United States

Large-scale cross-modal pre-training paradigms have recently shown ubiquitous success on a wide range of downstream tasks, e.g., zero-shot classification, retrieval and image captioning. However, their successes highly rely on the scale and quality of web-crawled data that naturally contain much incomplete and noisy information (e.g., wrong or irrelevant contents). Existing works either design manual rules to clean data or generate pseudo-targets as auxiliary signals for reducing noise impact, which do not explicitly tackle both the incorrect and incomplete challenges at the same time. In this paper, to automatically mitigate the impact of noise by solely mining over existing data, we propose a principled Noise-robust Language-Image Pre-training framework (NLIP) to stabilize pre-training via two schemes: noise-harmonization and noise-completion. First, in noise-harmonization scheme, NLIP estimates the noise probability of each pair according to the memorization effect of cross-modal transformers, then adopts noise-adaptive regularization to harmonize the cross-modal alignments with varying degrees. Second, in noise-completion scheme, to enrich the missing object information of text, NLIP injects a concept-conditioned cross-modal decoder to obtain semantic-consistent synthetic captions to complete noisy ones, which uses the retrieved visual concepts (i.e., objects’ names) for the corresponding image to guide captioning generation. By collaboratively optimizing noise-harmonization and noise-completion schemes, our NLIP can alleviate the common noise effects during image-text pre-training in a more efficient way. Extensive experiments show the significant performance improvements of our NLIP using only 26M data over existing pre-trained models (e.g., CLIP, FILIP and BLIP) on 12 zero-shot classification datasets (e.g., +8.6% over CLIP on average accuracy), MSCOCO image captioning (e.g., +1.9 over BLIP trained with 129M data on CIDEr) and zero-shot image-text retrieval tasks.

AAAI 2023

NLIP: Noise-robust Language-Image Pre-training

representation learning for vision

multimodal learning

language and vision

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-23 is the Thirty-Seventh AAAI Conference on Artificial Intelligence. The theme of this conference is to create collaborative bridges within and beyond AI. Like previous AAAI conferences, AAAI-23 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and two new activities: a Bridge Program and a Lab Program. Many of these activities are tailored to the theme of bridges and all are selected according to the highest standards, with additional programs for students and young researchers. 
AAAI is providing you with a conference planner, which you can use to help organize your itinerary of activities. This includes talks to attend in person, talks to attend remotely, breaks with colleagues and your site seeing activities. To access this conference planner, please go to [https://aaai-2023.takemobi.io](https://aaai-2023.takemobi.io).

In order to access this site, you need to register. If you haven't already, please register [here](https://aaai.org/Conferences/AAAI-23/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.

poster

Long-term time series forecasting (LTSF) provides substantial benefits for numerous real-world applications, whereas places essential demands on the model capacity to capture long-range dependencies. Recent Transformer-based models have significantly improved LTSF performance. It is worth noting that Transformer with the self-attention mechanism was originally proposed to model language sequences whose tokens (i.e., words) are discrete and highly semantic. However, unlike language sequences, most time series are sequential and continuous numeric points. Time steps with temporal redundancy are weakly semantic, and only leveraging time-domain tokens is hard to depict the overall properties of time series (e.g., the overall trend and periodic variations). To address these problems, we propose a novel Transformer-based forecasting model named InParformer with an Interactive Parallel Attention (InPar Attention) mechanism. The InPar Attention is proposed to learn long-range dependencies comprehensively in both frequency and time domains. To improve its learning capacity and efficiency, we further design several mechanisms, including query selection, key-value pair compression, and recombination. Moreover, InParformer is constructed with evolutionary seasonal-trend decomposition modules to enhance intricate temporal pattern extraction. Extensive experiments on six real-world benchmarks show that InParformer outperforms the state-of-the-art forecasting Transformers.

InParformer: Evolutionary Decomposition Transformers with Interactive Parallel Attention for Long-Term Time Series Forecasting

The scribble-supervised semantic segmentation is an important yet challenging task in the field of computer vision.
To deal with the pixel-wise sparse annotation problem, we propose a Progressive Bayesian Inference (PBI) framework to boost the performance of the scribble-supervised semantic segmentation, which can effectively infer the semantic distribution of these unlabeled pixels to guide the optimization of segmentation network. 
The PBI dynamically improves the model learning from two aspects: Bayesian inference module (i.e., semantic distribution learning) and the pixel-wise segmenter (i.e., model updating). 
Specifically, we effectively infer the semantic probability distribution of these unlabeled pixels with our designed Bayesian inference module, where its guidance is estimated through the Bayesian expectation maximization under the situation of partially observed data. 
The segmenter can be progressively improved under the joint guidance of the original scribble information and the learned semantic distribution. 
The segmenter optimization and semantic distribution promotion are encapsulated into a unified architecture where they could improve each other with mutual evolution in a progressive fashion. 
Comprehensive evaluations on several benchmark datasets demonstrate the effectiveness and superiority of our proposed PBI when compared with other state-of-the-art methods applied to the scribble-supervised semantic segmentation task.

Progressive Bayesian Inference for Scribble-supervised Semantic Segmentation

Federated learning (FL) is known to be susceptible to model poisoning attacks in which malicious clients hamper the accuracy of the global model by sending manipulated model updates to the central server during the FL training process.  Existing defenses mainly focus on Byzantine-robust FL aggregations, and largely ignore the impact of the underlying deep neural network (DNN) that is used to FL training.  Inspired by recent findings on critical learning periods (CLP) in DNNs, where small gradient errors have irrecoverable impact on the final model accuracy, we propose a new defense, called \textit{a CLP-aware defense against poisoning of FL} (DeFL).  The key idea of DeFL is to measure fine-grained differences between DNN model updates via an easy-to-compute federated gradient norm vector (FGNV) metric.  Using FGNV, DeFL simultaneously detects malicious clients and identifies CLP, which in turn is leveraged to guide the adaptive removal of detected malicious clients from aggregation.  As a result, DeFL not only mitigates model poisoning attacks on the global model but also is robust to detection errors.  Our extensive experiments on three benchmark datasets demonstrate that DeFL produces significant performance gain over conventional defenses against state-of-the-art model poisoning attacks.

DeFL: Defending Against Model Poisoning Attacks in Federated Learning via Critical Learning Periods Awareness

Modern recommender systems are increasingly expected to provide informative explanations that enable users to understand the reason for particular recommendations. However, previous methods struggle to interpret the input 
IDs of user--item pairs in real-world datasets, failing to extract adequate characteristics for controllable generation. To address this issue, we propose disentangled conditional variational autoencoders (CVAEs) for explainable recommendation, which leverage disentangled latent preference factors and guide the explanation generation with the refined condition of CVAEs via a self-regularization contrastive learning loss. Extensive experiments demonstrate that our method generates high-quality explanations and achieves new state-of-the-art results in diverse domains.

Disentangled CVAEs with Contrastive Learning for Explainable Recommendation

Quantum computers are regarded as a technology that will break Moore’s law. Recently, research on quantum deep learning, which processes data with logarithm complexity through a quantum neural network (QNN), is attracting attention. However, the full potential of QNNs has not been discovered yet. For this, we focus on the meta-characteristic of QNN that the quantum state is a knowledge base, and the measurement basis is a kernel to output. Moreover, one of the quantum measurement properties is easy initialization and transformation while requiring low memory and computation. Motivated by these features, this paper aims to investigate the full potential of QNNs in multi-agent reinforcement learning (MARL) and continual learning, named quantum multi-agent meta reinforcement learning (QMAMRL). To realize QMAMRL, we propose meta-QNN angle training, local QNN pole training, and pole initialization. In meta-QNN angle training, artificial noises are added on a measurement basis (i.e., pole) to improve knowledge. Then, local QNN pole training realizes the cooperation of multiple agents. Finally, pole initialization helps QNNs to achieve an adaptation to varying environments. Via extensive experiments and convergence analysis, we corroborate that our proposed QMAMRL framework has new properties that the previous algorithms have not.

Quantum Multi-Agent Meta Reinforcement Learning

Endowing dialogue agents with personas is the key to delivering more human-like conversations. However, existing persona-grounded dialogue systems still lack informative details of human conversations and tend to reply with inconsistent and generic responses.  
One of the main underlying causes is that pre-defined persona sentences are generally short and merely superficial descriptions of personal attributes, making appropriate persona selection and understanding non-trivial.
Another challenge is that it is crucial to consider the context and the conversation flow to dynamically determine when to invoke which kinds of persona signals.
To address these problems, we propose a disentangled-attention based pre-training architecture, which incorporates persona-aware prompt learning to bridge the connection between the selected persona and response generation. Our model first exploits the conversation flow to select context-relevant personas, and subsequently enriches the superficial persona descriptions with extra personality traits through persona-aware prompting. Finally, the decoder leverages a disentangled-attention mechanism to flexibly control the reliance on personas and dialogue contexts, and incorporates A*-like keyword-based heuristic estimates for controllable generation. Extensive experiments show that our approach can outperform strong baselines and deliver more consistent and engaging responses on the PERSONA-CHAT dataset.

A Disentangled-Attention Based Framework with Persona-Aware Prompt Learning for Dialogue Generation

Zero-shot learning (ZSL) is an extreme case of transfer learning that aims to recognize samples (e.g., images) of unseen classes relying on a train-set covering only seen classes and a set of auxiliary knowledge (e.g., semantic descriptors). Existing methods usually resort to constructing a visual-to-semantics mapping based on features extracted from each whole sample. However, since the visual and semantic spaces are inherently independent and may exist in different manifolds, these methods may easily suffer from the domain bias problem due to the knowledge transfer from seen to unseen classes. Unlike existing works, this paper investigates the fine-grained ZSL from a novel perspective of sample-level graph. Specifically, we decompose an input into several fine-grained elements and construct a graph structure per sample to measure and utilize element-granularity relations within each sample. Taking advantage of recently developed graph neural networks (GNNs), we formulate the ZSL problem to a graph-to-semantics mapping task, which can better exploit element-semantics correlation and local sub-structural information in samples. Experimental results on the widely used benchmark datasets demonstrate that the proposed method can mitigate the domain bias problem and achieve competitive performance against other representative methods.

Graph Knows Unknowns: Reformulate Zero-shot Learning as Sample-level Graph Recognition

Continual graph learning routinely finds its role in a variety of real-world applications where the graph data with different tasks come sequentially. Despite the success of prior works, it still faces great challenges. On the one hand, existing methods work with the zero-curvature Euclidean space, and largely ignore the fact that curvature varies over the com- ing graph sequence. On the other hand, continual learners in the literature rely on abundant labels, but labeling graph in practice is particularly hard especially for the continuously emerging graphs on-the-fly. To address the aforementioned challenges, we propose to explore a challenging yet practical problem, the self-supervised continual graph learning in adaptive Riemannian spaces. In this paper, we propose a novel self-supervised Riemannian Graph Continual Learner (RieGrace). In RieGrace, we first design an Adaptive Riemannian GCN (AdaRGCN), a unified GCN coupled with a neural curvature adapter, so that Riemannian space is shaped by the learnt curvature adaptive to each graph. Then, we present a Label-free Lorentz Distillation approach, in which we create teacher-student AdaRGCN for the graph sequence. The student successively performs intra-distillation from itself and inter-distillation from the teacher so as to consolidate knowledge without catastrophic forgetting. In particular, we propose a theoretically grounded Generalized Lorentz Projection for the contrastive distillation in Riemannian space. Extensive experiments on the benchmark datasets show the superiority of RieGrace, and additionally, we investigate on how curvature changes over the graph sequence. 

Self-Supervised Continual Graph Learning in Adaptive Riemannian Spaces

With the development of the online education system, personalized education recommendation has played an essential role. In this paper, we focus on developing path recommendation systems that aim to generating and recommending an entire learning path to the given user in each session. Noticing that existing approaches fail to consider the correlations of concepts in the path, we propose a novel framework named Set-to-Sequence Ranking-based Concept-aware Learning Path Recommendation (SRC), which formulates the recommendation task under a set-to-sequence paradigm. Specifically, we first design a concept-aware encoder module which can capture the correlations among the input learning concepts. The outputs are then fed into a decoder module that sequentially generates a path through an attention mechanism that handles correlations between the learning and target concepts. Our recommendation policy is optimized by policy gradient. In addition, we also introduce an auxiliary module based on knowledge tracing to enhance the model’s stability by evaluating students’ learning effects on learning concepts. We conduct extensive experiments on two real-world public datasets and one industrial dataset, and the experimental results demonstrate the superiority and effectiveness of SRC. Code will be available at https://gitee.com/mindspore/models/tree/master/research/recommend/SRC.

Set-to-Sequence Ranking-based Concept-aware Learning Path Recommendation

Safe reinforcement learning considers practical scenarios that maximize the return while satisfying safety constraints. Current algorithms, which suffer from training oscillations or approximation errors, still struggle to update the policy efficiently with precise constraint satisfaction. In this article, we propose Augmented Proximal Policy Optimization (APPO), which augments the Lagrangian function of the primal constrained problem via attaching a quadratic deviation term. The constructed multiplier-penalty function dampens cost oscillation for stable convergence while being equivalent to the primal constrained problem to precisely control safety costs. APPO alternately updates the policy and the Lagrangian multiplier via solving the constructed augmented primal-dual problem, which can be easily implemented by any first-order optimizer. We apply our APPO methods in diverse safety-constrained tasks, setting a new state of the art compared with a comprehensive list of safe RL baselines. Extensive experiments verify the merits of our method in easy implementation, stable convergence, and precise cost control.

NLIP: Noise-robust Language-Image Pre-training

Downloads

Next from AAAI 2023

InParformer: Evolutionary Decomposition Transformers with Interactive Parallel Attention for Long-Term Time Series Forecasting

Similar lecture

Learning Semantic Alignment with Global Modality Reconstruction for Video-Language Pre-training towards Retrieval

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES