add papers

data/2024/aaai/"Allot?" is "A Lot!" Towards Developing More Generalized Speech Recognition System for Accessible Communication

@@ -0,0 +1 @@
+The proliferation of Automatic Speech Recognition (ASR) systems has revolutionized translation and transcription. However, challenges persist in ensuring inclusive communication for non-native English speakers. This study quantifies the gap between accented and native English speech using Wav2Vec 2.0, a state-of-the-art transformer model. Notably, we found that accented speech exhibits significantly higher word error rates of 30-50%, in contrast to native speakers’ 2-8% (Baevski et al. 2020). Our exploration extends to leveraging accessible online datasets to highlight the potential of enhancing speech recognition by fine-tuning the Wav2Vec 2.0 model. Through experimentation and analysis, we highlight the challenges with training models on accented speech. By refining models and addressing data quality issues, our work presents a pipeline for future investigations aimed at developing an integrated system capable of effectively engaging with a broader range of individuals with diverse backgrounds. Accurate recognition of accented speech is a pivotal step toward democratizing AI-driven communication products.

data/2024/aaai/'Why Didn't You Allocate This Task to Them?' Negotiation-Aware Task Allocation and Contrastive Explanation Generation

@@ -0,0 +1 @@
+In this work, we design an Artificially Intelligent Task Allocator (AITA) that proposes a task allocation for a team of humans. A key property of this allocation is that when an agent with imperfect knowledge (about their teammate's costs and/or the team's performance metric) contests the allocation with a counterfactual, a contrastive explanation can always be provided to showcase why the proposed allocation is better than the proposed counterfactual. For this, we consider a negotiation process that produces a negotiation-aware task allocation and, when contested, leverages a negotiation tree to provide a contrastive explanation. With human subject studies, we show that the proposed allocation indeed appears fair to a majority of participants and, when not, the explanations generated are judged as convincing and easy to comprehend.

data/2024/aaai/1 2-Approximate MMS Allocation for Separable Piecewise Linear Concave Valuations

@@ -0,0 +1,6 @@
+We study fair distribution of a collection of m indivisible goods among a group of n agents, using the widely recognized fairness principles of Maximin Share (MMS) and Any Price Share (APS). These principles have undergone thorough investigation within the context of additive valuations. We explore these notions for valuations that extend beyond additivity.
+
+First, we study approximate MMS under the separable (piecewise-linear) concave (SPLC) valuations, an important class generalizing additive, where the best known factor was 1/3-MMS. We show that 1/2-MMS allocation exists and can be computed in polynomial time, significantly improving the state-of-the-art.
+We note that SPLC valuations introduce an elevated level of intricacy in contrast to additive. For instance, the MMS value of an agent can be as high as her value for the entire set of items. We use a relax-and-round paradigm that goes through competitive equilibrium and LP relaxation. Our result extends to give (symmetric) 1/2-APS, a stronger guarantee than MMS.
+
+APS is a stronger notion that generalizes MMS by allowing agents with arbitrary entitlements. We study the approximation of APS under submodular valuation functions. We design and analyze a simple greedy algorithm using concave extensions of submodular functions. We prove that the algorithm gives a 1/3-APS allocation which matches the best-known factor. Concave extensions are hard to compute in polynomial time and are, therefore, generally not used in approximation algorithms. Our approach shows a way to utilize it within analysis (while bypassing its computation), and hence might be of independent interest.

data/2024/aaai/3D Visibility-Aware Generalizable Neural Radiance Fields for Interacting Hands

@@ -0,0 +1 @@
+Neural radiance fields (NeRFs) are promising 3D representations for scenes, objects, and humans. However, most existing methods require multi-view inputs and per-scene training, which limits their real-life applications. Moreover, current methods focus on single-subject cases, leaving scenes of interacting hands that involve severe inter-hand occlusions and challenging view variations remain unsolved. To tackle these issues, this paper proposes a generalizable visibility-aware NeRF (VA-NeRF) framework for interacting hands. Specifically, given an image of interacting hands as input, our VA-NeRF first obtains a mesh-based representation of hands and extracts their corresponding geometric and textural features. Subsequently, a feature fusion module that exploits the visibility of query points and mesh vertices is introduced to adaptively merge features of both hands, enabling the recovery of features in unseen areas. Additionally, our VA-NeRF is optimized together with a novel discriminator within an adversarial learning paradigm. In contrast to conventional discriminators that predict a single real/fake label for the synthesized image, the proposed discriminator generates a pixel-wise visibility map, providing fine-grained supervision for unseen areas and encouraging the VA-NeRF to improve the visual quality of synthesized images. Experiments on the Interhand2.6M dataset demonstrate that our proposed VA-NeRF outperforms conventional NeRFs significantly. Project Page: https://github.com/XuanHuang0/VANeRF.

data/2024/aaai/3D-STMN: Dependency-Driven Superpoint-Text Matching Network for End-to-End 3D Referring Expression Segmentation

@@ -0,0 +1 @@
+In 3D Referring Expression Segmentation (3D-RES), the earlier approach adopts a two-stage paradigm, extracting segmentation proposals and then matching them with referring expressions. However, this conventional paradigm encounters significant challenges, most notably in terms of the generation of lackluster initial proposals and a pronounced deceleration in inference speed. Recognizing these limitations, we introduce an innovative end-to-end Superpoint-Text Matching Network (3D-STMN) that is enriched by dependency-driven insights. One of the keystones of our model is the Superpoint-Text Matching (STM) mechanism. Unlike traditional methods that navigate through instance proposals, STM directly correlates linguistic indications with their respective superpoints, clusters of semantically related points. This architectural decision empowers our model to efficiently harness cross-modal semantic relationships, primarily leveraging densely annotated superpoint-text pairs, as opposed to the more sparse instance-text pairs. In pursuit of enhancing the role of text in guiding the segmentation process, we further incorporate the Dependency-Driven Interaction (DDI) module to deepen the network's semantic comprehension of referring expressions. Using the dependency trees as a beacon, this module discerns the intricate relationships between primary terms and their associated descriptors in expressions, thereby elevating both the localization and segmentation capacities. Comprehensive experiments on the ScanRefer benchmark reveal that our model not only sets new performance standards, registering an mIoU gain of 11.7 points but also achieves a staggering enhancement in inference speed, surpassing traditional methods by 95.7 times. The code and models are available at https://github.com/sosppxo/3D-STMN.

data/2024/aaai/A Brain-Inspired Way of Reducing the Network Complexity via Concept-Regularized Coding for Emotion Recognition

@@ -0,0 +1 @@
+The human brain can effortlessly and reliably perceive emotions, whereas existing facial emotion recognition (FER) methods suffer from drawbacks such as complex model structures, high storage requirements, and poor interpretability. Inspired by the role of emotion concepts in visual perception coding within the human brain, we propose a dual-pathway framework emulating the neural computation of emotion recognition. Specifically, these two pathways are designed to model the representation of emotion concepts in the brain and the visual perception process, respectively. For the former, we adopt a disentangled approach to extract emotion concepts from complex facial geometric attributes; for the latter, we employ an emotional confidence evaluation strategy to determine which concept is optimal for regularizing the perceptual coding. The proposed concept-regularized coding strategy endows the framework with flexibility and interpretability as well as good performances on several benchmarking FER datasets.

data/2024/aaai/A Bregman Proximal Stochastic Gradient Method with Extrapolation for Nonconvex Nonsmooth Problems

@@ -0,0 +1 @@
+In this paper, we explore a specific optimization problem that involves the combination of a differentiable nonconvex function and a nondifferentiable function. The differentiable component lacks a global Lipschitz continuous gradient, posing challenges for optimization. To address this issue and accelerate the convergence, we propose a Bregman proximal stochastic gradient method with extrapolation (BPSGE), which only requires smooth adaptivity of the differentiable part. Under variance reduction framework, we not only analyze the subsequential and global convergence of the proposed algorithm under certain conditions, but also analyze the sublinear convergence rate of the subsequence, and the complexity of the algorithm, revealing that the BPSGE algorithm requires at most O(epsilon\^\,(-2)) iterations in expectation to attain an epsilon-stationary point. To validate the effectiveness of our proposed algorithm, we conduct numerical experiments on three real-world applications: graph regularized nonnegative matrix factorization (NMF), matrix factorization with weakly-convex regularization, and NMF with nonconvex sparsity constraints. These experiments demonstrate that BPSGE is faster than the baselines without extrapolation. The code is available at: https://github.com/nothing2wang/BPSGE-Algorithm.

data/2024/aaai/A Chain-of-Thought Prompting Approach with LLMs for Evaluating Students' Formative Assessment Responses in Science

@@ -0,0 +1 @@
+This paper explores the use of large language models (LLMs) to score and explain short-answer assessments in K-12 science. While existing methods can score more structured math and computer science assessments, they often do not provide explanations for the scores. Our study focuses on employing GPT-4 for automated assessment in middle school Earth Science, combining few-shot and active learning with chain-of-thought reasoning. Using a human-in-the-loop approach, we successfully score and provide meaningful explanations for formative assessment responses. A systematic analysis of our method's pros and cons sheds light on the potential for human-in-the-loop techniques to enhance automated grading for open-ended science assessments.

data/2024/aaai/A Class of Topological Pseudodistances for Fast Comparison of Persistence Diagrams

@@ -0,0 +1 @@
+Persistence diagrams (PD)s play a central role in topological data analysis, and are used in an ever increasing variety of applications. The comparison of PD data requires computing distances among large sets of PDs, with metrics which are accurate, theoretically sound, and fast to compute. Especially for denser multi-dimensional PDs, such comparison metrics are lacking. While on the one hand, Wasserstein-type distances have high accuracy and theoretical guarantees, they incur high computational cost. On the other hand, distances between vectorizations such as Persistence Statistics (PS)s have lower computational cost, but lack the accuracy guarantees and theoretical properties of a true distance over PD space. In this work we introduce a class of pseudodistances called Extended Topological Pseudodistances (ETD)s, which have tunable complexity, and can approximate Sliced and classical Wasserstein distances at the high-complexity extreme, while being computationally lighter and close to Persistence Statistics at the lower complexity extreme, and thus allow users to interpolate between the two metrics. We build theoretical comparisons to show how to fit our new distances at an intermediate level between persistence vectorizations and Wasserstein distances. We also experimentally verify that ETDs outperform PSs in terms of accuracy and outperform Wasserstein and Sliced Wasserstein distances in terms of computational complexity.

data/2024/aaai/A Closer Look at Curriculum Adversarial Training: From an Online Perspective

@@ -0,0 +1 @@
+Curriculum adversarial training empirically finds that gradually increasing the hardness of adversarial examples can further improve the adversarial robustness of the trained model compared to conventional adversarial training. However, theoretical understanding of this strategy remains limited. In an attempt to bridge this gap, we analyze the adversarial training process from an online perspective. Specifically, we treat adversarial examples in different iterations as samples from different adversarial distributions. We then introduce the time series prediction framework and deduce novel generalization error bounds. Our theoretical results not only demonstrate the effectiveness of the conventional adversarial training algorithm but also explain why curriculum adversarial training methods can further improve adversarial generalization. We conduct comprehensive experiments to support our theory.

data/2024/aaai/A Compiler for Weak Decomposable Negation Normal Form

@@ -0,0 +1 @@
+This paper integrates weak decomposable negation normal form (wDNNF) circuits, introduced by Akshay et al. in 2018, into the knowledge compilation map. This circuit type generalises decomposable negation normal form (DNNF) circuits in such a way that they allow a restricted form of sharing variables among the inputs of a conjunction node. We show that wDNNF circuits have the same properties as DNNF circuits regarding the queries and transformations presented in the knowledge compilation map, whilst being strictly more succinct than DNNF circuits (that is, they can represent Boolean functions compactly). We also present and evaluate a knowledge compiler, called Bella, for converting CNF formulae into wDNNF circuits. Our experiments demonstrate that wDNNF circuits are suitable for configuration instances.

data/2024/aaai/A Comprehensive Analysis of the Effectiveness of Large Language Models as Automatic Dialogue Evaluators

@@ -0,0 +1 @@
+Automatic evaluation is an integral aspect of dialogue system research. The traditional reference-based NLG metrics are generally found to be unsuitable for dialogue assessment. Consequently, recent studies have suggested various unique, reference-free neural metrics that better align with human evaluations. Notably among them, large language models (LLMs), particularly the instruction-tuned variants like ChatGPT, are shown to be promising substitutes for human judges. Yet, existing works on utilizing LLMs for automatic dialogue evaluation are limited in their scope in terms of the number of meta-evaluation datasets, mode of evaluation, coverage of LLMs, etc. Hence, it remains inconclusive how effective these LLMs are. To this end, we conduct a comprehensive study on the application of LLMs for automatic dialogue evaluation. Specifically, we analyze the multi-dimensional evaluation capability of 30 recently emerged LLMs at both turn and dialogue levels, using a comprehensive set of 12 meta-evaluation datasets. Additionally, we probe the robustness of the LLMs in handling various adversarial perturbations at both turn and dialogue levels. Finally, we explore how model-level and dimension-level ensembles impact the evaluation performance. All resources are available at https://github.com/e0397123/comp-analysis.

data/2024/aaai/A Comprehensive Augmentation Framework for Anomaly Detection

@@ -0,0 +1,2 @@
+Data augmentation methods are commonly integrated into the training of anomaly detection models.
+Previous approaches have primarily focused on replicating real-world anomalies or enhancing diversity, without considering that the standard of anomaly varies across different classes, potentially leading to a biased training distribution. This paper analyzes crucial traits of simulated anomalies that contribute to the training of reconstructive networks and condenses them into several methods, thus creating a comprehensive framework by selectively utilizing appropriate combinations. Furthermore, we integrate this framework with a reconstruction-based approach and concurrently propose a split training strategy that alleviates the overfitting issue while avoiding introducing interference to the reconstruction process. The evaluations conducted on the MVTec anomaly detection dataset demonstrate that our method outperforms the previous state-of-the-art approach, particularly in terms of object classes. We also generate a simulated dataset comprising anomalies with diverse characteristics, and experimental results demonstrate that our approach exhibits promising potential for generalizing effectively to various unseen anomalies encountered in real-world scenarios.

data/2024/aaai/A Computation-Aware Shape Loss Function for Point Cloud Completion

@@ -0,0 +1,3 @@
+Learning-based point cloud completion tasks have shown potential in various critical tasks, such as object detection, assignment, and registration. However, accurately and efficiently quantifying the shape error between the predicted point clouds generated by networks and the ground truth remains challenging. While EMD-based loss functions excel in shape detail and perceived density distribution, their approach can only yield results with significant discrepancies from the actual EMD within a tolerable training time.
+To address these challenges, we first propose the initial price based on the auction algorithm, reducing the number of iterations required for the algorithm while ensuring the correctness of the assignment results. We then introduce an algorithm to compute the initial price through a successive shortest path and the Euclidean information between its nodes. Finally, we adopt a series of optimization strategies to speed up the algorithm and offer an EMD approximation scheme for point cloud problems that balances time loss and computational accuracy based on point cloud data characteristics.
+Our experimental results confirm that our algorithm achieves the smallest gap with the real EMD within an acceptable time range and yields the best results in end-to-end training.

data/2024/aaai/A Convolutional Neural Network Interpretable Framework for Human Ventral Visual Pathway Representation

@@ -0,0 +1 @@
+Recently, convolutional neural networks (CNNs) have become the best quantitative encoding models for capturing neural activity and hierarchical structure in the ventral visual pathway. However, the weak interpretability of these black-box models hinders their ability to reveal visual representational encoding mechanisms. Here, we propose a convolutional neural network interpretable framework (CNN-IF) aimed at providing a transparent interpretable encoding model for the ventral visual pathway. First, we adapt the feature-weighted receptive field framework to train two high-performing ventral visual pathway encoding models using large-scale functional Magnetic Resonance Imaging (fMRI) in both goal-driven and data-driven approaches. We find that network layer-wise predictions align with the functional hierarchy of the ventral visual pathway. Then, we correspond feature units to voxel units in the brain and successfully quantify the alignment between voxel responses and visual concepts. Finally, we conduct Network Dissection along the ventral visual pathway including the fusiform face area (FFA), and discover variations related to the visual concept of `person'. Our results demonstrate the CNN-IF provides a new perspective for understanding encoding mechanisms in the human ventral visual pathway, and the combination of ante-hoc interpretable structure and post-hoc interpretable approaches can achieve fine-grained voxel-wise correspondence between model and brain. The source code is available at: https://github.com/BIT-YangLab/CNN-IF.