United States

Existing knowledge distillation (KD) methods have demonstrated their ability in achieving student network performance on par with their teachers. However, the knowledge gap between the teacher and student remains significant and may hinder the effectiveness of the distillation process. In this work, we introduce
 the
structure of Neural Collapse (NC) into the KD framework. NC typically occurs in the
final phase of training, resulting in a graceful geometric structure where the last-layer features form a simplex equiangular tight frame. Such phenomenon has improved the generalization of deep network training. 
We hypothesize that NC can also alleviate the knowledge gap in distillation, thereby enhancing student performance. This paper begins with an empirical analysis to bridge the connection between knowledge distillation and neural collapse. Through this analysis, we establish that transferring the teacher&#39;s NC structure to the student benefits the distillation process. Therefore, instead of merely transferring instance-level logits or features, as done by existing distillation methods, we encourage students to learn the teacher&#39;s NC structure. Thereby, we propose a 
new distillation paradigm termed Neural Collapse-inspired Knowledge Distillation (NCKD). Comprehensive experiments demonstrate that NCKD is simple yet effective, 
improving the generalization of all distilled student models and achieving state-of-the-art accuracy performance.

AAAI 2025

Neural Collapse Inspired Knowledge Distillation

learning on the edge

model compression

### Welcome to ACL 2023, the 61st Annual Meeting of the Association for Computational Linguistics! 
 The conference will be held in Toronto, Canada, July 9-14, 2023. 
Following the succession of the recent conferences in our field, ACL 2023 will adopt a hybrid format.
While the impact of Covid has considerably diminished in terms of traveling, obtaining visas to Canada
entails a very long process. Moreover, the global economic conditions pose challenges for many individuals to travel to conferences. Recognizing these circumstances, we know many participants may not be
able to attend the conference in person. Therefore, we are committed to providing a great virtual platform
so everyone has the opportunity to interact with other participants and enjoy the conference. Based on the
current registered participants, approxiately 30% have chosen to attend the conference virtually. Whether
you join us in person or virtually, we sincerely hope everyone has a remarkable conference experience. 
This General Chair’s message is where I express my gratitude to the many individuals who have made
enormous contributions to the conference over the past year.

Read [**ACL 2023 General Chair's message**](https://docs.google.com/document/d/1WobYM7norbG4dI48s75HfJoD89qgX5a_F-6U8AteLSA/edit?usp=sharing/) in full.

##### **[Conference Handbook](https://2023.aclweb.org/downloads/acl2023-handbook.pdf)**

ACL 2023

The Association for Computational Linguistics (ACL) is the premier international scientific and professional society for people working on computational problems involving human language, a field often referred to as either computational linguistics or natural language processing.

Existing knowledge distillation (KD) methods have demonstrated their ability in achieving student network performance on par with their teachers. However, the knowledge gap between the teacher and student remains significant and may hinder the effectiveness of the distillation process. In this work, we introduce
 the
structure of Neural Collapse (NC) into the KD framework. NC typically occurs in the
final phase of training, resulting in a graceful geometric structure where the last-layer features form a simplex equiangular tight frame. Such phenomenon has improved the generalization of deep network training. 
We hypothesize that NC can also alleviate the knowledge gap in distillation, thereby enhancing student performance. This paper begins with an empirical analysis to bridge the connection between knowledge distillation and neural collapse. Through this analysis, we establish that transferring the teacher's NC structure to the student benefits the distillation process. Therefore, instead of merely transferring instance-level logits or features, as done by existing distillation methods, we encourage students to learn the teacher's NC structure. Thereby, we propose a 
new distillation paradigm termed Neural Collapse-inspired Knowledge Distillation (NCKD). Comprehensive experiments demonstrate that NCKD is simple yet effective, 
improving the generalization of all distilled student models and achieving state-of-the-art accuracy performance.

poster

We are pleased to announce the Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI-25), which will be held in Philadelphia, Pennsylvania at the Pennsylvania Convention Center from February 25 to March 4, 2025.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-25 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

### [Invited Speakers](https://aaai.org/conference/aaai/aaai-25/aaai-25-invited-speakers/)

Register [here](https://aaai.org/conference/aaai/aaai-25/registration/)

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-25 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.



Hypergraphs are powerful mathematical structures that can model complex, high-order relationships in various domains, including social networks, bioinformatics, and recommender systems. However, generating realistic and diverse hypergraphs remains challenging due to their inherent complexity and lack of effective generative models. In this paper, we introduce a diffusion-based Hypergraph Generation (HYGENE) method that addresses these challenges through a progressive local expansion approach. HYGENE works on the bipartite representation of hypergraphs, starting with a single pair of connected nodes and iteratively expanding it to form the target hypergraph. At each step, nodes and hyperedges are added in a localized manner using a denoising diffusion process, which allows for the construction of the global structure before refining local details. Our experiments demonstrated the effectiveness of HYGENE, proving its ability to closely mimic a variety of properties in hypergraphs. To the best of our knowledge, this is the first attempt to employ deep learning models for hypergraph generation, and our work aims to lay the groundwork for future research in this area.

HYGENE: A Diffusion-Based Hypergraph Generation Method

A market maker is a specialist who provides liquidity by continuously offering bid and ask quotes for a financial asset. The market maker’s objective is to maximize profit while avoiding the accumulation of a large position in the asset to control inventory risk. To achieve model-free results, online learning has been applied to design market-making strategies that make no assumptions on the dynamics of the limit order book and asset price. However, existing work primarily focuses on profit rather than inventory risk. To address this limitation, this paper develops market-making strategies with inventory constraints within the online learning framework. To manage inventory risk, we propose two classes of market-making strategies with fixed bid-ask spreads that serve as reference strategies. Each reference strategy can ensure that the inventory remains under control, which enables the online learning algorithms designed for each class of reference strategies to satisfy inventory constraints. Different from the standard online learning model where the gain in each period is assumed to lie within a fixed bounded interval, the gain in our model depends on a state variable (i.e., the inventory size). Thus, a key challenge in analyzing the regret bounds is to bound the difference between the gains of any two reference strategies, which becomes significantly more complicated compared with scenarios without inventory constraints. By tackling these difficulties, we show that these algorithms achieve low regrets. Experimental results illustrate the superior performance of our algorithms in inventory risk control.

Adaptive Market Making with Inventory Constraints via Online Learning

Edit-based approaches for Grammatical Error Correction (GEC) have attracted volume attention due to their outstanding explanations of the correction process and rapid inference. Through our exploring the characteristics of the generalized and specific knowledge learned for GEC, we discover efficiently training GEC system with satisfactory generalization capacity prefers more generalized knowledge rather than specific knowledge. Current gradient-based methods for training GEC system, however, usually prioritize minimizing training loss over generalization loss. This paper proposes the strategy of Adjusting Learning Rate Based on Memory Rate to optimize of Adjusting Learning Rate Based on Memory Rate to optimize the edit-based GEC scorer (ALRMR-GEC). Specifically, we introduce the memory rate, a novel metric, to provide an explicit indicator for the model’s state of learning generalized and specific knowledge, which can effectively guide GEC system to timely adjust the learning rate. Extensive experiments, conducted by optimizing the published editscorer (Sorokin 2022) on BEA2019 dataset, have shown our ALRMR-GEC significantly enhances the model generalization ability with stable and satisfactory performance irrespective of the initial learning rate selection. Also, our method can accelerate the training over tenfold faster in certain cases. Finally, the experiments indicate the memory rate induced in our ALRMR-GEC surpasses the gradient as a more informative metric to guide the GEC editscorer to learn more generalized knowledge. Our code will be released as soon as possible.

ALRMR-GEC: Adjusting Learning Rate Based on Memory Rate to Optimize the Edit Scorer for Grammatical Error Correction

The insufficient generalization of adaptive moment estimation (Adam) has hindered its broader application. Recent studies have shown that flat minima in loss landscapes are highly associated with improved generalization.  Inspired by the filtering effect of integration operations on high-frequency signals, we propose multiple integral Adam (MIAdam), a novel optimizer that integrates a multiple integral term into Adam. This multiple integral term effectively filters out sharp minima encountered during optimization, guiding the optimizer towards flatter regions and thereby enhancing generalization capability. We provide a theoretical explanation for the improvement in generalization through the diffusion theory framework and analyze the impact of the multiple integral term on the optimizer's convergence. Experimental results demonstrate that MIAdam not only enhances generalization and robustness against label noise but also maintains the rapid convergence characteristic of Adam, outperforming Adam and its variants in state-of-the-art benchmarks.

A Method for Enhancing Generalization of Adam by Multiple Integrations

In this work, we extend the concept of the $p$-mean welfare objective from social choice theory (Moulin 2004) to study $p$-mean regret in stochastic multi-armed bandit problems. The $p$-mean regret, defined as the difference between the optimal mean among the arms and the $p$-mean of the expected rewards, offers a flexible framework for evaluating bandit algorithms, enabling algorithm designers to balance fairness and efficiency by adjusting the parameter $p$. Our framework encompasses both average cumulative regret and Nash regret as special cases.

We introduce a simple, unified UCB-based algorithm (Explore-Then-UCB) that achieves novel $p$-mean regret bounds. Our algorithm consists of two phases: a carefully calibrated uniform exploration phase to initialize sample means, followed by the UCB1 algorithm of (Auer et al. 2002). Under mild assumptions, we prove that our algorithm achieves a $p$-mean regret bound of $\tilde{O}\left(\sqrt{\frac{k}{T^{\frac{1}{2|p|}}}}\right)$ for all $p \leq -1$, where $k$ represents the number of arms and $T$ the time horizon. When $-1<p<0$, we achieve a regret bound of $\tilde{O}\left(\sqrt{\frac{k^{1.5}}{T^{\frac{1}{2}}}}\right)$. For the range $0< p \leq 1$, we achieve a $p$-mean regret scaling as $\tilde{O}\left(\sqrt{\frac{k}{T}}\right)$, which matches the previously established lower bound up to logarithmic factors (Auer et al. 1995). This result stems from the fact that the $p$-mean regret of any algorithm is at least its average cumulative regret for $p \leq 1$.
In the case of Nash regret (the limit as $p$ approaches zero), our unified approach differs from prior work (Barman et al. 2023), which requires a new Nash Confidence Bound algorithm. Notably, we achieve the same regret bound up to constant factors using our more general method.

p-Mean Regret for Stochastic Bandits

Knowledge distillation transfers "dark knowledge" from a large teacher model to a smaller student model, yielding a highly efficient network. 
To improve network's generalization ability, existing works use a larger temperature coefficient for knowledge distillation. Nevertheless, these methods may lower the target category's confidence and lead to ambiguous recognition of similar samples. To mitigate this issue, some studies introduce intra-batch distillation to reduce prediction discrepancy. However, these methods overlook the inconsistency between background information and the target category, which may increase prediction bias due to noise disturbance. Additionally, label imbalance from random sampling and batch size can undermine network generalization reliability. To tackle these challenges, we propose a simple yet effective Intra-class Knowledge Distillation (IKD) method that facilitates knowledge sharing within the same class to ensure consistent predictions. First, we initialize the matrix and the vector to store logits and class counts provided by the teacher, respectively. Then, in the first epoch, we calculate the sum of logits and sample counts per class and perform KD to prevent knowledge omission. Finally, in subsequent training, we update the matrix to obtain the average logits and compute the KL divergence between the student's output and the updated matrix according to the label index. This process ensures intra-class consistency and improves the student's performance. Furthermore, this method theoretically reduces prediction bias by ensuring intra-class consistency. Extensive experiments on the CIFAR-100, ImageNet-1K, and Tiny-ImageNet datasets validate the superiority of IKD. The code will be made publicly available.

Debiased Distillation for Consistency Regularization

Dense video captioning aims to detect and describe all events in untrimmed videos. This paper presents a dense video captioning network called Multi-Concept Cyclic Learning (MCCL), which aims to: (1) detect multiple concepts at the frame level, using these concepts to enhance video features and provide temporal event cues; (2) design cyclic co-learning between the generator and the localizer within the captioning network to promote semantic perception and event localization. Specifically, we perform weakly supervised concept detection for each frame, and the detected concept embeddings are integrated into the video features to provide event cues. Additionally, video-level concept contrastive learning is introduced to obtain more discriminative concept embeddings. In the captioning network, we establish a cyclic co-learning strategy where the generator guides the localizer for event localization through semantic matching, while the localizer enhances the generator’s event semantic perception through location matching, making semantic perception and event localization mutually beneficial. MCCL achieves state-of-the-art performance on the ActivityNet Captions and YouCook2 datasets. Extensive experiments demonstrate its effectiveness and interpretability.

Exploring Temporal Event Cues for Dense Video Captioning in Cyclic Co-Learning

Growing customer demand for smart solutions in robotics and augmented reality has attracted considerable attention to 3D object detection from point clouds. Yet, existing indoor datasets taken individually are too small and insufficiently diverse to train a powerful and general 3D object detection model. In the meantime, more general approaches utilizing foundation models are still inferior in quality to those based on supervised training for a specific task.
In this work, we propose UniDet3D, a simple yet effective 3D object detection model, which is trained on a mixture of indoor datasets and is capable to work in various indoor environments. By unifying different label spaces, UniDet3D enables learning a strong representation across multiple datasets through a supervised joint training scheme. The proposed network architecture is built upon a vanilla transformer encoder, making it easy to run, customize and extend the prediction pipeline for practical use. Extensive experiments demonstrate that UniDet3D obtains significant gains over existing 3D object detection methods in 6 indoor benchmarks: ScanNet (+1.1 $mAP_{50}$), S3DIS (+9.1 $mAP_{50}$), ARKitScenes (+19.4 $mAP_{25}$), MultiScan (+14.3 $mAP_{50}$), 3RScan (+3.2 $mAP_{50}$), and ScanNet++ (+2.7 $mAP_{50}$).

UniDet3D: Multi-dataset Indoor 3D Object Detection

In recent years, visually-rich document understanding has attracted increasing attention. Transformer-based pre-trained models have become the mainstream approach, yielding significant performance gains in this field. However, the self-attention mechanism's quadratic computational complexity hinders their efficiency and ability to process long documents. In this paper, we present DocMamba, a novel framework based on the state space model. It is designed to reduce computational complexity to linear while preserving global modeling capabilities. To further enhance its effectiveness in document processing, we introduce the Segment-First Bidirectional Scan (SFBS) to capture contiguous semantic information. Experimental results demonstrate that DocMamba achieves new state-of-the-art results on downstream datasets such as FUNSD, CORD, and SORIE, while significantly improving speed and reducing memory usage. Notably, experiments on the HRDoc confirm DocMamba's potential for length extrapolation. The code is included in the supplementary material and will also be available online.

DocMamba: Efficient Document Pre-training with State Space Model

Text-video retrieval (TVR) has seen substantial advancements in recent years, fueled by the utilization of pre-trained models and large language models (LLMs). Despite these advancements, achieving accurate matching in TVR remains challenging due to inherent disparities between video and textual modalities and irregularities in data representation. In this paper, we propose Text-Video-ProxyNet (TV-ProxyNet), a novel framework designed to decompose the conventional 1-to-$N$ relationship of TVR into $N$ distinct 1-to-1 relationships. By replacing a single text query with a series of text proxies, TV-ProxyNet not only broadens the query scope but also achieves a more precise expansion. Each text proxy is crafted through a refined iterative process, controlled by mechanisms we term as the director and dash, which regulate the proxy's direction and distance relative to the original text query. This setup not only facilitates more precise semantic alignment but also effectively manages the disparities and noise inherent in multimodal data. Our experiments on three representative video-text retrieval benchmarks, MSRVTT, DiDeMo, and ActivityNet Captions, demonstrate the effectiveness of TV-ProxyNet. The results show an improvement of 2.0\% to 3.3\% in R@1 over the baseline. TV-ProxyNet achieved state-of-the-art performance on MSRVTT and ActivityNet Captions, and a 2.0\% improvement on DiDeMo compared to existing methods, validating our approach's ability to enhance semantic mapping and reduce error propensity.

Downloads

Next from AAAI 2025

HYGENE: A Diffusion-Based Hypergraph Generation Method

Similar lecture

ReAugKD: Retrieval-Augmented Knowledge Distillation For Pre-trained Language Models

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2025

HYGENE: A Diffusion-Based Hypergraph Generation Method

Similar lecture

ReAugKD: Retrieval-Augmented Knowledge Distillation For Pre-trained Language Models

Downloads