United States

Early-exiting dynamic neural networks (EDNN), as one type of dynamic neural networks, has been widely studied recently. A typical EDNN has multiple prediction heads at different layers of the network backbone. During inference, the model will exit at either the last prediction head or an intermediate prediction head where the prediction confidence is higher than a predefined threshold. To optimize the model, these prediction heads together with the network backbone are trained on every batch of training data. This brings a train-test mismatch problem that all the prediction heads are optimized on all types of data in training phase while the deeper heads will only see difficult inputs in testing phase. Treating training and testing inputs differently at the two phases will cause the mismatch between training and testing data distributions. To mitigate this problem, we formulate an EDNN as an additive model inspired by gradient boosting, and propose multiple training techniques to optimize the model effectively. We name our method BoostNet. Our experiments show it achieves the state-of-the-art performance on CIFAR100 and ImageNet datasets in both anytime and budgeted-batch prediction modes.

AAAI 2023

Boosted Dynamic Neural Networks

gradient boosting

adaptive inference

dynamic neural networks

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

Out-of-distribution (OOD) detection can be used in deep learning-based applications to reject outlier samples from being unreliably classified by deep neural networks. Learning to classify between OOD and in-distribution samples is difficult because data comprising the former is extremely diverse. It has been observed that an auxiliary OOD dataset is most effective in training a ``rejection'' network when its samples are semantically similar to in-distribution images. We first deduce that OOD images are perceived by a deep neural network to be semantically similar to in-distribution samples when they share a common background, as deep networks are observed to incorrectly classify such images with high confidence. We then propose a simple yet effective Key In-distribution feature Replacement BY inpainting (KIRBY) procedure that constructs a surrogate OOD dataset by replacing class-discriminative features of in-distribution samples with marginal background features. The procedure can be implemented using off-the-shelf vision algorithms, where each step within the algorithm is shown to make the surrogate data increasingly similar to in-distribution data. Design choices in each step are studied extensively, and an exhaustive comparison with state-of-the-art algorithms demonstrates KIRBY's competitiveness on various benchmarks.

Key Feature Replacement of In-Distribution Samples for Out-of-Distribution Detection

User Satisfaction Estimation is an important task and increasingly being applied in goal-oriented dialogue systems to estimate whether the user is satisfied with the service. It is observed that whether the user’s needs are met often triggers various sentiments, which can be pertinent to the successful estimation of user satisfaction, and vice versa. Thus, User Satisfaction Estimation (USE) and Sentiment Analysis (SA) should be treated as a joint, collaborative effort, considering the strong connections between the sentiment states of speakers and the user satisfaction. Existing joint learning frameworks mainly unify the two highly pertinent tasks over cascade or shared-bottom implementations, however they fail to distinguish task-specific and common features, which will produce sub-optimal utterance representations for downstream tasks. In this paper, we propose a novel Speaker Turn-Aware Multi-Task Adversarial Network (STMAN) for dialogue-level USE and utterance-level SA. Specifically, we first introduce a multi-task adversarial strategy which trains a task discriminator to make utterance representation more task-specific, and then utilize a speaker-turn aware multi-task interaction strategy to extract the common features which are complementary to each task. Extensive experiments conducted on two real-world service dialogue datasets show that our model outperforms several state-of-the-art methods.

A Speaker Turn-Aware Multi-Task Adversarial Network for Joint User Satisfaction Estimation and Sentiment Analysis

As deep neural networks can easily overfit noisy labels, robust training in the presence of noisy labels is becoming an important challenge in modern deep learning. While existing methods address this problem in various directions, they still produce unpredictable sub-optimal results since they rely on the posterior information estimated by the feature extractor corrupted by noisy labels. Lipschitz regularization successfully alleviates this problem by training a robust feature extractor, but it requires longer training time and expensive computations. Motivated by this, we propose a simple yet effective method, called ALASCA, which efficiently provides a robust feature extractor under label noise. ALASCA integrates two key ingredients: (1) adaptive label smoothing based on our theoretical analysis that label smoothing implicitly induces Lipschitz regularization, and (2) auxiliary classifiers that enable practical application of intermediate Lipschitz regularization with negligible computations. We conduct wide-ranging experiments for ALASCA and combine our proposed method with previous noise-robust methods on several synthetic and real-world datasets. Experimental results show that our framework consistently improves the robustness of feature extractors and the performance of existing baselines with efficiency.

A Gift from Label Smoothing: Robust Training with Adaptive Label Smoothing via Auxiliary Classifier under Label Noise

Overparameterized deep neural networks have redundant neurons that do not contribute to the network's accuracy. In this paper, we introduce a novel channel regeneration technique that reinvigorates these redundant channels by re-initializing its batch normalization scaling factor gamma. This re-initialization of BN gamma promotes regular weight updates during training. Furthermore, we show that channel regeneration encourages the channels to contribute equally to the learned representation and further boosts the generalization accuracy. We apply our technique at regular intervals of the training cycle to improve channel utilization. The solutions proposed in previous works either raise the total computational cost or increase the model complexity. Integrating the proposed channel regeneration technique into the training methodology of efficient architectures requires minimal effort and comes at no additional cost in size or memory. Extensive experiments on several image classification and semantic segmentation benchmarks demonstrate the effectiveness of applying the channel regeneration technique to compact architectures. 

Channel Regeneration: Improving Channel Utilization for Compact DNNs

The immune repertoire is a collection of immune recep-tors that has emerged as an important biomarker for both diagnostic and therapeutic of cancer patients. In terms of deep learning, analyzing immune repertoire is a challeng-ing multiple-instance learning problem in which the im-mune repertoire of an individual is a bag, and the immune receptor is an instance. Although several deep learning methods for immune repertoire analysis are introduced, they consider the immune repertoire as a set-like struc-ture that doesn’t take account of the nature of the im-mune response. When the immune response occurs, mu-tations are introduced to the immune receptor sequence sequentially to optimize the immune response against the pathogens that enter our body. As a result, immune receptors for the specific pathogen have the lineage of evolution; thus, immune repertoire is better represented as a graph-like structure. In this work, we present our novel method graph representation of immune repertoire (GRIP), which analyzes the immune repertoire as a hier-archical graph structure and utilize the collection of graph neural network followed by graph pooling and transformer to efficiently represents the immune reper-toire as an embedding vector. We show that GRIP predict the survival probability of cancer patients better than the set-based methods and graph-based structure is critical for performance. Also, GRIP provides interpretable re-sults, which prove that GRIP adequately use the progno-sis-related immune receptor and give further possibility to use the GRIP as the novel biomarker searching tool

GRIP: Graph representation of immune repertoire using graph neural network and transformer

Online bipartite-matching platforms are ubiquitous and find applications in important areas such as crowdsourcing and ridesharing. In the most general form, the platform consists of three entities: two sides to be matched and a platform operator that decides the matching. The design of algorithms for such platforms has traditionally focused on the operator’s (expected) profit. Since fairness has become an important consideration that was ignored in the existing algorithms a collection of online matching algorithms have been developed that give a fair treatment guarantee for one side of the market at the expense of a drop in the operator’s profit. In this paper, we generalize the existing work to offer fair treatment guarantees to both sides of the market simultaneously, at a calculated worst case drop to operator profit. We consider group and individual Rawlsian fairness criteria. Moreover, our algorithms have theoretical guarantees and have adjustable parameters that can be tuned as desired to balance the trade-off between the utilities of the three sides. We also derive hardness results that give clear upper bounds over the performance of any algorithm.

Rawlsian Fairness in Online Bipartite Matching: Two-sided, Group, and Individual

Compared with the feature-based distillation methods, logits distillation can liberalize the requirements of consistent feature dimension between teacher and student networks, while the performance is deemed inferior in face recognition. One major challenge is that the light-weight student network has difficulty fitting the target logits due to its low model capacity, which is attributed to the significant number of identities in face recognition. Therefore, we seek to probe the target logits to extract the primary knowledge related to face identity, and discard the others, to make the distillation more achievable for the student network. Specifically, there is a tail group with near-zero values in the prediction, containing minor knowledge for distillation. To provide a clear perspective of its impact, we first partition the logits into two groups, i.e., Primary Group and Secondary Group, according to the cumulative probability of the softened prediction. Then, we reorganize the Knowledge Distillation (KD) loss of grouped logits into three parts, i.e., Primary-KD, Secondary-KD, and Binary-KD. Primary-KD refers to distilling the primary knowledge from the teacher, Secondary-KD aims to refine minor knowledge but increases the difficulty of distillation, and Binary-KD ensures the consistency of knowledge distribution between teacher and student. We experimentally found that (1) Primary-KD and Binary-KD are indispensable for KD, and (2) Secondary-KD is the culprit restricting KD at the bottleneck. Therefore, we propose a Grouped Knowledge Distillation (GKD) that retains the Primary-KD and Binary-KD but omits Secondary-KD in the ultimate KD loss calculation. Extensive experimental results on popular face recognition benchmarks demonstrate the superiority of proposed GKD over state-of-the-art methods.

Grouped Knowledge Distillation for Deep Face Recognition

In this paper, we consider the parallel implementation of an already-trained deep model on multiple processing nodes (a.k.a. workers). Specifically, we investigate as to how a deep model should be divided into several parallel sub-models, each of which is executed efficiently by a worker. Since latency due to synchronization and data transfer among workers negatively impacts the performance of the parallel implementation, it is desirable to have minimum interdependency among parallel sub-models. To achieve this goal, we propose to rearrange the neurons in the neural network, partition them (without changing the general topology of the neural network), and modify the weights such that the interdependency among sub-models is minimized under the computations and communications constraints of the workers while minimizing its impact on the performance of the model. We propose RePurpose, a layer-wise model restructuring and pruning technique that guarantees the performance of the overall parallelized model. To efficiently apply RePurpose, we propose an approach based on $\ell_0$ optimization and the Munkres assignment algorithm. We show that, compared to the existing methods, RePurpose significantly improves the efficiency of the distributed inference via parallel implementation, both in terms of communication and computational complexity.

Efficient Distributed Inference of Deep Neural Networks via Restructuring and Pruning

A primary objective of news articles is to establish the factual record for an event, frequently achieved by conveying both the details of the specified event (i.e., the 5 Ws; Who, What, Where, When and Why regarding the event) and how people reacted to it (i.e., reported statements). However, existing work on news summarization almost exclusively focuses on the event details. In this work, we propose the novel task of summarizing the reactions of different speakers, as expressed by their reported statements, to a given event. To this end, we create a new multi-document summarization benchmark, SumREN, comprising 745 summaries of reported statements from various public figures obtained from 633 news articles discussing 132 events. We propose an automatic silver-training data generation approach for our task, which helps smaller models like BART achieve GPT-3 level performance on this task. Finally, we introduce a pipeline-based framework for summarizing reported speech, which we empirically show to generate summaries that are more abstractive and factual than baseline query-focused summarization approaches.  

SumREN: Summarizing Reported Speech about Events in News

Causal analysis for time series data, in particular estimating individualized treatment effect (ITE), is a key task in many real world applications, such as finance, retail, healthcare,  etc. Real world time series, i.e., large-scale irregular or sparse and intermittent time series, raise significant challenges to existing work attempting to estimate treatment effects. Specifically, the existence of hidden confounders can lead to  biased treatment estimates and complicate the causal inference process. In particular, anomaly hidden confounders which exceed the typical range can lead to high variance estimates. Moreover,  in continuous time settings with irregular samples, it is challenging to directly handle the dynamics of causality. In this paper, we leverage recent advances in Lipschitz regularization and neural controlled differential equations (CDE)  to develop an effective and scalable solution, namely LipCDE, to address the above challenges. LipCDE can directly model the dynamic causal relationships between historical data and outcomes with irregular samples by considering the boundary of hidden confounders given by Lipschitz constrained neural networks. Furthermore, we conduct extensive experiments on both synthetic and real world datasets to demonstrate the effectiveness and scalability of LipCDE. 

Boosted Dynamic Neural Networks

Downloads

Next from AAAI 2023

Key Feature Replacement of In-Distribution Samples for Out-of-Distribution Detection

Similar lecture

Towards Inference Efficient Deep Ensemble Learning