United States

Counterfactual Regret Minimization algorithms are the most popular way of estimating the Nash Equilibrium in imperfect-information zero-sum games. In particular, Deepstack -- the state-of-the-art Poker bot -- employs the so-called Deep Counterfactual Value Network (DCVN) to learn the Counterfactual Values (CFVs) associated with various states in the game. Each CFV is a multiplication of two factors: (1) the probability that the opponent would reach a given state in a game, which can be explicitly calculated from the input data, and (2) the expected value (EV) of a payoff in that state, which is a complex function of the input data, hard to calculate. In this paper, we propose a simple yet powerful modification to the CFVs estimation process, which consists in utilizing a deep neural network to estimate only the EV factor of CFV. This new target setting significantly simplifies the learning problem and leads to a much more accurate CFVs estimation. A direct comparison, in terms of CFVs prediction losses, shows a significant prediction accuracy improvement of the proposed approach (DEVN) over the original DCVN formulation (relatively by 9.18-15.70%, depending on particular settings). Furthermore, the application of DEVN improves the theoretical lower bound of the error by 29.05-31.83% compared to the DCVN pipeline. Additionally, DEVN is able to achieve the goal using significantly smaller, and faster to infer, networks. While the proposed modification may seem to be of a rather technical nature, it, in fact, presents a fundamentally different approach to the overall process of learning and estimating CFVs, since the distributions of the training signals differ significantly between DCVN and DEVN. The former estimates CFVs, which are biased by the probability of reaching a given game state, while training the latter relies on a direct EV estimation, regardless of the state probability. In effect, the learning signal of DEVN presents a better estimation of the true value of a given state, thus allowing more accurate CFVs estimation.

AAAI 2023

Don&#39;t Predict Counterfactual Values, Predict Expected Values Instead

gtep: imperfect information

app: games

ml: reinforcement learning algorithms

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.

Don't Predict Counterfactual Values, Predict Expected Values Instead

poster

Learning directed acyclic graph (DAG) that  describes the causality of observed data is a very challenging but important task. Due to the limited quantity and quality of observed data, and non-identifiability of causal graph, it is almost impossible to infer a single precise DAG. Some methods approximate the posterior distribution of DAGs to explore the DAG space via Markov chain Monte Carlo (MCMC), but the DAG space is over the nature of super-exponential growth, accurately characterizing the whole distribution over DAGs is very intractable. In this paper, we propose {Reinforcement Causal Structure Learning on Order Graph} (RCL-OG) that uses order graph instead of MCMC to model different DAG topological orderings and to reduce the problem size. RCL-OG first defines reinforcement learning with a new reward mechanism to approximate the posterior distribution of orderings in an efficacy way, and uses deep Q-learning to update and transfer rewards between nodes. Next, it obtains the probability transition model of nodes on order graph, and computes the posterior probability of different orderings. In this way, we can sample on this model to obtain the ordering with high probability. Experiments on synthetic and benchmark datasets show that RCL-OG provides accurate posterior probability approximation and achieves better results than competitive causal discovery algorithms.

Reinforcement Causal Structure Learning on Order Graph

Along with the widespread use of face identification systems, their vulnerability has become highlighted. While the existing face anti-spoofing methods can be generalized to adapt to multiple attack types, generic face anti-spoofing is still challenging in practical scenarios due to the diversity of spoof characteristics. The spoof trace disentanglement framework shows great potential for coping with both seen and unseen spoof scenarios, but the performance is largely restricted by the single-modal input. This paper focuses on this issue and presents a multi-modal disentanglement network which targetedly learns polysemantic spoof traces for more accurate and robust generic attack detection. In particular, based on the adversarial learning mechanism, a two-stream disentangling model is designed to estimate spoof patterns from the RGB and depth inputs, respectively. It effectively captures complementary spoofing clues inhering in different attacks. Furthermore, a fusion module is exploited, which recalibrates both representations at multiple stages to promote the disentanglement of each individual modality. Then it performs cross-modality aggregation for a more comprehensive spoof trace representation. Promising results have been achieved on multiple databases, demonstrating that learning polysemantic spoof trace not only performs favorably for anti-spoofing, but also is more perceptible and interpretable for humans.

Learning Polysemantic Spoof Trace: A Multi-Modal Disentanglement Network for Face Anti-spoofing

As acquiring manual labels on data could be costly, unsupervised domain adaptation (UDA), which transfers knowledge learned from a rich-label dataset to the unlabeled target dataset, is gaining increasing popularity. While extensive studies have been devoted to improving the model accuracy on target domain, an important issue of model robustness is neglected. To make things worse, conventional adversarial training (AT) methods for improving model robustness are inapplicable under UDA scenario since they train models on adversarial examples that are generated by supervised loss function. In this paper, we present a new meta self-training pipeline, named SRoUDA, for improving adversarial robustness of UDA models. Based on self-training paradigm, SRoUDA starts with pre-training a source model by applying UDA baseline on source labeled data and taraget unlabeled data with a developed random masked augmentation (RMA), and then alternates between adversarial target model training on pseudo-labeled target data and fine-tuning source model by a meta step. While self-training allows the direct incorporation of AT in UDA, the meta step in SRoUDA further helps in mitigating error propagation from noisy pseudo labels. Extensive experiments on various benchmark datasets demonstrate the state-of-the-art performance of SRoUDA where it achieves significant model robustness improvement without harming clean accuracy.

SRoUDA: Meta Self-training for Robust Unsupervised Domain Adaptation

In image denoising networks, feature scaling is widely used to enlarge the receptive field size and reduce computational costs. This practice, however, also leads to the loss of high-frequency information and fails to consider within-scale characteristics. Recently, dynamic convolution has exhibited powerful capabilities in processing high-frequency information (e.g., edges, corners, textures), but previous works lack sufficient spatial contextual information in filter generation. To alleviate these issues, we propose to employ dynamic convolution to improve the learning of high-frequency and multi-scale features. Specifically, we design a spatially enhanced kernel generation (SEKG) module to improve dynamic convolution, enabling the learning of spatial context information with a very low computational complexity. Based on the SEKG module, we propose a dynamic convolution block (DCB) and a multi-scale dynamic convolution block (MDCB). The former enhances the high-frequency information via dynamic convolution and preserves low-frequency information via skip connections. The latter utilizes shared adaptive dynamic kernels and the idea of dilated convolution to achieve efficient multi-scale feature extraction. The proposed multi-dimension feature integration (MFI) mechanism further fuses the multi-scale features, providing precise and contextually enriched feature representations. Finally, we build an efficient denoising network with the proposed DCB and MDCB, named ADFNet. It achieves better performance with low computational complexity on real-world and synthetic Gaussian noisy datasets. The source code is available at https://github.com/it-hao/ADFNet.

Adaptive Dynamic Filtering Network for Image Denoising

Conversational recommender systems (CRS) aim to employ natural language conversations to suggest suitable products to users. Understanding user preferences for prospective items and learning efficient item representations are crucial for CRS. Despite various attempts, earlier studies mostly learned item representations based on individual conversations, ignoring item popularity embodied among all others. Besides, they still need support in efficiently capturing user preferences since the information reflected in a single conversation is limited. Inspired by collaborative filtering, we propose a collaborative augmentation (COLA) method to simultaneously improve both item representation learning and user preference modeling to address these issues. We construct an interactive user-item graph from all conversations, which augments item representations with user-aware information, i.e., item popularity. To improve user preference modeling, we retrieve similar conversations from the training corpus, where the involved items and attributes that reflect the user's potential interests are used to augment the user representation through gate control. Extensive experiments on two benchmark datasets demonstrate the effectiveness of our method. Our code and data are available at https://github.com/DongdingLin/COLA.

COLA: Improving Conversational Recommender Systems by Collaborative Augmentation

Images captured in low-light environments have problems of insufficient brightness and low contrast, which will affect subsequent image processing tasks. Although most current enhancement methods can obtain high-contrast images, they still suffer from noise amplification and color distortion. To address these issues, this paper proposes a low-light image enhancement network based on multi-scale feature complementation (LIEN-MFC), which is a U-shaped encoder-decoder network supervised by multiple images of different scales. In the encoder, four feature extraction branches are constructed to extract features of low-light images at different scales. In the decoder, to ensure the integrity of the learned features at each scale, a feature supplementary fusion module (FSFM) is proposed to complement and integrate features from different branches of the encoder and decoder. In addition, a feature restoration module (FRM) and an image reconstruction module (IRM) are built in each branch to reconstruct the restored features and output enhanced images. To better train the network, a joint loss function is defined, in which a discriminative loss term is designed to ensure that the enhanced results better meet the visual properties of the human eye. Extensive experiments on benchmark datasets show that the proposed method outperforms some state-of-the-art methods subjectively and objectively.

Low-Light Image Enhancement Network Based on Multi-scale Feature Complementation

Complex query answering (CQA) is an essential task for multi-hop and logical reasoning on knowledge graphs (KGs). Currently, most approaches are limited to queries among binary relational facts and pay less attention to n-ary facts (n≥2) containing more than two entities, which are more prevalent in the real world. Moreover, previous CQA methods can only make predictions for a few given types of queries and cannot be flexibly extended to more complex logical queries, which significantly limits their applications. To overcome these challenges, in this work, we propose a novel N-ary Query Embedding (NQE) model for CQA over hyper-relational knowledge graphs (HKGs), which include massive n-ary facts. The NQE utilizes a dual-heterogeneous Transformer encoder and fuzzy logic theory to satisfy all n-ary FOL queries, including existential quantifiers (∃), conjunction (∧), disjunction (∨), and negation (¬). We also propose a parallel processing algorithm that can train or predict arbitrary n-ary FOL queries in a single batch, regardless of the kind of each query, with good flexibility and extensibility. In addition, we generate a new CQA dataset WD50K-NFOL, including diverse n-ary FOL queries over WD50K. Experimental results on WD50K-NFOL and other standard CQA datasets show that NQE is the state-of-the-art CQA method over HKGs with good generalization capability. Our code and dataset are publicly available.

NQE: N-ary Query Embedding for Complex Query Answering over Hyper-relational Knowledge Graphs

Current math word problem (MWP) solvers are usually Seq2Seq models  trained by the (one-problem; one-solution) pairs, each of which is made of a problem description and a solution showing reasoning flow to get the correct answer. However, one MWP problem naturally has multiple solution equations. The training of an MWP solver with (one-problem; one-solution) pairs excludes other correct solutions, and thus limits the generalizability of the MWP solver. One feasible solution to this limitation is to augment multiple solutions to a given problem. However, it is difficult to collect diverse and accurate augment solutions through human efforts. In this paper, we design a new training framework for an MWP solver by introducing a solution buffer and a solution discriminator. The buffer includes solutions generated by an MWP solver to encourage  the training data diversity.  The discriminator controls the quality of buffered solutions to participate in training. Our framework is flexibly applicable to a wide setting of fully, semi-weakly and weakly supervised training for all Seq2Seq MWP solvers. We conduct extensive experiments on a benchmark dataset Math23k and a new dataset named Weak12k, and show that our framework improves the performance of various MWP solvers under different settings by generating correct and diverse solutions.

Generalizing Math Word Problem Solvers via Solution Diversification

Most existing distillation methods ignore the flexible role of the temperature in the loss function and fix it as a hyper-parameter that can be decided by an inefficient grid search. In general, the temperature controls the discrepancy between two distributions and can faithfully determine the difficulty level of the distillation task. Keeping a constant temperature, i.e., a fixed level of task difficulty, is usually sub-optimal for a growing student during its progressive learning stages. In this paper, we propose a simple curriculum-based technique, termed Curriculum Temperature for Knowledge Distillation (CTKD), which controls the task difficulty level during the student's learning career through a dynamic and learnable temperature. Specifically, following an easy-to-hard curriculum, we gradually increase the distillation loss w.r.t. the temperature, leading to increased distillation difficulty in an adversarial manner. As an easy-to-use plug-in technique, CTKD can be seamlessly integrated into existing knowledge distillation frameworks and brings general improvements at a negligible additional computation cost. Extensive experiments on CIFAR-100, ImageNet-2012, and MS-COCO demonstrate the effectiveness of our method.

Curriculum Temperature for Knowledge Distillation

Only a subset of infections are actually observed in an outbreak, due to multiple reasons such as asymptomatic cases and under-reporting. Therefore, reconstructing an epidemic cascade given some observed cases is an important step in responding to such an outbreak. A maximum likelihood solution to this problem ( referred to as CascadeMLE ) can be shown to be a variation of the classical Steiner subgraph problem, which connects a subset of observed infections. In contrast to prior works on epidemic reconstruction, which consider the standard Steiner tree objective, we show that a solution to CascadeMLE, based on the actual MLE objective, has a very different structure. We design a logarithmic approximation algorithm for CascadeMLE, and evaluate it on multiple synthetic and social contact networks, including a contact network constructed for a hospital. Our algorithm has significantly better performance compared to a prior baseline.

Premium content

Don't Predict Counterfactual Values, Predict Expected Values Instead

Downloads

Next from AAAI 2023

Reinforcement Causal Structure Learning on Order Graph

Similar lecture

REMIT: Reinforced Multi-Interest Transfer for Cross-domain Recommendation