United States

Data augmentation methods, especially SoTA interpolation-based methods such as Fair Mixup, have been widely shown to increase model fairness. However, this fairness is evaluated on metrics that do not capture model uncertainty and on datasets with only one, relatively large, minority group. As a remedy, multicalibration has been introduced to measure fairness while accommodating uncertainty and accounting for multiple minority groups. However, existing methods of improving multicalibration involve reducing initial training data to create a holdout set for post-processing, which is not ideal when minority training data is already sparse. This paper uses multicalibration to more rigorously examine data augmentation for classification fairness. We stress-test four versions of Fair Mixup on two structured data classification problems with up to 81 marginalized groups, evaluating multicalibration violations and balanced accuracy. We find that on nearly every experiment, Fair Mixup $\textit{worsens}$ baseline performance and fairness, but the simple vanilla Mixup $\textit{outperforms}$ both Fair Mixup and the baseline, especially when calibrating on small groups. $\textit{Combining}$ vanilla Mixup with multicalibration post-processing, which enforces multicalibration through post-processing on a holdout set, further increases fairness.

AAAI 2025

Who’s the (Multi-)Fairest of Them All: Rethinking Interpolation-Based Data Augmentation Through the Lens of Multicalibration

transparency

ethics

fairness

bias

privacy

stages 

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

First established in 1965, the biennial COLING conference is held in diverse parts of the globe and attracts participants from both top-ranked research centers and emerging countries. Today, the most important developments in our field are taking place not only in universities and academic research institutes, but also in industrial research departments and in technological startups. COLING conferences provide opportunities for all these communities to showcase their exciting developments.

COLING 2020

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

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.



The unwavering disparity in labeled resources between resource-rich languages and those considered low-resource remains a significant impediment for Large Language Models (LLMs). Recent strides in cross-lingual in-context learning (X-ICL), mainly through semantically aligned examples retrieved from multilingual pre-trained transformers, have shown promise in mitigating this issue. However, our investigation reveals that LLMs intrinsically reward in-language semantically aligned cross-lingual instances over direct cross-lingual semantic alignments, with a pronounced disparity in handling time-sensitive queries in X-ICL setup. Such queries demand sound temporal reasoning ability from LLMs, yet the advancements have predominantly focused on English. This study aims to bridge this gap by enhancing temporal reasoning capabilities in low-resource languages. To this end, we introduce a temporal reasoning dataset, $\texttt{mTEMPREASON}$ aimed at the varied degrees of low-resource languages and propose a novel method, Cross-Lingual Time-Sensitive Semantic Alignment ($\texttt{CLiTSSA}$), to elevate temporal reasoning in these contexts. To facilitate this, we construct an extension of $\texttt{mTEMPREASON}$ comprising pairs of parallel cross-language temporal queries along with their anticipated in-language semantic similarity scores. Our empirical evidence underscores the superior performance of $\texttt{CLiTSSA}$ compared to established baselines across three languages- Romanian, German, and French, encompassing three temporal tasks and including a diverse set of four contemporaneous LLMs. This marks a significant step forward in addressing the resource disparity in the temporal reasoning context across languages.

Multilingual LLMs Inherently Reward In-Language Time-Sensitive Semantic Alignment for Low-Resource Languages

Prompt learning has emerged as a promising method for adapting pre-trained visual-language models (VLMs) to a wide range of downstream tasks. Advanced
prompt learning methods usually initialize and optimize the context, e.g., ``a photo of a []'', for downstream task adaptation. While optimizing the context can be effective for improving performance on specific tasks, it can often lead to poor generalization performance on unseen classes or datasets sampled from different distributions. It may be attributed to that textual prompts tend to overfit downstream data distributions, leading to the forgetting of hand-crafted general textual knowledge having a strong generalization ability.
In this paper, we propose a  novel method called Similarity Paradigm with Textual Regularization  (SPTR) for prompt learning without forgetting. SPTR is a two-pronged design, which is an inseparable framework.  1) To   avoid forgetting general textual knowledge, we introduce an adaptive  plan  as a textual regularization to ensure approximation with  hand-crafted features and tuning textual features. 2) To improve model robustness for generalization, we propose a  similarity paradigm for natural alignment score and adversarial alignment score. Both modules share a common objective in addressing generalization issues, aiming to maximize the generalization capability derived from hand-crafted prompts. 4 representative tasks
(i.e.,  non-generalization classification, base-to-novel generalization, cross-dataset generalization,  domain shifts generalization) across  15 datasets demonstrate that SPTR outperforms existing prompt learning methods.

A Similarity Paradigm through Textual Regularization without Forgetting

Large language models (LLMs) require model editing to efficiently update specific knowledge within them and avoid factual errors. 
Most model editing methods are solely designed for single-time use and result in a significant forgetting effect in lifelong editing scenarios, where sequential edits are conducted over time.
Previous approaches manage sequential edits by freezing original parameters and discretely allocating new parameters for each knowledge update.
However, these methods lack robustness to minor input variations due to the discrete mapping between data and parameters. 
To overcome this challenge, we propose ELDER, a novel approach to create a continuous association between data and adapters. 
ELDER integrates multiple LoRAs through a router network and is trained to establish a smooth data-adapter association, thereby enhancing the edit robustness and generalization of semantically equivalent inputs.
To ensure inputs containing the same knowledge will be processed by the same LoRAs, we design a novel loss to guide the model link LoRA allocations with edit knowledge.
Furthermore, we propose a deferral mechanism to retain the original LLM capabilities post-edit. 
Extensive experiments on GPT-2 XL and LLaMA2-7B demonstrate that ELDER effectively edits models in the lifelong setting, outperforming eight baselines while exhibiting strong scalability and preserving LLMs' general abilities on downstream tasks.

ELDER: Enhancing Lifelong Model Editing with Mixture-of-LoRA

Currently, 3D rendering for large-scale free camera trajectories, namely, arbitrary input camera trajectories, poses significant challenges: 1) The distribution and observation angles of the cameras are irregular, and various types of scenes are included in the free trajectories; 2) Processing the entire point cloud and all images at once for large-scale scenes requires a substantial amount of GPU memory. This paper presents a Toy-GS method for accurately rendering large-scale free camera trajectories. Specifically, we propose an adaptive spatial division approach for free trajectories to divide cameras and the sparse point cloud of the entire scene into various regions according to camera poses. Training each local Gaussian in parallel for each area enables us to concentrate on texture details and minimize GPU memory usage. Next, we use the multi-view constraint and position-aware point adaptive control (PPAC) to improve the rendering quality of texture details. In addition, our regional fusion approach combines local and global Gaussians to enhance rendering quality with an increasing number of divided areas. Extensive experiments have been carried out to confirm the effectiveness and efficiency of Toy-GS, leading to state-of-the-art results on two public large-scale datasets as well as our SCUTic dataset. Our proposal demonstrates an enhancement of 1.19 dB in PSNR and conserves 7 G of GPU memory when compared to various benchmarks.

Toy-GS: Assembling Local Gaussians for Precisely Rendering Large-Scale Free Camera Trajectories

Multi-task learning (MTL) is widely utilized across a variety of real-world applications, including recommendation systems. For instance, in the field of e-commerce, MTL is commonly employed to simultaneously model click, conversion, and user dwelling time. Among a various of MTL models, the Multi-gate Mixture-of-Experts (MMoE) has gained significant popularity. However, MMoE suffers from the polarization issue during training, where the weights of certain experts tend to converge towards 0. To address this issue, we propose a novel method called $\textbf{B}$agging-$\textbf{E}$xpert $\textbf{net}$work (BEnet) for multi-task learning. BEnet effectively mitigates the problem of polarization and achieves excellent performance in multi-task learning. It incorporates a bagging layer and an attention mechanism to encourage experts focusing on diverse knowledge domains. Simultaneously, polarization is avoided as different experts execute respective duties and specialize in distinct domains. Experimental results on real-world datasets demonstrate that BEnet has strong robustness and outperforms other state-of-the-art (SOTA) MTL methods.

Bagging-Expert Network for Multi-Task Learning: A Depolarization Solution in Multi-Gate Mixture-of-Experts

Conventional GAN-based models for talking head generation often suffer from limited quality and unstable training. Recent approaches based on diffusion models aim to address these limitations and improve fidelity. However, they still face challenges, including extensive sampling time and difficulties in maintaining temporal consistency due to the high stochasticity of diffusion models. To overcome these challenges, we propose a novel motion-disentangled diffusion model for high-quality talking head generation, dubbed MoDiTalker. We introduce two modules: the audio-to-motion (AToM), designed to generate synchronized lip motions from audio, and the motion-to-video (MToV), designed to produce high-quality talking head video following the generated motion.
AToM excels in capturing subtle lip movements by leveraging an audio attention mechanism. In addition, MToV enhances temporal consistency by leveraging an efficient tri-plane representation. Our experiments conducted on standard benchmarks demonstrate that our model achieves superior performance compared to existing models. We also provide comprehensive ablation studies and user study results.

MoDiTalker: Motion-Disentangled Diffusion Model for High-Fidelity Talking Head Generation

Acute lymphoblastic leukemia is a childhood cancer prevalent worldwide, which can prove fatal within weeks or months. However, current diagnosis models based on machine learning and deep learning methods fail to consider device noise (pixel-level perturbations) and rotation/translation (spatial-transformed perturbations), which can undermine the model's robustness. Adversarial training is a potential solution to this issue. This paper presents a hybrid perturbation adversarial training (HPAT) strategy that leverages two types of adversarial samples: pixel-level adversarial samples and spatial adversarial samples. This work generates these hybrid adversarial samples through Projected Gradient Descent (PGD) in couple with spatial transformation based on the Bayesian optimization (STBO) algorithm, respectively. This work introduced the Mixed Batch Normalization (MixBN) module to handle both adversarial samples and clean samples, alleviating the problem of clean accuracy degradation due to adversarial training. The proposed hybrid adversarial training strategy is tested on the public C\_NMC dataset and found that it outperformed existing acute lymphoblastic cell classification models.

Adversarial Learning under Hybrid Perturbations for Robust Acute Lymphoblastic Leukemia Classification

Federated Learning (FL) can be affected by data and device heterogeneities, caused by clients' different local data distributions and latencies in uploading model updates (i.e., staleness). Traditional schemes consider these heterogeneities as two separate and independent aspects, but this assumption is unrealistic in practical FL scenarios where these heterogeneities are intertwined. In these cases, traditional FL schemes are ineffective, and a better approach is to convert a stale model update into an unstale one. In this paper, we present a new FL framework that ensures the accuracy and computational efficiency of this conversion, hence effectively tackling the intertwined heterogeneities that may cause unlimited staleness in model updates. Our basic idea is to estimate the distributions of clients' local training data from their uploaded stale model updates, and use these estimations to compute unstale client model updates. In this way, our approach does not require any auxiliary dataset nor the clients' local models to be fully trained, and does not incur any additional computation or communication overhead at client devices. We compared our approach with the existing FL strategies on mainstream datasets and models, and demonstrated that our approach can improve the trained model accuracy by up to 25% and reduce the required amount of training epochs by up to 35%.

Tackling Intertwined Data and Device Heterogeneities in Federated Learning with Unlimited Staleness

In this paper, we introduce a syntactic framework for analyzing and handling inconsistencies in propositional bases. Our approach focuses on examining the relationships between variable occurrences within conflicts. We propose two dual concepts: Minimal Inconsistency Relation (MIR) and Maximal Consistency Relation (MCR). Each MIR is a minimal equivalence relation on variable occurrences that results in inconsistency, while each MCR is a maximal equivalence relation designed to prevent inconsistency. Notably, MIRs capture conflicts overlooked by minimal inconsistent subsets. Using MCRs, we develop a series of non-explosive inference relations. The main strategy involves restoring consistency by modifying the propositional base according to each MCR, followed by employing the classical inference relation to derive conclusions. Additionally, we propose an unusual semantics that assigns truth values to variable occurrences instead of the variables themselves. The associated inference relations are established through Boolean interpretations compatible with the occurrence-based models.

A Variable Occurrence-Centric Framework for Inconsistency Handling

Tabular data plays a vital role in various real-world scenarios and finds extensive applications. Although recent deep tabular models have shown remarkable success, they still struggle to handle data distribution shifts, leading to performance degradation when testing distributions change. To remedy this, a robust tabular model must adapt to generalize to unknown distributions during testing. In this paper, we investigate the problem of fully test-time adaptation (FTTA) for tabular data, where the model is adapted using only the testing data. We identify three key challenges: the existence of label and covariate distribution shifts, the lack of effective data augmentation, and the sensitivity of adaptation, which render existing FTTA methods ineffective for tabular data. To this end, we propose the Fully Test-time Adaptation for Tabular data, namely FTAT, which enables FTTA methods to robustly optimize the label distribution of predictions, adapt to shifted covariate distributions, and dynamically adapt the model for various tasks and models. We conduct comprehensive experiments on six benchmark datasets, which are evaluated using three metrics. The experimental results demonstrate that FTAT outperforms state-of-the-art methods by a margin.

Downloads

Next from AAAI 2025

Multilingual LLMs Inherently Reward In-Language Time-Sensitive Semantic Alignment for Low-Resource Languages

Similar lecture

Mixup-Transformer: Dynamic Data Augmentation for NLP Tasks