论文检索

Yifan Zhang, Jeff Heflin

In this paper, we present a new image similarity search algorithm designed to enhance traditional information retrieval(IR) by adding an image search capability. Our approach uses a quadtree data structure to organize image data, significantly reducing search space and improving retrieval efficiency. We describe an indexing strategy and two query algorithms that can be implemented in any IR system. We tested our method on a 70K material microscopy image dataset, achieving a 25 times improvement in retrieval speed with only a 20% reduction in ranking accuracy.

Tianyu Zhan, Zheqi Lv, Shengyu Zhang, Jiwei Li

This paper explores the application and effectiveness of TestTime Training (TTT) layers in improving the performance of recommendation systems. We developed a model, TTT4Rec, utilizing TTT-Linear as the feature extraction layer. Our tests across multiple datasets indicate that TTT4Rec, as a base model, performs comparably or even surpasses other baseline models in similar environments.

Emily Yu

Data-driven analysis has shown promising results in identifying subtle patterns in the behavior of individuals with Autism Spectrum Disorder (ASD) for diagnosis and intervention. However, most existing methods primarily focus on a single behavioral modality (e.g., eye movements) instead of capturing the intricate multimodal behavior of humans. We propose a multimodal approach that investigates the underlying connections between eye movements and hand motions through eye-to-hand prediction. To tackle the highly noisy and irregular behavioral data, we propose a novel approach that defines the prediction as a machine translation problem and leverages a sequence-to-sequence machine learning model for the prediction. An experimental study on a dataset collected from a VR system has demonstrated high prediction accuracy. The significant difference in the prediction accuracy between the autistic group and their typically developing (TD) peers serves as quantitative evidence to objectively understand the restricted and repetitive behaviors (RRBs) in autistic children. The source code can be accessed here: https://github.com/mathjams/AAAI_2024.

Gerard Christopher Yeo, Kokil Jaidka

Large language models (LLMs) are trained on vast amounts of publicly available text. However, the current training frameworks take for granted that these annotations are accurate reflections of the authors’ true intents. This study questions that assumption by examining the gaps between writers’ actual psychological states and the inferences made by third-party annotators. We explore how readers interpret psychological cues in text and demonstrate that third-person annotations often fail to align with first-person realities. By integrating both first- and third-person annotations, we develop computational models that reveal significant biases in how psychological states are perceived and the downstream effects these perceptions have on reader behavior. Our findings challenge the foundational assumptions of LLM training, suggesting that the reliance on potentially flawed third-person annotations could impact model accuracy and real-world applications.

Shuo Yang, Siwen Luo, Soyeon Caren Han

Existing Multimodal Large Language Models (MLLMs) and Visual Language Pretrained Models (VLPMs) have shown remarkable performances in general Visual Question Answering (VQA). However, these models struggle with VQA questions that require external commonsense knowledge due to the challenges in generating high-quality prompts and the high computational costs of fine-tuning. In this work, we propose a novel graph-based multimodal commonsense knowledge distillation framework that constructs a unified relational graph over commonsense knowledge, visual objects and questions through a Graph Convolutional Network (GCN) following a teacher-student environment. This proposed framework is flexible with any type of teacher and student models without further fine-tuning, and has achieved competitive performances on the ScienceQA dataset. The code is in https://github.com/adlnlp/MCKDVQA.

Enshuo Yan, Huachuan Wang, Weihao Xia

In multivariate time series classification, although current sequence analysis models have excellent classification capabilities, they show significant shortcomings when dealing with long sequence multivariate data. This paper focuses on optimizing model performance for long-sequence multivariate data by mitigating the impact of extended time series and multiple variables on the model. We propose a principal component analysis (PCA)-based temporal streaming compression and dimensionality reduction algorithm for time series data (temporal streaming batch PCA, TSBPCA), which continuously updates the compact representation of the entire sequence through streaming PCA time estimation with time block updates, enhancing the data representation capability of a range of sequence analysis models.We evaluated this method using various models on five datasets, and the experimental results show that our method demonstrates outstanding performance in both classification accuracy and time efficiency.

Xiaoqing Xu, Jiaming Pei, Lukun Wang

In federated learning, frequent parameter transmission between clients and the server results in significant communication overhead, particularly due to redundancy within the parameters. To address this issue, we propose a Complementary Pruning for Device-to-Device Communication (FedCPD) method. This approach effectively reduces the amount of transmitted parameters by applying complementary pruning techniques on both the server and clients. Additionally, we decrease the communication frequency between clients and the server by employing chain updates among clients (i.e., device-to-device communication). We conducted experiments on the MNIST, FMNIST, CIFAR-10, and CIFAR-100 datasets, and the results demonstrate that our method significantly reduces communication costs while improving model accuracy.

Jingzehua Xu, Guanwen Xie, Yimian Ding, Yongming Zeng, Haoyu Wang, Shuai Zhang

Ocean exploration requires effective collaboration between the unmanned surface vehicle (USV) and autonomous underwater vehicles (AUVs). We propose UACOF, a USV-AUV collaboration framework that enhances multi-AUV performance under extreme sea conditions. The framework includes high-precision multi-AUV location via USV path planning with Fisher information matrix optimization and reinforcement learning training for cooperative tasks. Experimental results show UACOF's superior feasibility, performance, coordination and robustness in extreme conditions.

Guanwen Xie, Jingzehua Xu, Yiyuan Yang, Yimian Ding, Shuai Zhang

We propose ERFSL, an efficient reward function searcher using large language models (LLMs) for custom-environment, multi-objective reinforcement learning (RL). ERFSL generates reward components based on explicit user requirements and rectifies them, and iteratively optimizes the weights of these components based on textual context. Applied to an underwater data collection RL task, ERFSL corrects reward codes with only one feedback iteration per requirement, and acquires diverse reward functions within the Pareto set. ERFSL also presents robust capability for deviated weights and small-size LLMs such as GPT-4o mini. The full-text prompts, examples of LLM-generated answers, and source code are available at https://360zmem.github.io/LLMRsearcher/ .

Eric Xia, Jugal Kalita

The recent success of transformer language models owes much to their conversational fluency, which includes linguistic and morphological proficiency. An affine Taylor approximation has been found to be a good approximation for transformer computations over certain factual and encyclopedic relations. We show that the truly linear approximation W s, where s is a early layer representation of the base form and W is a local model derivative, is necessary and sufficient to approximate morphological derivation, achieving above 80% top-1 accuracy across most morphological tasks in the Bigger Analogy Test Set. We argue that many morphological forms in transformer models are likely linearly encoded.

Piotr Wyrwiński, Krzysztof Krawiec

This study introduces a neurosymbolic approach that performs iterative graph expansion guided by a graph neural network to solve symbolic regression problems. Empirical evaluation demonstrates superior performance of the method compared to baseline algorithms. We also integrate the method with an evolutionary algorithm, which results in further performance improvements.

Yasir White, Jevon Lipsey, Jeff Heflin

Knowledge bases traditionally require manual optimization to ensure reasonable performance when answering queries. We build on previous neurosymbolic approaches by improving the training of an embedding model for logical statements that maximizes similarity between unifying atoms and minimizes similarity of non-unifying atoms. In particular, we evaluate different approaches to training this model.

Deliang Wang, Yu Lu, Gaowei Chen

This paper proposes extended Long Short-Term Memory (LSTM) networks for the knowledge tracing task and employs explainable AI methods to address interpretability issues. Specifically, we developed an extended LSTM-based model to automatically diagnose students' knowledge states. We then leveraged three interpreting methods—gradient sensitivity, gradient*input, and Deep SHAP—to explain the model's predictions by computing input contributions. The results demonstrate that the proposed model outperforms DKT, and the three methods effectively explain its predictions. Additionally, we identified three key insights into the model's working mechanisms.

Guihong Wan, Ninghui Hao, Crystal Maung, Haim Schweitzer, Chen Zhao, Kun-Hsing Yu, Yevgeniy R. Semenov

Given a data matrix, unsupervised column subset selection refers to the problem of identifying a subset of columns that can be used to linearly approximate the original data matrix. This problem has many applications, such as feature selection and representative selection, but solving it optimally is known to be NP-hard. We consider multi-view unsupervised column subset selection, which extends the concept of (single-view) column subset selection to data represented in multiple views or modalities. We introduce a combinatorial search algorithm for this generalized problem. One variant of the algorithm is guaranteed to compute an optimal solution in a setting similar to the classical A* algorithm. Other suboptimal variants, in a setting similar to the weighted A* algorithm, are much faster and provide a solution along with a bound on its quality.

Jonas Vistrup

We present FÆRDXEL, an expert system for providing answers and explanations to legal questions (queries) regarding Danish traffic law cases. It utilizes a Datalog encoding of Danish traffic laws and uses SLD-resolution to answer queries. The SLD-resolution’s trace of operations can be converted into a legal explanation for the query. A user interface allows legal professionals to input case facts, ask questions, and explore explanations. Feedback from legal experts identified usability challenges and potential end-users, including traffic police and judges. Future steps include empirical evaluation of soundness, integrating punishment reasoning, and enhancing usability through natural language processing.

Diana Vins, Jean Erik Delanois, Maxim Bazhenov

Artificial neural networks (ANNs) struggle with continual learning, sacrificing performance on previously learned tasks to acquire new task knowledge. Here we propose a new approach allowing to mitigate catastrophic forgetting during continuous task learning. Typically a new task is trained until it reaches maximal performance, causing complete catastrophic forgetting of the previous tasks. In our new approach, termed Optimal Stopping (OS), network training on each new task continues only while the mean validation accuracy across all the tasks (current and previous) increases. The stopping criterion creates an explicit balance: lower performance on new tasks is accepted in exchange for preserving knowledge of previous tasks, resulting in higher overall network performance. The overall performance is further improved when OS is combined with Sleep Replay Consolidation (SRC), wherein the network converts to a Spiking Neural Network (SNN) and undergoes unsupervised learning modulated by Hebbian plasticity. During the SRC, the network spontaneously replays activation patterns from previous tasks, helping to maintain and restore prior task performance. This combined approach offers a promising avenue for enhancing the robustness and longevity of learned representations in continual learning models, achieving over twice the mean accuracy of baseline continuous learning while maintaining stable performance across tasks.

Supriti Vijay, Aman Priyanshu, Ashiqur R. KhudaBukhsh

In an era where societal narratives are increasingly shaped by algorithmic curation, investigating the political neutrality of LLMs is an important research question. This study presents a fresh perspective on quantifying the political neutrality of LLMs through the lens of abstractive text summarization of polarizing news articles. We consider five pressing issues in current US politics: abortion, gun control/rights, healthcare, immigration, and LGBTQ+ rights. Via a substantial corpus of 20,344 news articles, our study reveals a consistent trend towards pro-Democratic biases in several well-known LLMs, with gun control and healthcare exhibiting the most pronounced biases (max polarization differences of -9.49% and -6.14%, respectively). Further analysis uncovers a strong convergence in the vocabulary of the LLM outputs for these divisive topics (55% overlap for Democrat-leaning representations, 52% for Republican). Being months away from a US election of consequence, we consider our findings important.

Sutashu Tomonaga, Haruo Mizutani, Kenji Doya

Wearable devices are transforming healthcare by providing continuous, real-time physiological data for monitoring and analysis. However, data often suffer from noise and significant missing values due to operational constraints and user compliance. Traditional approaches address these issues through data imputation during pre-processing, introducing biases and inaccuracies. We propose a novel method enabling Recurrent Neural Networks (RNNs) to inherently handle missing data without imputation. By implementing teacher-forcing during Backpropagation Through Time (BPTT) when data are available and switching to autonomous mode otherwise, our approach leverages RNNs' dynamics to model physiological signals accurately. We demonstrate our method's effectiveness using the Lorenz 63 system as a surrogate dataset, achieving robust reconstructions with 80% missing data.

Shota Takayama, Katsuhide Fujita

Multi-agent reinforcement learning (MARL) trains multiple agents in shared environments. Recently, MARL models have significantly improved performance by leveraging sequential decision-making processes. Although these models can enhance performance, they do not explicitly con-sider the importance of the order in which agents make decisions. We propose AOAD-MAT, a novel model incorporating action decision sequence into learning. AOAD-MAT uses a Transformer-based actor-critic architecture to dynamically adjust agent action order. It introduces a subtask predicting the next agent to act, integrated into a PPO-based loss function. Experiments on StarCraft Multi-Agent Challenge and Multi-Agent MuJoCo benchmarks show AOAD-MAT out-performs existing models, demonstrating the effectiveness of adjusting agent order in MARL.

Zhihang Sun, Shuhan Qi, Xinhao Huang, Xinyu Xiao, Jiajia Zhang, Xuan Wang, Peixi Peng

In recent years, reinforcement learning has been widely applied in the field of games. However, most studies focus on assisting agents to achieve victory, with less attention paid to whether the agents exhibit human-like characteristics. In order to build human-like agents with high performance, we propose a method for learning the strategies of human players in modern three-dimensional video games. Our method utilizes a hierarchical framework, learning basic behaviors and intentions of human players at the lower level through imitation learning, and generalized policies at the high level through reinforcement learning. Compared with other existing methods, our method demonstrates significant advantages in learning human-like strategies in complex environments.