IJCAI 2021 论文列表

We study the fundamental problem of allocating indivisible goods to agents with additive preferences. We consider eliciting from each agent only a ranking of her k most preferred goods instead of her full cardinal valuations. We characterize the amount of preference information that must be elicited in order to satisfy envy-freeness up to one good and approximate maximin share guarantee, two widely studied fairness notions. We also analyze the multiplicative loss in social welfare incurred due to the lack of full information with and without fairness requirements.

We study the pairwise organ exchange problem among groups motivated by real-world applications and consider two types of group formulations. Each group represents either a certain type of patient-donor pairs who are compatible with the same set of organs, or a set of patient-donor pairs who reside in the same region. We address a natural research question, which asks how to match a maximum number of pairwise compatible patient-donor pairs in a fair and individually rational way. We first propose a natural fairness concept that is applicable to both types of group formulations and design a polynomial-time algorithm that checks whether a matching exists that satisfies optimality, individual rationality, and fairness. We also present several running time upper bounds for computing such matchings for different graph structures.

Training is one way of enabling novice workers to work on complex crowdsourcing tasks. Based on goal setting theory in psychology, we conduct a randomized experiment to study whether and how setting different goals---including performance goal, learning goal, and behavioral goal---when training workers for a complex crowdsourcing task affects workers' learning perception, learning gain, and post-training performance. We find that setting different goals during training significantly affects workers' learning perception, but does not have an effect on learning gain or post-training performance. Further, exploratory analysis helps shed light on when and why various goals may or may not work in the crowdsourcing context.

Sequential recommendation systems alleviate the problem of information overload, and have attracted increasing attention in the literature. Most prior works usually obtain an overall representation based on the user’s behavior sequence, which can not sufficiently reflect the multiple interests of the user. To this end, we propose a novel method called PIMI to mitigate this issue. PIMI can model the user’s multi-interest representation effectively by considering both the periodicity and interactivity in the item sequence. Specifically, we design a periodicity-aware module to utilize the time interval information between user’s behaviors. Meanwhile, an ingenious graph is proposed to enhance the interactivity between items in user’s behavior sequence, which can capture both global and local item features. Finally, a multi-interest extraction module is applied to describe user’s multiple interests based on the obtained item representation. Extensive experiments on two real-world datasets Amazon and Taobao show that PIMI outperforms state-of-the-art methods consistently.

Biological spiking neurons with intrinsic dynamics underlie the powerful representation and learning capabilities of the brain for processing multimodal information in complex environments. Despite recent tremendous progress in spiking neural networks (SNNs) for handling Euclidean-space tasks, it still remains challenging to exploit SNNs in processing non-Euclidean-space data represented by graph data, mainly due to the lack of effective modeling framework and useful training techniques. Here we present a general spike-based modeling framework that enables the direct training of SNNs for graph learning. Through spatial-temporal unfolding for spiking data flows of node features, we incorporate graph convolution filters into spiking dynamics and formalize a synergistic learning paradigm. Considering the unique features of spike representation and spiking dynamics, we propose a spatial-temporal feature normalization (STFN) technique suitable for SNN to accelerate convergence. We instantiate our methods into two spiking graph models, including graph convolution SNNs and graph attention SNNs, and validate their performance on three node-classification benchmarks, including Cora, Citeseer, and Pubmed. Our model can achieve comparable performance with the state-of-the-art graph neural network (GNN) models with much lower computation costs, demonstrating great benefits for the execution on neuromorphic hardware and prompting neuromorphic applications in graphical scenarios.

Much of the focus on explanation in the field of artificial intelligence has focused on machine learning methods and, in particular, concepts produced by advanced methods such as neural networks and deep learning. However, there has been a long history of explanation generation in the general field of constraint satisfaction, one of the AI's most ubiquitous subfields. In this paper we survey the major seminal papers on the explanation and constraints, as well as some more recent works. The survey sets out to unify many disparate lines of work in areas such as model-based diagnosis, constraint programming, Boolean satisfiability, truth maintenance systems, quantified logics, and related areas.

Recently introduced self-supervised methods for image representation learning provide on par or superior results to their fully supervised competitors, yet the corresponding efforts to explain the self-supervised approaches lag behind. Motivated by this observation, we introduce a novel visual probing framework for explaining the self-supervised models by leveraging probing tasks employed previously in natural language processing. The probing tasks require knowledge about semantic relationships between image parts. Hence, we propose a systematic approach to obtain analogs of natural language in vision, such as visual words, context, and taxonomy. We show the effectiveness and applicability of those analogs in the context of explaining self-supervised representations. Our key findings emphasize that relations between language and vision can serve as an effective yet intuitive tool for discovering how machine learning models work, independently of data modality. Our work opens a plethora of research pathways towards more explainable and transparent AI.

Deep neural networks (DNNs) have became one of the most high performing tools in a broad range of machine learning areas. However, the multilayer non-linearity of the network architectures prevent us from gaining a better understanding of the models’ predictions. Gradient based attribution methods (e.g., Integrated Gradient (IG)) that decipher input features’ contribution to the prediction task have been shown to be highly effective yet requiring a reference input as the anchor for explaining model’s output. The performance of DNN model interpretation can be quite inconsistent with regard to the choice of references. Here we propose an Adversarial Gradient Integration (AGI) method that integrates the gradients from adversarial examples to the target example along the curve of steepest ascent to calculate the resulting contributions from all input features. Our method doesn’t rely on the choice of references, hence can avoid the ambiguity and inconsistency sourced from the reference selection. We demonstrate the performance of our AGI method and compare with competing methods in explaining image classification results. Code is available from https://github.com/pd90506/AGI.

Recently, generative approaches have been used effectively to provide definitions of words in their context. However, the opposite, i.e., generating a usage example given one or more words along with their definitions, has not yet been investigated. In this work, we introduce the novel task of Exemplification Modeling (ExMod), along with a sequence-to-sequence architecture and a training procedure for it. Starting from a set of (word, definition) pairs, our approach is capable of automatically generating high-quality sentences which express the requested semantics. As a result, we can drive the creation of sense-tagged data which cover the full range of meanings in any inventory of interest, and their interactions within sentences. Human annotators agree that the sentences generated are as fluent and semantically-coherent with the input definitions as the sentences in manually-annotated corpora. Indeed, when employed as training data for Word Sense Disambiguation, our examples enable the current state of the art to be outperformed, and higher results to be achieved than when using gold-standard datasets only. We release the pretrained model, the dataset and the software at https://github.com/SapienzaNLP/exmod.

K-Means++ and its distributed variant K-Means|| have become de facto tools for selecting the initial seeds of K-means. While alternatives have been developed, the effectiveness, ease of implementation,and theoretical grounding of the K-means++ and || methods have made them difficult to "best" from a holistic perspective. We focus on using triangle inequality based pruning methods to accelerate both of these algorithms to yield comparable or better run-time without sacrificing any of the benefits of these approaches. For both algorithms we are able to reduce distance computations by over 500×. For K-means++ this results in up to a 17×speedup in run-time and a551×speedup for K-means||. We achieve this with simple, but carefully chosen, modifications to known techniques which makes it easy to integrate our approach into existing implementations of these algorithms.

Non-convex optimization is often involved in artificial intelligence tasks, which may have many saddle points, and is NP-hard to solve. Evolutionary algorithms (EAs) are general-purpose derivative-free optimization algorithms with a good ability to find the global optimum, which can be naturally applied to non-convex optimization. Their performance is, however, limited due to low efficiency. Gradient descent (GD) runs efficiently, but only converges to a first-order stationary point, which may be a saddle point and thus arbitrarily bad. Some recent efforts have been put into combining EAs and GD. However, previous works either utilized only a specific component of EAs, or just combined them heuristically without theoretical guarantee. In this paper, we propose an evolutionary GD (EGD) algorithm by combining typical components, i.e., population and mutation, of EAs with GD. We prove that EGD can converge to a second-order stationary point by escaping the saddle points, and is more efficient than previous algorithms. Empirical results on non-convex synthetic functions as well as reinforcement learning (RL) tasks also show its superiority.

The advantages of event-sensing over conventional sensors (e.g., higher dynamic range, lower time latency, and lower power consumption) have spurred research into machine learning for event data. Unsurprisingly, deep learning has emerged as a competitive methodology for learning with event sensors; in typical setups, discrete and asynchronous events are first converted into frame-like tensors on which standard deep networks can be applied. However, over-fitting remains a challenge, particularly since event datasets remain small relative to conventional datasets (e.g., ImageNet). In this paper, we introduce EventDrop, a new method for augmenting asynchronous event data to improve the generalization of deep models. By dropping events selected with various strategies, we are able to increase the diversity of training data (e.g., to simulate various levels of occlusion). From a practical perspective, EventDrop is simple to implement and computationally low-cost. Experiments on two event datasets (N-Caltech101 and N-Cars) demonstrate that EventDrop can significantly improve the generalization performance across a variety of deep networks.

Event-based cameras have attracted increasing attention due to their advantages of biologically inspired paradigm and low power consumption. Since event-based cameras record the visual input as asynchronous discrete events, they are inherently suitable to cooperate with the spiking neural network (SNN). Existing works of SNNs for processing events mainly focus on the task of object recognition. However, events from the event-based camera are triggered by dynamic changes, which makes it an ideal choice to capture actions in the visual scene. Inspired by the dorsal stream in visual cortex, we propose a hierarchical SNN architecture for event-based action recognition using motion information. Motion features are extracted and utilized from events to local and finally to global perception for action recognition. To the best of the authors’ knowledge, it is the first attempt of SNN to apply motion information to event-based action recognition. We evaluate our proposed SNN on three event-based action recognition datasets, including our newly published DailyAction-DVS dataset comprising 12 actions collected under diverse recording conditions. Extensive experimental results show the effectiveness of motion information and our proposed SNN architecture for event-based action recognition.

Multiwinner elections have proven to be a fruitful research topic with many real world applications. We contribute to this line of research by improving the state of the art regarding the computational complexity of computing good committees. More formally, given a set of candidates C, a set of voters V, each ranking the candidates according to their preferences, and an integer k; a multiwinner voting rule identifies a committee of size k, based on these given voter preferences. In this paper we consider several utilitarian and egailitarian OWA (ordered weighted average) scoring rules, which are an extensively researched family of rules (and a subfamily of the family of committee scoring rules). First, we improve the result of Betzler et al. [JAIR, 2013], which gave a O(n^n) algorithm for computing winner under the Chamberlin Courant rule (CC), where n is the number of voters; to a running time of O(2^n), which is optimal. Furthermore, we study the parameterized complexity of the Pessimist voting rule and describe a few tractable and intractable cases. Apart from such utilitarian voting rules, we extend our study and consider egalitarian median and egalitarian mean (both committee scoring rules), showing some tractable and intractable results, based on nontrivial structural observations.

Symbolic knowledge can provide crucial inductive bias for training neural models, especially in low data regimes. A successful strategy for incorporating such knowledge involves relaxing logical statements into sub-differentiable losses for optimization. In this paper, we study the question of how best to relax logical expressions that represent labeled examples and knowledge about a problem; we focus on sub-differentiable t-norm relaxations of logic. We present theoretical and empirical criteria for characterizing which relaxation would perform best in various scenarios. In our theoretical study driven by the goal of preserving tautologies, the Lukasiewicz t-norm performs best. However, in our empirical analysis on the text chunking and digit recognition tasks, the product t-norm achieves best predictive performance. We analyze this apparent discrepancy, and conclude with a list of best practices for defining loss functions via logic.

We propose an analysis of Probably Approximately Correct (PAC) identification of an ϵ-best arm in graph bandit models with Gaussian distributions. We consider finite but potentially very large bandit models where the set of arms is endowed with a graph structure, and we assume that the arms' expectations μ are smooth with respect to this graph. Our goal is to identify an arm whose expectation is at most ϵ below the largest of all means. We focus on the fixed-confidence setting: given a risk parameter δ, we consider sequential strategies that yield an ϵ-optimal arm with probability at least 1-δ. All such strategies use at least T*(μ)log(1/δ) samples, where R is the smoothness parameter. We identify the complexity term T*(μ) as the solution of a min-max problem for which we give a game-theoretic analysis and an approximation procedure. This procedure is the key element required by the asymptotically optimal Track-and-Stop strategy.

Fine-Grained Entity Typing (FGET) is a task that aims at classifying an entity mention into a wide range of entity label types. Recent researches improve the task performance by imposing the label-relational inductive bias based on the hierarchy of labels or label co-occurrence graph. However, they usually overlook explicit interactions between instances and labels which may limit the capability of label representations. Therefore, we propose a novel method based on a two-phase graph network for the FGET task to enhance the label representations, via imposing the relational inductive biases of instance-to-label and label-to-label. In the phase 1, instance features will be introduced into label representations to make the label representations more representative. In the phase 2, interactions of labels will capture dependency relationships among them thus make label representations more smooth. During prediction, we introduce a pseudo-label generator for the construction of the two-phase graph. The input instances differ from batch to batch so that the label representations are dynamic. Experiments on three public datasets verify the effectiveness and stability of our proposed method and achieve state-of-the-art results on their testing sets.

Low-light image enhancement exhibits an ill-posed nature, as a given image may have many enhanced versions, yet recent studies focus on building a deterministic mapping from input to an enhanced version. In contrast, we propose a lightweight one-path conditional generative adversarial network (cGAN) to learn a one-to-many relation from low-light to normal-light image space, given only sets of low- and normal-light training images without any correspondence. By formulating this ill-posed problem as a modulation code learning task, our network learns to generate a collection of enhanced images from a given input conditioned on various reference images. Therefore our inference model easily adapts to various user preferences, provided with a few favorable photos from each user. Our model achieves competitive visual and quantitative results on par with fully supervised methods on both noisy and clean datasets, while being 6 to 10 times lighter than state-of-the-art generative adversarial networks (GANs) approaches.

This paper surveys the recent attempts at leveraging machine learning to solve constrained optimization problems. It focuses on surveying the work on integrating combinatorial solvers and optimization methods with machine learning architectures. These approaches hold the promise to develop new hybrid machine learning and optimization methods to predict fast, approximate, solutions to combinatorial problems and to enable structural logical inference. This paper presents a conceptual review of the recent advancements in this emerging area.