challenging for the medical community. In regular cases, it is hard for developing countries to test cases frequently. The RT - PCR test is a generally utilized analysis framework for COVID-19 case detection. However, by utilizing X-ray image-based programs, recognition can diminish the expense and testing time. So it is important to program an effective recognition system to identify positive cases. In this paper, the author proposes an ensemble deep learning model, combining two state-of-art pre-trained models as ResNet-152 and DenseNet-121 to identify COVID-19 cases. The experimental validation result is immensely well with an accuracy of 98.43% on the proposed model. The author also compares the ensemble model's performance with ResNet-50 and DenseNet-121 separately.