United States

Multi-teacher Knowledge Distillation (KD) transfers diverse knowledge from a teacher pool to a student network. The core problem of multi-teacher KD is how to balance distillation strengths among various teachers. Most existing methods often develop weighting strategies from an individual perspective of teacher performance or teacher-student gaps, lacking comprehensive information for guidance. This paper proposes Multi-Teacher Knowledge Distillation with Reinforcement Learning (MTKD-RL) to optimize multi-teacher weights. In this framework, we construct both teacher performance and teacher-student gaps as state information to an agent. The agent outputs the teacher weight and can be updated by the return reward from the student. MTKD-RL reinforces the interaction between the student and teacher using an agent in an RL-based decision mechanism, achieving better matching capability with more meaningful weights. Experimental results on visual recognition tasks, including image classification, object detection, and semantic segmentation tasks, demonstrate that MTKD-RL achieves state-of-the-art performance compared to the existing multi-teacher KD works. Our code is attached to the supplementary material.

AAAI 2025

Multi-Teacher Knowledge Distillation with Reinforcement Learning for Visual Recognition

categorization

object detection

The purpose of the AAAI conference is to promote research in artificial intelligence (AI) and scientific exchange among AI researchers, practitioners, scientists, and engineers in affiliated disciplines. 

AAAI 2021

technical paper

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.



We address the challenge of multi-agent cooperation, where agents achieve a common goal by cooperating with decentralized agents under complex partial observations. Existing cooperative agent systems often struggle with efficiently processing continuously accumulating information, managing globally suboptimal planning due to lack of consideration of collaborators, and addressing false planning caused by environmental changes introduced by other collaborators. To overcome these challenges, we propose the RElevance, Proximity, and Validation-Enhanced Cooperative Language Agent (REVECA), a novel cognitive architecture powered by GPT-4o-mini. REVECA enables efficient memory management, optimal planning, and cost-effective prevention of false planning by leveraging Relevance Estimation, Adaptive Planning, and Trajectory-based Validation. Extensive experimental results demonstrate REVECA's superiority over existing methods across various benchmarks, while a user study reveals its potential for achieving trustworthy human-AI cooperation.

REVECA: Adaptive Planning and Trajectory-Based Validation in Cooperative Language Agents Using Information Relevance and Relative Proximity

One of the major techniques to tackle temporal planning problems is heuristic search augmented with a symbolic representation of time in the states. Augmenting the problem with composite actions (macro-actions) is a simple and powerful approach to create "shortcuts" in the search space, at the cost of augmenting the branching factor of the problem and thus the expansion time of a heuristic search planner. Hence, it is of paramount importance to select the right macro-actions and minimize the number of such actions to optimize the planner performance.

In this paper, we first discuss a simple, yet powerful, model similar to macro-actions for the case of temporal planning, and we call these macro-events. Then, we present a novel ranking function to extract and select a suitable set of macro-events from a dataset of valid plans. In our ranking approach, we consider an estimation of the hypothetical search space for a blind search including a candidate set of macro-events under four different exploitation schemata. Finally, we experimentally demonstrate that the proposed approach yields a substantial performance improvement for a state-of-the-art temporal planner.

Automatic Selection of Macro-Events for Heuristic-Search Temporal Planning

The Emotional Voice Conversion (EVC) aims to convert the discrete emotional state from the source emotion to the target for a given speech utterance while preserving linguistic content. In this paper, we propose regularizing emotion intensity in the diffusion-based EVC framework to generate precise speech of the target emotion. Traditional approaches control the intensity of an emotional state in the utterance via emotion class probabilities or intensity labels that often lead to inept style manipulations and degradations in quality. On the contrary, we aim to regulate emotion intensity using self-supervised learning-based feature representations and unsupervised directional latent vector modeling (DVM) in the emotional embedding space within a diffusion-based framework.
These emotion embeddings can be modified based on the given target emotion intensity and the corresponding direction vector. Furthermore, the updated embeddings can be fused in the reverse diffusion process to generate the speech with the desired emotion and intensity. In summary, this paper aims to achieve high-quality emotional intensity regularization in the diffusion-based EVC framework, which is the first of its kind work. The effectiveness of the proposed method has been shown across state-of-the-art (SOTA) baselines in terms of subjective and objective evaluations for the English and Hindi languages\footnote{Demo samples are available at

EmoReg: Directional Latent Vector Modeling for Emotional Intensity Regularization in Diffusion-based Voice Conversion

In the $k$-committee election problem, we wish to aggregate the preferences of $n$ agents
over a set of alternatives and select a committee of $k$ alternatives that minimizes the
cost incurred by the agents. While we typically assume that agent preferences are captured
by a cardinal utility function, in many contexts we only have access to ordinal
information, namely the agents' rankings over the outcomes. As ordinal preference rankings
are not as expressive as cardinal utilities, a loss of efficiency is inevitable, and is
quantified by the notion of \emph{distortion}.  
		
		
We study the problem of electing a $k$-committee that minimizes the sum of the
$\ell$-largest costs incurred by the agents, when agents and candidates are embedded in a
metric space. This problem is called the $\ell$-centrum problem and captures both the
utilitarian and egalitarian objectives. When $k \geq 2$, it is not possible to compute a
bounded-distortion committee using purely ordinal information. We develop the first
algorithms (that we call mechanisms) for the $\ell$-centrum problem (when $k \geq 2$),
which achieve $O(1)$-distortion while eliciting only a very limited amount of cardinal
information via value queries. We obtain two types of query-complexity guarantees: $O(\log
k \log n)$ queries \emph{per agent},  and $O(k^2 \log^2 n)$ queries \emph{in total} (while
achieving $O(1)$-distortion in both cases). En route, we give a simple adaptive-sampling
algorithm for the $\ell$-centrum $k$-clustering problem.

Constant-Factor Distortion Mechanisms for k-Committee Election

Correct labels are indispensable for training effective machine learning models. However, creating high-quality labels is expensive, and even professionally labeled data contains errors and ambiguities. Filtering and denoising can be applied to curate labeled data prior to training, at the cost of additional processing and loss of information. An alternative is on-the-fly sample reweighting during the training process to decrease the negative impact of incorrect or ambiguous labels, but this typically requires clean seed data. In this work we propose unsupervised on-the-fly meta loss rescaling to reweight training samples. Crucially, we rely only on features provided by the model being trained, to learn a rescaling function in real time without knowledge of the true clean data distribution. We achieve this via a novel meta learning setup that samples validation data for the meta update directly from the noisy training corpus by employing the rescaling function being trained. Our proposed method consistently improves performance across various NLP tasks with minimal computational overhead. Further, we are among the first to attempt on-the-fly training data reweighting on the challenging task of dialogue modelling, where noisy and ambiguous labels are common. Our strategy is robust in the face of noisy and clean data, handles class imbalance, and prevents overfitting to noisy labels. Our self-taught loss rescaling improves as the model trains, showing the ability to keep learning from the model's own signals. As training progresses, the impact of correctly labeled data is scaled up, while the impact of wrongly labeled data is suppressed.

Learning from Noisy Labels via Self-Taught On-the-Fly Meta Loss Rescaling

Decoding visual information from human brain activity has seen remarkable advancements in recent research. However, the diversity in cortical parcellation and fMRI patterns across individuals has prompted the development of deep learning models tailored to each subject. The personalization limits the broader applicability of brain visual decoding in real-world scenarios. To address this issue, we introduce Wills Aligner, a novel approach designed to achieve multi-subject collaborative brain visual decoding. Wills Aligner begins by aligning the fMRI data from different subjects at the anatomical level. It then employs delicate mixture-of-brain-expert adapters and a meta-learning strategy to account for individual fMRI pattern differences. Additionally, Wills Aligner leverages the semantic relation of visual stimuli to guide the learning of inter-subject commonality, enabling visual decoding for each subject to draw insights from other subjects' data. We rigorously evaluate our Wills Aligner across various visual decoding tasks, including classification, cross-modal retrieval, and image reconstruction. The experimental results demonstrate that Wills Aligner achieves promising performance.

Wills Aligner: Multi-Subject Collaborative Brain Visual Decoding

By generating new yet effective data, data augmentation has become a promising method to mitigate the data sparsity problem in sequential recommendation. Existing works focus on augmenting the original data but rarely explore the issue of imbalanced relevance and diversity for augmented data, leading to semantic drift problems or limited performance improvements. In this paper, we propose a novel Balanced data Augmentation Plugin for Sequential Recommendation (BASRec) to generate data that balance relevance and diversity. BASRec consists of two modules: Single-sequence Augmentation and Cross-sequence Augmentation. The former leverages the randomness of the heuristic operators to generate diverse sequences for a single user, after which the diverse and the original sequences are fused at the representation level to obtain relevance. Further, we devise a reweighting strategy to enable the model to learn the preferences based on the two properties adaptively. The Cross-sequence Augmentation performs nonlinear mixing between different sequence representations from two directions. It produces virtual sequence representations that are diverse enough but retain the vital semantics of the original sequences. These two modules enhance the model to discover fine-grained preferences knowledge from single-user and cross-user perspectives. Extensive experiments verify the effectiveness of BASRec. The average improvement is up to 72.0% on GRU4Rec, 33.8% on SASRec, and 68.5% on FMLP-Rec. We demonstrate that BASRec generates data with a better balance between relevance and diversity than existing methods. We provide an anonymous implementation in the supplementary material.

Augmenting Sequential Recommendation with Balanced Relevance and Diversity

Multi-view multi-label learning has become a research focus for describing objects with rich expressions and annotations. However, real-world data often contains numerous unlabeled instances, due to the high cost and technical limitations of manual labeling. This crucial problem involves three main challenges: i) How to  extract advanced semantics from available views? ii) How to build a refined classification framework with limited labeled space?
iii) How to provide more high-quality supervisory information? To address these problems, we propose a  Semi-Supervised Multi-View Multi-Label Learning Method with View-Specific Transformer and Enhanced Pseudo-Label named SMVTEP. Specifically, Generative Adversarial Networks are employed to extract informative shared and specific representations and their consistency and distinctiveness are ensured through the adversarial mechanism and information theory based contrastive learning. Then we build specific classifiers for each extracted feature and apply instance-level manifold  constraints to reduce bias across classifiers. Moreover, we design a transformer-style fusion approach that simultaneously captures the imbalance of expressive power among views, mapping effects on specific labels, and label dependencies by incorporating confidence scores and category semantics into the self-attention mechanism. Furthermore, after using Mixup for data augmentation, category-enhanced pseudo-labels are leveraged to improve  the reliability of additional annotations by aligning the label  distribution of unlabeled samples with the true distribution. Finally, extensive experimental results validate the effectiveness of SMVTEP against state-of-the-art methods.

Semi-Supervised Multi-View Multi-Label Learning with View-Specific Transformer and Enhanced Pseudo-Label

We present an open-source tool for manipulating Boolean circuits. It implements efficient algorithms, both existing and novel, for a rich variety of frequently used circuit tasks such as satisfiability, synthesis, and minimization. We tested the tool on a wide range of practically relevant circuits (computing, in particular, symmetric and arithmetic functions) that have been optimized intensively by the community for the last three years. The tool helped us to win the IWLS 2024 Programming Contest. In 2023, it was Google DeepMind who took the first place in the competition. We were able to reduce the size of the best circuits from 2023 by 12% on average, whereas for some individual circuits, our size reduction was as large as 83%.

Cirbo: A New Tool for Boolean Circuit Analysis and Synthesis

The rapid evolution of multimedia technology has revolutionized human perception, paving the way for multi-view learning. However, traditional multi-view learning approaches are tailored for scenarios with fixed data views, falling short of emulating the intricate cognitive procedures of the human brain processing signals sequentially. Our cerebral architecture seamlessly integrates sequential data through intricate feed-forward and feedback mechanisms. In stark contrast, traditional methods struggle to generalize effectively when confronted with data spanning diverse domains, highlighting the need for innovative strategies that can mimic the brain's adaptability and dynamic integration capabilities. In this paper, we propose a bio-neurologically inspired multi-view incremental framework named MVIL aimed at emulating the brain's fine-grained fusion of sequentially arriving views. MVIL lies two fundamental modules: structured Hebbian plasticity and synaptic partition learning. The structured Hebbian plasticity reshapes the structure of weights to express the high correlation between view representations, facilitating fine-grained fusion of view representations. Moreover, synaptic partition learning is efficient in alleviating drastic changes in weights and also retaining old knowledge by inhibiting partial synapses. These modules bionically play a central role in reinforcing crucial associations between newly acquired information and existing knowledge repositories, thereby enhancing the network's capacity for generalization. Experimental results on six benchmark datasets shows MVIL's effectiveness over state-of-the-art methods.

Downloads

Next from AAAI 2025

REVECA: Adaptive Planning and Trajectory-Based Validation in Cooperative Language Agents Using Information Relevance and Relative Proximity

Similar lecture

Reinforced Multi-Teacher Selection for Knowledge Distillation