United States

Continual Learning (CL) considers the problem of training an agent sequentially on a set of tasks while seeking to retain performance on all previous tasks. A key challenge in CL is catastrophic forgetting, which arises when performance on a previously mastered task is reduced when learning a new task. While a variety of methods exist to combat forgetting, in some cases tasks are fundamentally incompatible with each other and thus cannot be learnt by a single policy. This can occur, in reinforcement learning (RL) when an agent may be rewarded for achieving different goals from the same observation. In this paper we formalize this &quot;interference&quot; as distinct from the problem of forgetting. We show that existing CL methods based on single neural network predictors with shared replay buffers fail in the presence of interference. Instead, we propose a simple method, OWL, to address this challenge. OWL learns a factorized policy, using shared feature extraction layers, but separate heads, each specializing on a new task. The separate heads in OWL are used to prevent interference. At test time, we formulate policy selection as a multi-armed bandit problem, and show it is possible to select the best policy for an unknown task using feedback from the environment. The use of bandit algorithms allows the OWL agent to constructively re-use different continually learnt policies at different times during an episode. We show in multiple RL environments that existing replay based CL methods fail, while OWL is able to achieve close to optimal performance when training sequentially.

AAAI 2022

Same State, Different Task: Continual Reinforcement Learning without Interference

Continual Learning (CL) considers the problem of training an agent sequentially on a set of tasks while seeking to retain performance on all previous tasks. A key challenge in CL is catastrophic forgetting, which arises when performance on a previously mastered task is reduced when learning a new task. While a variety of methods exist to combat forgetting, in some cases tasks are fundamentally incompatible with each other and thus cannot be learnt by a single policy. This can occur, in reinforcement learning (RL) when an agent may be rewarded for achieving different goals from the same observation. In this paper we formalize this "interference" as distinct from the problem of forgetting. We show that existing CL methods based on single neural network predictors with shared replay buffers fail in the presence of interference. Instead, we propose a simple method, OWL, to address this challenge. OWL learns a factorized policy, using shared feature extraction layers, but separate heads, each specializing on a new task. The separate heads in OWL are used to prevent interference. At test time, we formulate policy selection as a multi-armed bandit problem, and show it is possible to select the best policy for an unknown task using feedback from the environment. The use of bandit algorithms allows the OWL agent to constructively re-use different continually learnt policies at different times during an episode. We show in multiple RL environments that existing replay based CL methods fail, while OWL is able to achieve close to optimal performance when training sequentially.

technical paper

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. 

With the rapid progress of generation technology, it has become necessary to attribute the origin of fake images. Existing works on fake image attribution perform multi-class classification on several Generative Adversarial Network (GAN) models and obtain high accuracies. While encouraging, these works are restricted to model-level attribution, only capable of handling images generated by seen models with a specific seed, loss and dataset, which is limited in real-world scenarios when fake images may be generated by privately trained models. This motivates us to ask whether it is possible to attribute fake images to the source models' architectures even if they are finetuned or retrained under different configurations. In this work, we present the first study on Deepfake Network Architecture Attribution to attribute fake images on architecture-level. Based on an observation that GAN architecture is likely to leave globally consistent fingerprints while traces left by model weights vary in different regions, we provide a simple yet effective solution named by DNA-Det for this problem. Extensive experiments on multiple cross-test setups and a large-scale dataset demonstrate the effectiveness of DNA-Det.

Deepfake Network Architecture Attribution

Assessing the quality of natural language generation (NLG) systems through human annotation is very expensive. Additionally, human annotation campaigns are time-consuming and include non-reusable human labour. In practice, researchers rely on automatic metrics as a proxy of quality. In the last decade, many string-based metrics (e.g., BLEU or ROUGE) have been introduced. However, such metrics usually rely on exact matches and thus, do not robustly handle synonyms. In this paper, we introduce InfoLM a family of untrained metrics that can be viewed as a string-based metric that addresses the aforementioned flaws thanks to a pre-trained masked language model. This family of metrics also makes use of information measures allowing the possibility to adapt InfoLM to different evaluation criteria. Using direct assessment, we demonstrate that InfoLM achieves statistically significant improvement and two figure correlation gains in many configurations compared to existing metrics on both summarization and data2text generation tasks.

InfoLM: A New Metric to Evaluate Summarization & Data2Text Generation

In this paper, we give a new definition for sample complexity, and further develop a theoretical analysis to bridge the gap between sample complexity and model capacity. In contrast to previous works which study on some toy samples, we conduct our analysis on more general data space, and build a qualitative relationship from sample complexity to model capacity required to achieve comparable performance. Besides, we introduce a simple indicator to evaluate the sample complexity based on continuous mapping. Moreover, we further analysis the relationship between sample complexity and data distribution, which paves the way to understand the present representation learning. Extensive experiments on several datasets well demonstrate the effectiveness of our evaluation method.

Towards Bridging Sample Complexity and Model Capacity

Model-based diagnosis (MBD) with multiple observations is complicated and difficult to manage over. In this paper, we proposed two new diagnosis models, namely, the Compacted Model with Multiple Observations (CMMO) and the
 Dominated-based Compacted Model with Multiple Observations (D-CMMO), to solve the problem in which a considerable amount of time is needed when multiple observations are given and more than one fault is injected. Three ideas are presented in this paper. First, we propose to encode MBD with each observation as a subsystem and share as many system variables as possible to compress the size of encoded clauses. Second, we utilize the notion of gate dominance in the CMMO approach to compute Top-Level Diagnosis with Compacted Model (CM-TLD) to reduce the solution space. Finally, we explore the performance of our model using three fault models. Experimental results on the ISCAS-85 benchmarks show that CMMO and D-CMMO perform better than
 the state-of-the-art algorithms.

Two Compacted Models for Efficient Model-Based Diagnosis

Multimodal summarization with multimodal output (MSMO) generates a summary with both textual and visual content. Multimodal news report contains heterogeneous contents, which makes MSMO nontrivial. Moreover, it is observed that different modalities of data in the news report correlate hierarchically. Traditional MSMO methods indistinguishably handle different modalities of data by learning a representation for the whole data, which is not directly adaptable to the heterogeneous contents and hierarchical correlation. In this paper, we propose a hierarchical cross-modality semantic correlation learning model (HCSCL) to learn the intra- and inter-modal correlation existing in the multimodal data. HCSCL adopts a graph network to encode the intra-modal correlation. Then, a hierarchical fusion framework is proposed to learn the hierarchical correlation between text and images. Furthermore, we construct a new dataset with relevant image annotation and image object label information to provide the supervision information for the learning procedure. Extensive experiments on the dataset show that HCSCL significantly outperforms the baseline methods in automatic summarization metrics and fine-grained diversity tests.

Hierarchical Cross-Modality Semantic Correlation Learning Model for Multimodal Summarization

Graph Convolutional Neural Networks (GCNs) have been generally accepted to be an effective tool for node representations learning. An interesting way to understand GCNs is to think of them as a message passing mechanism where each node updates its representation by accepting information from its neighbours (also known as positive samples). However, beyond these neighbouring nodes, graphs have a large, dark, all-but forgotten world in which we find the non-neighbouring nodes (negative samples). In this paper, we show that this great dark world holds a substantial amount of information that might be useful for representation learning. Most specifically, it can provide negative information about the node representations. Our overall idea is to select appropriate negative samples for each node and incorporate the negative information contained in these samples into the representation updates. Moreover, we show that the process of selecting the negative samples is not trivial. Our theme therefore begins by describing the criteria for a good negative sample, followed by a determinantal point process algorithm for efficiently obtaining such samples. A GCN, boosted by diverse negative samples, then jointly considers the positive and negative information when passing messages. Experimental evaluations show that this idea not only improves the overall performance of standard representation learning but also significantly alleviates over-smoothing problems.

Learning from the Dark: Boosting Graph Convolutional Neural Networks with Diverse Negative Samples

Elkind et al. (AAAI'21) introduced a model for deliberative coalition formation, where a community wishes to identify a strongly supported proposal from a space of alternatives, in order to change the status quo. In their model, agents and proposals are points in a metric space, agents' preferences are determined by distances, and agents deliberate by dynamically forming coalitions around proposals that they prefer over the status quo. The deliberation process operates via k-compromise transitions, where agents from k (current) coalitions come together to form a larger coalition in order to support a (perhaps new) proposal, possibly leaving behind some of the dissenting agents from their old coalitions. A deliberation succeeds if it terminates by identifying a proposal with the largest possible support. For deliberation in d dimensions, Elkind et al. consider two variants of their model: in the Euclidean model, proposals and agent locations are points in R^d and the distance is measured according to ||...||_2; and in the hypercube model, proposals and agent locations are vertices of the d-dimensional hypercube and the metric is the Hamming distance. They show that in the Euclidean model 2-compromises are guaranteed to succeed, but in the hypercube model for deliberation to succeed it may be necessary to use k-compromises with k >= d. 
We complement their analysis by 
 (1) proving that in both models it is hard to find a proposal with a high degree of support, and even a 2-compromise transition may be hard to compute;
 (2) showing that a sequence of 2-compromise transitions may be exponentially long;
 (3) strengthening the lower bound on the size of the compromise for the d-hypercube model from d to 2^â„¦(d).

Complexity of Deliberative Coalition Formation

State-of-the-art deep NLP models have achieved impressive improvements on many tasks. However, they are found to be vulnerable to some perturbations. Before they are widely adopted, the fundamental issues of robustness need to be addressed. In this paper, we design a robustness enhancement method to defend against word substitution perturbation, whose basic idea is to fight perturbation with perturbation. We find that: although many well-trained deep models are not robust in the setting of the presence of adversarial samples, they satisfy weak robustness. That means they can handle most non-crafted perturbations well. Taking advantage of the weak robustness property of deep models, we utilize non-crafted perturbations to resist the adversarial perturbations crafted by attackers. Our method contains two main stages. The first stage is using randomized perturbation to conform the input to the data distribution. The second stage is using randomized perturbation to eliminate the instability of prediction results and enhance the robustness guarantee. Experimental results show that our method can significantly improve the ability of deep models to resist the state-of-the-art adversarial attacks while maintaining the prediction performance on the original clean data.

Word Level Robustness Enhancement: Fight Perturbation with Perturbation

The use of priors to avoid manual labeling for training machine learning methods has received much attention in the last few years. One of the critical subthemes in this regard is Learning from Label Proportions (LLP), where only the information about class proportions is available for training the models. While various LLP training settings verse in the literature, most approaches focus on bag-level label proportions errors, often leading to suboptimal solutions. This paper proposes a new model that jointly uses prototypical contrastive learning and bag-level cluster proportions to implement efficient LLP classification. Our proposal explicitly relaxes the equipartition constraint commonly used in prototypical contrastive learning methods and incorporates the exact cluster proportions into the optimal transport algorithm used for cluster assignments. At inference time, we compute the clusters' assignment, delivering instance-level classification. We experimented with our method on two widely used image classification benchmarks and report a new state-of-art LLP performance, achieving results close to fully supervised methods.

Learning from Label Proportions with Prototypical Contrastive Clustering

Modern neural networks can assign high confidence to inputs drawn from outside the training distribution, posing threats to models in real-world deployments. While much research attention has been placed on designing new out-of-distribution (OOD) detection methods, the precise definition of OOD is often left in vagueness and falls short of the desired notion of OOD in reality. In this paper, we present a new formalization and model the data shifts by taking into account both the invariant and environmental (spurious) features. Under such formalization, we systematically investigate how spurious correlation in the training set impacts OOD detection. Our results suggest that the detection performance is severely worsened when the correlation between spurious features and labels is increased in the training set. We further show insights on detection methods that are more effective in reducing the impact of spurious correlation, and provide theoretical analysis on why reliance on environmental features leads to high OOD detection error. Our work aims to facilitate better understanding of OOD samples and their formalization, as well as the exploration of methods that enhance OOD detection. Code is available at https://github.com/deeplearning-wisc/Spurious_OOD.

Same State, Different Task: Continual Reinforcement Learning without Interference

Downloads

Next from AAAI 2022

Deepfake Network Architecture Attribution

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Same State, Different Task: Continual Reinforcement Learning without Interference

.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 2022

Deepfake Network Architecture Attribution

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads