Canada

The application of mixture-of-experts (MoE) is gaining popularity due to its ability to improve model&#39;s performance.  In an MoE structure, the gate layer plays a significant role in distinguishing and routing input features to different experts. This enables each expert to specialize in processing their corresponding sub-tasks. However, the gate&#39;s routing mechanism also gives rise to &quot;narrow vision&quot;: the individual MoE&#39;s expert fails to use more samples in learning the allocated subtask, which in turn limits the MoE to further improve its generalization ability. To effectively address this, we propose a method called Mixture-of-Distilled-Expert (MoDE), which applies moderate mutual distillation among experts to enable each expert to pick up more features learned by other experts and gain more accurate perceptions on their allocated sub-tasks. We conduct plenty experiments including tabular, NLP and CV datasets, which shows MoDE&#39;s effectiveness, universality and robustness. Furthermore, we develop a parallel study through innovatively constructing &quot;expert probing&quot;, to experimentally prove why MoDE works: moderate distilling knowledge from other experts can improve each individual expert&#39;s test performances on their assigned tasks, leading to MoE&#39;s overall performance improvement.

AAAI 2024

MoDE: A Mixture-of-Experts Model with Mutual Distillation among the Experts

mode

generalization ability

knowledge distillation

The application of mixture-of-experts (MoE) is gaining popularity due to its ability to improve model's performance.  In an MoE structure, the gate layer plays a significant role in distinguishing and routing input features to different experts. This enables each expert to specialize in processing their corresponding sub-tasks. However, the gate's routing mechanism also gives rise to "narrow vision": the individual MoE's expert fails to use more samples in learning the allocated subtask, which in turn limits the MoE to further improve its generalization ability. To effectively address this, we propose a method called Mixture-of-Distilled-Expert (MoDE), which applies moderate mutual distillation among experts to enable each expert to pick up more features learned by other experts and gain more accurate perceptions on their allocated sub-tasks. We conduct plenty experiments including tabular, NLP and CV datasets, which shows MoDE's effectiveness, universality and robustness. Furthermore, we develop a parallel study through innovatively constructing "expert probing", to experimentally prove why MoDE works: moderate distilling knowledge from other experts can improve each individual expert's test performances on their assigned tasks, leading to MoE's overall performance improvement.

technical paper

We are pleased to announce the Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI-24), which will be held in Vancouver, British Columbia at the Vancouver Convention Centre – West Building from 20-27 February, 2024.

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-24 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.

We expect for AAAI-24 to be an in-person conference – one author of all accepted papers will be expected to present work in person unless there are exceptional circumstances that prevent this.<br><br><br><br>

In order to access the AAAI-24 event page you need to register [here](https://aaai.org/aaai-conference/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. 

Recently decades have witnessed the empirical success of framing Knowledge Graph (KG) embeddings via language models. However, language model-based KG embeddings are usually deployed as static artifacts, which makes them difficult to modify post-deployment without undergoing re-training after deployment. To address this issue, we propose a new task of editing language model-based KG embeddings in this paper. This task is designed to facilitate rapid, data-efficient updates to KG embeddings without compromising the performance of other aspects. We build four new datasets: E-FB15k237, A-FB15k237, E-WN18RR, and A-WN18RR, and evaluate several knowledge editing baselines demonstrating the limited ability of previous models to handle the proposed challenging task. We further propose a simple yet strong baseline dubbed KGEditor, which utilizes additional parametric layers of the hyper network to edit/add facts. Our comprehensive experimental results reveal that KGEditor excels in updating specific facts without impacting the overall performance, even when faced with limited training resources Code and datasets will be available in https://github.com/AnonymousForPapers/DeltaKG.

Editing Language Model-Based Knowledge Graph Embeddings

Scene text recognition is inherently a vision-language task. However, previous works have predominantly focused either on extracting more robust visual features or designing better language modeling. How to effectively and jointly model vision and language to mitigate heavy reliance on a single modality remains a problem. In this paper, aiming to enhance vision-language reasoning in scene text recognition, we present a balanced, unified and synchronized vision-language reasoning network (BUSNet). Firstly, revisiting the image as a language by balanced concatenation along length dimension alleviates the issue of over-reliance on vision or language. Secondly, BUSNet learns an ensemble of unified external and internal vision-language model with shared weight by masked modality modeling (MMM). Thirdly, a novel vision-language reasoning module (VLRM) with synchronized vision-language decoding capacity is proposed. Additionally, BUSNet achieves improved performance through iterative reasoning, which utilizes the vision-language prediction as a new language input. Extensive experiments indicate that BUSNet achieves state-of-the-art performance on several mainstream benchmark datasets and more challenge datasets for both synthetic and real training data compared to recent outstanding methods. Code and dataset will be available at https://github.com/jjwei66/BUSNet.

Image as a Language: Revisiting Scene Text Recognition via Balanced, Unified and Synchronized Vision-Language Reasoning Network | VIDEO

As a kind of 3D data, RGB-D images have been extensively used in object tracking, 3D reconstruction, remote sensing mapping, and other tasks. In the realm of computer vision, the significance of RGB-D images is progressively growing. However, the existing learning-based image compression methods usually process RGB images and depth images separately, which cannot entirely exploit the redundant information between the modalities, limiting the further improvement of the Rate-Distortion performance. With the goal of overcoming the defect, in this paper, we propose a learning-based dual-branch RGB-D image compression framework. Compared with traditional RGB domain compression scheme, a YUV domain compression scheme is presented for spatial redundancy removal. In addition, Intra-Modality Attention (IMA) and Cross-Modality Attention (CMA) are introduced for modal redundancy removal. For the sake of benefiting from cross-modal prior information, Context Prediction Module (CPM) and Context Fusion Module (CFM) are raised in the conditional entropy model which makes the context probability prediction more accurate. The experimental results demonstrate our method outperforms existing image compression methods in two RGB-D image datasets. Compared with BPG, our proposed framework can achieve up to 15% bit rate saving for RGB images.

End-to-End RGB-D Image Compression via Exploiting Channel-Modality Redundancy

Decentralized Stochastic Gradient Descent (D-SGD) represents an efficient communication approach tailored for mastering insights from vast, distributed datasets. Inspired by parallel optimization paradigms, the incorporation of minibatch serves to diminish variance, consequently expediting the optimization process. Nevertheless, as per our current understanding, the existing literature has not thoroughly explored the learning theory foundation of Decentralized Minibatch Stochastic Gradient Descent (DM-SGD). In this paper, we try to address this theoretical gap by investigating the generalization properties of DM-SGD. We establish the sharper generalization bounds for the DM-SGD algorithm with replacement (without replacement) on (non)convex and (non)smooth cases. Moreover, our results consistently recover to the results of Centralized Stochastic Gradient Descent (C-SGD). In addition, we derive generalization analysis for Zero-Order (ZO) version of DM-SGD.

Towards Stability and Generalization Bounds in Decentralized Minibatch Stochastic Gradient Descent | VIDEO

With the increasing need for facial behavior analysis, semi-supervised AU intensity estimation using only keyframe annotations has emerged as a practical and effective solution to relieve the burden of annotation. However, the lack of annotations makes the spurious correlation problem caused by AU co-occurrences and subject variation much more prominent, leading to non-robust intensity estimation that is entangled among AUs and biased among subjects. We observe that trend information inherent in keyframe annotations could act as extra supervision and raising the awareness of AU-specific facial appearance changing trends during training is the key to learning invariant AU-specific features. To this end, we propose Trend-AwareSupervision (TAS), which pursues three kinds of trend awareness, including intra-trend ranking awareness, intra-trend speed awareness, and inter-trend subject awareness. TAS alleviates the spurious correlation problem by raising trend awareness during training to learn AU-specific features that represent the corresponding facial appearance changes, to achieve intensity estimation invariance. Experiments conducted on two commonly used AU benchmark datasets, BP4D and DISFA, show the effectiveness of each kind of awareness. And under trend-aware supervision, the performance can be improved without extra computational or storage costs during inference.

Trend-Aware Supervision: On Learning Invariance for Semi-supervised Facial Action Unit Intensity Estimation

Source detection in graphs has demonstrated robust efficacy in the domain of rumor source identification. Although recent solutions have enhanced performance by leveraging deep neural networks, they often require complete user data. In this paper, we address a more challenging task, rumor source detection with incomplete user data, and propose a novel framework, i.e., Source Detection in Graphs with Incomplete Nodes via Positional Encoding and Attentive Fusion (GIN-SD), to tackle this challenge. Specifically, our approach utilizes a positional embedding module to distinguish nodes that are incomplete and employs a self-attention mechanism to focus on nodes with greater information transmission capacity. To mitigate the prediction bias caused by the significant disparity between the numbers of source and non-source nodes, we also introduce a class-balancing mechanism. Extensive experiments validate the effectiveness of GIN-SD and its superiority to state-of-the-art methods.

GIN-SD: Source Detection in Graphs with Incomplete Nodes via Positional Encoding and Attentive Fusion

Recurrent Neural Cascades (RNCs) are the recurrent neural networks with no cyclic dependencies among recurrent neurons. This class of recurrent networks has received a lot of attention in practice. Besides training methods for a fixed architecture such as backpropagation, the cascade architecture naturally allows for constructive learning methods, where recurrent nodes are added incrementally one at a time, often yielding smaller networks. Furthermore, acyclicity amounts to a structural prior that even for the same number of neurons yields a more favourable sample complexity compared to a fully-connected architecture.
A central question is whether the advantages of the cascade architecture come at the cost of a reduced expressivity. We provide new insights into this question. We show that the regular languages captured by RNCs with sign and tanh activation with positive recurrent weights are the star-free regular languages. In order to establish our results we developed a novel framework where capabilities of RNCs are assessed by analysing which semigroups and groups a single neuron is able to implement. A notable implication of our framework is that RNCs can achieve the expressivity of all regular languages by introducing neurons that can implement groups.

On the Expressivity of Recurrent Neural Cascades

Training data in federated learning (FL) frameworks can have label noise, since they must be stored and annotated on clients' devices. 
If trained over such corrupted data, the models learn the wrong knowledge of label noise, which highly degrades their performance.  
Although several FL schemes are designed to combat label noise, they suffer performance degradation when the clients' devices only have limited local training samples.
To this end, a new scheme called federated label-noise learning (FedLNL) is developed in this paper.
The key problem of FedLNL is how to estimate a noise transition matrix (NTM) accurately in the case of limited local training samples.
If a gradient-based update method is used to update the local NTM on each client's device, it can generate too large gradients for the local NTM, causing a high estimation error of the local NTM.
To tackle this issue, an alternating update method for the local NTM and the local classifier is designed in FedLNL, where the local NTM is updated by a Bayesian inference-based update method.
Such an alternating update method makes the loss function of existing NTM-based schemes not applicable to FedLNL.
To enable federated optimization of FedLNL, a new regularizer on the parameters of the classifier called local diversity product regularizer is designed for the loss function of FedLNL. 
The results show that FedLNL improves the test accuracy of a trained model by up to 25.98%, compared with the state-of-the-art FL schemes that tackle label-noise issues.

Federated Label-Noise Learning with Local Diversity Product Regularization

Previous face Presentation Attack Detection (PAD) methods aim to improve the effectiveness of cross-domain tasks. However, in real-world scenarios, the original training data of the pre-trained model is not available due to data privacy or other reasons. Under these constraints, general methods for fine-tuning single-target domain data may lose previously learned knowledge, leading to a catastrophic forgetting problem. To address these issues, we propose a multi-domain incremental learning (MDIL) method for PAD, which not only learns knowledge well from the new domain but also maintains the performance of previous domains stably. Specifically, we propose an adaptive domain-specific experts (ADE) framework based on the vision transformer to preserve the discriminability of previous domains. Furthermore,  an asymmetric classifier is designed to keep the output distribution of different classifiers consistent, thereby improving the generalization ability. Extensive experiments show that our proposed method achieves state-of-the-art performance compared to prior methods of incremental learning. Excitingly, under more stringent setting conditions, our method approximates or even outperforms the DA/DG-based methods.

Multi-Domain Incremental Learning for Face Presentation Attack Detection | VIDEO

Within the scope of natural language processing, the domain of multi-label text classification is uniquely challenging due to its expansive and uneven label distribution. The complexity deepens due to the demand for an extensive set of annotated data for training an advanced deep learning model, especially in specialized fields where the labeling task can be labor-intensive and often requires domain-specific knowledge. Addressing these challenges, our study introduces a novel deep active learning strategy, capitalizing on the Beta family of proper scoring rules within the Expected Loss Reduction framework. It computes the expected increase in scores using the Beta Scoring Rules,  which are then transformed into sample vector representations. These vector representations guide the diverse selection of informative sample, directly linking this process to the model's expected proper score. Comprehensive evaluations across both synthetic and real datasets reveal our method's capability to often outperform established acquisition techniques in multi-label text classification, presenting encouraging outcomes across various architectural and dataset scenarios.

Content not yet available

MoDE: A Mixture-of-Experts Model with Mutual Distillation among the Experts

Downloads

Next from AAAI 2024

Editing Language Model-Based Knowledge Graph Embeddings

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Content not yet available

MoDE: A Mixture-of-Experts Model with Mutual Distillation among the Experts

.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 2024

Editing Language Model-Based Knowledge Graph Embeddings

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads