Canada

While vision-language pre-trained models (VL-PTMs) have advanced multimodal research in recent years, their mastery in a few languages like English restricts their applicability in broader communities. To this end, there is an increasing interest in developing multilingual VL models via a joint-learning setup, which, however, could be unrealistic due to expensive costs and data availability. In this work, we propose to extend VL-PTMs&#39; language capacity by continual language learning (CLL), where a model needs to update its linguistic knowledge incrementally without suffering from catastrophic forgetting (CF). We begin our study by introducing a model dubbed CLL-CLIP, which builds upon CLIP, a prevailing VL-PTM that has acquired image-English text alignment. Specifically, CLL-CLIP contains an expandable token embedding layer to handle linguistic differences. It solely trains token embeddings to improve memory stability and is optimized under cross-modal and cross-lingual objectives to learn the alignment between images and multilingual texts. To alleviate CF raised by covariate shift and lexical overlap, we further propose a novel approach that ensures the identical distribution of all token embeddings during initialization and regularizes token embedding learning during training. We construct a CLL benchmark covering 36 languages based on MSCOCO and XM3600 datasets and then evaluate multilingual image-text retrieval performance. Extensive experiments verify the effectiveness of CLL-CLIP and show that our approach can boost CLL-CLIP, e.g., by 6.7% in text-to-image average Recall@1 on XM3600, and improve various state-of-the-art methods consistently. Our code and data are available at https://github.com/yangbang18/CLFM.

AAAI 2024

Embracing Language Inclusivity and Diversity in CLIP through Continual Language Learning

lifelong and continual learning

image retrieval

multilinguality

language and vision

### 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.

While vision-language pre-trained models (VL-PTMs) have advanced multimodal research in recent years, their mastery in a few languages like English restricts their applicability in broader communities. To this end, there is an increasing interest in developing multilingual VL models via a joint-learning setup, which, however, could be unrealistic due to expensive costs and data availability. In this work, we propose to extend VL-PTMs' language capacity by continual language learning (CLL), where a model needs to update its linguistic knowledge incrementally without suffering from catastrophic forgetting (CF). We begin our study by introducing a model dubbed CLL-CLIP, which builds upon CLIP, a prevailing VL-PTM that has acquired image-English text alignment. Specifically, CLL-CLIP contains an expandable token embedding layer to handle linguistic differences. It solely trains token embeddings to improve memory stability and is optimized under cross-modal and cross-lingual objectives to learn the alignment between images and multilingual texts. To alleviate CF raised by covariate shift and lexical overlap, we further propose a novel approach that ensures the identical distribution of all token embeddings during initialization and regularizes token embedding learning during training. We construct a CLL benchmark covering 36 languages based on MSCOCO and XM3600 datasets and then evaluate multilingual image-text retrieval performance. Extensive experiments verify the effectiveness of CLL-CLIP and show that our approach can boost CLL-CLIP, e.g., by 6.7% in text-to-image average Recall@1 on XM3600, and improve various state-of-the-art methods consistently. Our code and data are available at https://github.com/yangbang18/CLFM.

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.

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. 

Multi-exposure image fusion (MEF) has emerged as a prominent solution to address the limitations of digital imaging in representing varied exposure levels. Despite its advancements, the field grapples with challenges, notably the reliance on manual designs for network structures and loss functions, and the constraints of utilizing simulated reference images as ground truths. Consequently, current methodologies often suffer from color distortions and exposure artifacts, further complicating the quest for authentic image representation. In addressing these challenges, this paper presents a Hybrid-Supervised Dual-Search approach for MEF, dubbed HSDS-MEF, which introduces a bi-level optimization search scheme for automatic design of both network structures and loss functions. More specifically, we harness a unique dual research mechanism rooted in a novel weighted structure refinement architecture search. Besides, a hybrid supervised contrast constraint seamlessly guides and integrates with searching process, facilitating a more adaptive and comprehensive search for optimal loss functions. We realize the state-of-the-art performance in comparison to various competitive schemes, yielding a 10.61% and 4.38% improvement in Visual Information Fidelity (VIF)
for general and no-reference scenarios, respectively, while providing results with high contrast, rich details and colors.

Hybrid-Supervised Dual-Search: Leveraging Automatic Learning for Loss-Free Multi-Exposure Image Fusion

In the domain of scene graph generation, modeling commonsense as a single-prototype representation has been typically employed to facilitate the recognition of infrequent predicates. However, a fundamental challenge lies in the large intra-class variations of the visual appearance of predicates, resulting in subclasses within a predicate class. Such a challenge typically leads to the problem of misclassifying diverse predicates due to the rough predicate space clustering. In this paper, inspired by cognitive science, we maintain multi-prototype representations for each predicate class, which can accurately find the multiple class centers of the predicate space. Technically, we propose a novel multi-prototype learning framework consisting of three main steps: prototype-predicate matching, prototype updating, and prototype space optimization. We first design a triple-level optimal transport to match each predicate feature within the same class to a specific prototype. In addition, the prototypes are updated using momentum updating to find the class centers according to the matching results. Finally, we enhance the inter-class separability of the prototype space through iterations of the inter-class separability loss and intra-class compactness loss. Extensive evaluations demonstrate that our approach significantly outperforms state-of-the-art methods on the Visual Genome dataset.

Multi-Prototype Space Learning for Commonsense-Based Scene Graph Generation

Large-scale pre-training has proven to be an effective method for improving performance across different tasks. Current person search methods use ImageNet pre-trained models for feature extraction, yet it is not an optimal solution due to the gap between the pre-training task and person search task (as a downstream task). Therefore, in this paper, we focus on pre-training for person search, which involves detecting and re-identifying individuals simultaneously. Although labeled data for person search is scarce, datasets for two sub-tasks person detection and re-identification are relatively abundant. To this end, we propose a hybrid pre-training framework specifically designed for person search using sub-task data only. It consists of a hybrid learning paradigm that handles data with different kinds of supervisions, and an intra-task alignment module that alleviates domain discrepancy under limited resources. To the best of our knowledge, this is the first work that investigates how to support full-task pre-training using sub-task data. Extensive experiments demonstrate that our pre-trained model can achieve significant improvements across diverse protocols, such as person search method, fine-tuning data, pre-training data and model backbone. For example, our model improves ResNet50 based NAE by 10.3% relative improvement w.r.t. mAP. Our code and pre-trained models are released for plug-and-play usage to the person search community (https://github.com/personsearch/PretrainPS).

Divide and Conquer: Hybrid Pre-training for Person Search | VIDEO

Graph neural networks (GNNs) are commonly employed in collaborative friend recommendation systems. Nevertheless, recent studies reveal a notable performance gap, particularly for users with limited connections, commonly known as \textit{tail users}, in contrast to their counterparts with abundant connections (\textit{head users}). Uniformly treating head and tail users poses two challenges for tail user preference learning: \textit{(C1) Label Sparsity}, as tail users typically possess limited labels; and \textit{(C2) Neighborhood Sparsity}, where tail users exhibit sparse observable friendships, leading to distinct preference distributions and performance degradation compared to head users. In response to these challenges, we introduce Tail-STEAK, an innovative framework that combines self-training with enhanced knowledge distillation for tail user representation learning. To address \textit{(C1)}, we present Tail-STEAK$_{base}$, a two-stage self-training framework. In the first stage, only head users and their accurate connections are utilized for training, while pseudo links are generated for tail users in the second stage. To tackle \textit{(C2)}, we propose two data augmentation-based self-knowledge distillation pretext tasks. These tasks are seamlessly integrated into different stages of Tail-STEAK$_{base}$, culminating in the comprehensive Tail-STEAK framework. Extensive experiments, conducted on state-of-the-art GNN-based friend recommendation models, substantiate the efficacy of Tail-STEAK in significantly improving tail user performance. Our code and data are publicly available at https://github.com/antman9914/Tail-STEAK.

Tail-STEAK: Improve Friend Recommendation for Tail Users via Self-Training Enhanced Knowledge Distillation | VIDEO

The artificial neuron (N-N) model-based networks have accomplished extraordinary success for various vision tasks. However, as a simplification of the mammal neuron model, their structure is locked during training, resulting in overfitting and over-parameters. The astrocyte, newly explored by biologists, can adaptively modulate neuronal communication by inserting itself between neurons. The communication, between the astrocyte and neuron, is bidirectionally and shows the potential to alleviate issues raised by unidirectional communication in the N-N model. In this paper, we first elaborate on the artificial Multi-Astrocyte-Neuron (MA-N) model, which enriches the functionality of the artificial neuron model. Our MA-N model is formulated at both astrocyte- and neuron-level that mimics the bidirectional communication with temporal and joint mechanisms. Then, we construct the MA-Net network with the MA-N model, whose neural connections can be continuously and adaptively modulated during training. Experiments show that our MA-Net advances new state-of-the-art on multiple tasks while significantly reducing its parameters by connection optimization.

MA-Net: Rethinking Neural Unit in the Light of Astrocytes | VIDEO

The representative k-median problem generalizes the classical clustering formulations in that it partitions the data points into several disjoint demographic groups and poses a lower-bound constraint on the number of opened facilities from each group, such that all the groups are fairly represented by the opened facilities. Due to its simplicity, the local-search heuristic that optimizes an initial solution by iteratively swapping at most a constant number of closed facilities for the same number of opened ones (denoted by the O(1)-swap heuristic) has been frequently used in the representative k-median problem. Unfortunately, despite its good performance exhibited in experiments, whether the O(1)-swap heuristic has provable approximation guarantees for the case where the number of groups is more than 2 remains an open question for a long time. As an answer to this question, we show that the O(1)-swap heuristic
(1) is guaranteed to yield a constant-factor approximation solution if the number of groups is a constant, and
(2) has an unbounded approximation ratio otherwise.
Our main technical contribution is a new approach for theoretically analyzing local-search heuristics, which derives the approximation ratio of the O(1)-swap heuristic via linearly combining the increased clustering costs induced by a set of  hierarchically organized swaps.

Towards a Theoretical Understanding of Why Local Search Works for Clustering with Fair-Center Representation

Neuroscience shows that interaction of different brain functional regions drives different cognitive tasks. Existing studies focused on constructing local or global functional connectivity in the brain, lacking adaptive fusion of functional brain regions to explore latent relationships between localizations under different cognitive tasks. Here, this paper proposes a Local-Ascending-Global Learning Strategy (LAG) for mining higher-level potential topological patterns of functional brain regions. The strategy starts from the local connectivity of single brain functional regions, and constructs a K-level adaptive ascending network (SALK) to dynamically capture the strong connectivity of brain regions under different cognitive tasks. In the process of fusing brain regions step by step, higher-level latent patterns between brain functional regions are captured. With reference to previous studies, this is the first time to study the higher-level latent patterns of progressively adaptive fusion of various brain functional regions under different cognitive tasks. This paper uses the fatigue dataset (SEED-VIG), the emotion dataset (SEED-IV), and the motor imagery dataset (BCI_C_IV_2a) to verify the generalizability of LAG. The result shows that LAG achieves satisfactory results in independent-subject experiments on all three datasets, which suggests that LAG can characterize higher-level latent patterns of different cognitive tasks, providing a new idea for characterizing brain patterns under different cognitive tasks.

A Local-Ascending-Global Learning Strategy for Brain-Computer Interface

Multilingual code retrieval aims to find code snippets relevant to a user's query from a multilingual codebase, which plays a crucial role in software development and expands their application scenarios compared to classical monolingual code retrieval. Despite the performance improvements achieved by previous studies, two crucial problems are overlooked in the multilingual scenario. First, certain programming languages face data scarcity in specific domains, resulting in limited representation capabilities within those domains. Second, different programming languages can be used interchangeably within the same domain, making it challenging for multilingual models to accurately identify the intended programming language of a user's query. To address these issues, we propose the CommONalities and SpecIalties Driven Multilingual CodE Retrieval Framework (CONSIDER), which includes two modules. The first module enhances the representation of various programming languages by modeling pairwise and global commonalities among them. The second module introduces a novel contrastive learning negative sampling algorithm that leverages language confusion to automatically extract specific language features. Through our experiments, we confirm the significant benefits of our model in real-world multilingual code retrieval scenarios in various aspects. Furthermore, an evaluation demonstrates the effectiveness of our proposed CONSIDER framework in monolingual scenarios as well. Our source code is available at https://github.com/smsquirrel/consider.

CONSIDER: Commonalities and Specialties Driven Multilingual Code Retrieval Framework

Due to the wavelength-dependent light attenuation and scattering, the color of the underwater organism usually appears distorted. The existing underwater image enhancement methods mainly focus on designing networks capable of generating enhanced underwater organisms with fixed color. Different from the existing methods, this paper proposes an algorithm with color enhancement and color fine-tuning (CECF) capabilities. The color enhancement behavior of CECF is the same as that of existing methods, aiming to restore the color of the distorted underwater organism. Beyond this general purpose, the color fine-tuning behavior of CECF can adjust the color of organisms in a controlled manner, which can generate enhanced organisms with diverse colors. To achieve this purpose, four processes are used in CECF. A supervised enhancement process learns the mapping from a distorted image to an enhanced image by the decomposition of color code. A self-reconstruction process and a cross-reconstruction process are used for content-invariant learning. A color fine-tuning process is designed based on the guidance for obtaining various enhanced results with different colors. Experimental results have proven the enhancement ability and color fine-tuning ability of the proposed CECF. The source code is provided in the Supplementary Material.

Underwater Organism Color Fine-Tuning via Decomposition and Guidance

Invariant representation learning (IRL) encourages the prediction from invariant causal features to labels deconfounded from the environments, advancing the technical roadmap of out-of-distribution (OOD) generalization. Despite spotlights around, recent theoretical results verified that some causal features recovered by IRLs merely pretend domain-invariantly in the training environments but fail in unseen domains. The fake invariance severely endangers OOD generalization since the trustful objective can not be diagnosed and existing causal surgeries are invalid to rectify. In this paper, we review a IRL family (InvRat) under the Partially and Fully Informative Invariant Feature Structural Causal Models (PIIF SCM /FIIF SCM) respectively, to certify their weaknesses in representing fake invariant features, then, unify their causal diagrams to propose ReStructured SCM (RS-SCM). RS-SCM can ideally rebuild the spurious and the fake invariant features simultaneously. Given this, we further develop an approach based on conditional mutual information with respect to RS-SCM, then rigorously rectify the spurious and fake invariant effects. It can be easily implemented by a small feature selection subnet introduced in the IRL family, which is alternatively optimized to achieve our goal. Experiments verified the superiority of our approach to fight against the fake invariant issue across a variety of OOD generalization benchmarks.

Downloads

Next from AAAI 2024

Hybrid-Supervised Dual-Search: Leveraging Automatic Learning for Loss-Free Multi-Exposure Image Fusion

Similar lecture

AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities

.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

Hybrid-Supervised Dual-Search: Leveraging Automatic Learning for Loss-Free Multi-Exposure Image Fusion

Similar lecture

AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities

Downloads